No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
A Self Monitoring and Analyzing System for Solar Power Station using IoT and Data Mining Algorithms
Abstract
Renewable energy sources are gaining a significant research attention due to their economical and sustainable characteristics. In particular, solar power stations are considered as one of the renewable energy systems that may be used in different locations since it requires a lower installation cost and maintenance than conventional systems, despite the fact that they require less area. In most of the small generating stations, space occupancy is controlled by placing the equipment on an open terrace. However, for large-scale power generating stations, acres of land are required for installation. Human employers face a challenging task in maintaining such a large area of power station. Through IoT and data mining techniques, the proposed algorithm would aid human employers in detecting the regularity of power generation and failure or defective regions in solar power systems. This allows performing a quick action for the fault rectification process, resulting in increased generating station efficiency.
... As a core component of photovoltaic power plants, the fault detection and diagnosis technology of photovoltaic modules is a difficult topic in the industry. However, traditional photovoltaic module fault detection methods often rely on manual inspection and offline testing, which have low efficiency and high False Detection Rate (FDR), making it difficult to meet the operation and maintenance needs of large-scale photovoltaic power plants [1][2]. In recent years, remote sensing technology has been extensively applied in the monitoring and management of photovoltaic power plants due to its high efficiency and wide coverage. ...
... When processing images, bilateral filtering not only eliminates noise but also preserves edges and details in the image, which is a major advantage [14][15]. The bilateral filtering is displayed in (2 ...
... The data are classified according to the minimum Euclidean distance to achieve the preliminary classification of hot-spots, as shown in (11). 2 arg min ( , ) ( ) ...
With the rapid advancement of renewable energy, fault detection of photovoltaic modules has become a key link to ensure their efficient operation. The study first utilizes remote sensing technology to obtain high-resolution images of photovoltaic power plants, and then uses the Deeplabv3+model to segment the images and identify faulty components. Combining remote sensing technology with Deeplabv3+ model, fast and accurate photovoltaic module fault detection can be achieved. The research results indicated that bilateral filtering and gamma filtering algorithms showed superior performance in testing, with the highest indicator evaluation results. Meanwhile, the structural similarity index value was also very close to 1. The error of the improved K-means was mainly concentrated between 0.000 and 0.014, while the traditional K-means was mainly distributed between 0.022 and 0.051. This method can detect faults in photovoltaic modules, which has significant advantages over traditional methods. It provides a new and efficient method for photovoltaic module fault detection, which helps to optimize the operational efficiency and reliability of photovoltaic power plants and promote the sustainable development of renewable energy.
... For instance, there needs to be irradiance and wind available and this availability depends on randomness of the resources. Data mining and machine learning techniques are often employed to predict this availability in order to investigate the system's behavior in the future [4,5]. ...
... Moreover, the Internet of Things (IoT) has been used to oversee solar power stations [4]. As these panels often need a vast area to install large-scale systems, it is crucial to find the right place and also analyze functionality of the panels in real-time tasks. ...
... Also, various data mining methods are used to predict solar cell's energy production. However, a new finding proposes a hybrid method incorporating machine learning algorithms and statistical methods is going to perform better in terms of PV energy predictions [4,5,7]. ...
Designing and manufacturing a system in the current industrial world cannot be accomplished without addressing safety related issues. For this purpose, system reliability is a powerful tool to ensure that failure probability of the system is below an accepted level while the system is operational. A commonly used approach to deal with these considerations is to define a performance function for the system in order to investigate its reliability. In this case, renewable energy systems (RESs) are not different. When a wind turbine, as a RES, is designed, its reliability cannot be ignored or underestimated. Therefore, stable and efficient models are needed to make sure that the turbine remains operational and is able to safely generate electricity power. In this paper, a new approach is proposed to set up a reliability analysis model for the wind turbines. The introduced model takes two important factors, i.e. the wind speed and the wind angle, and their probability distributions into account. These two factors are indeed considered as random variables to design a new system performance function and set up the new model in order to investigate wind turbine's reliability.
... It plays a key role in applications like SCADA systems, integral to smart grids, collecting data from sensors, cameras, and IoT devices across the power grid for optimal energy grid functioning [66]. Applications of IoT in power systems are vast, for instance, it has been used to measure adaptive solar irradiation for photovoltaic systems [68], [69]; another example is given in [70], in which IoT is used to assist power electronics for modern power systems; moreover, in reference [71] can be found that IoT is employed for monitor energy flow in smart grids. However, challenges such as service latency and energy consumption in edge computing environments persist. ...
... [38], [39], [73], [40]- [42], [49], [64], [69]- [71] Smart Grid Components, ...
... [46], [61], [78], [62], [63], [69], [73]- [77] ...
The primary contributions of this paper include the systematic organization of existing research and an in-depth analysis of significant milestones in the field of CPPS, leading to the development of a taxonomy for categorizing various drivers. Furthermore, this paper elucidates current strategies for defining clear terms, models, methodologies, and attributes essential to cybersecurity policies within CPPS. The incorporation of relevant standards employed in the CPPS domain is also a paramount aspect of this review. In addition to these contributions, the paper identifies areas warranting further research and highlights emerging trends within CPPS, aiming to offer valuable insights to industry practitioners and to catalyze future research endeavors.
... It plays a key role in applications like SCADA systems, integral to smart grids, collecting data from sensors, cameras, and IoT devices across the power grid for optimal energy grid functioning [66]. Applications of IoT in power systems are vast, for instance, it has been used to measure adaptive solar irradiation for photovoltaic systems [68], [69]; another example is given in [70], in which IoT is used to assist power electronics for modern power systems; moreover, in reference [71] can be found that IoT is employed for monitor energy flow in smart grids. However, challenges such as service latency and energy consumption in edge computing environments persist. ...
... [38], [39], [73], [40]- [42], [49], [64], [69]- [71] Smart Grid Components, ...
... [46], [61], [78], [62], [63], [69], [73]- [77] ...
The primary contributions of this paper include the systematic organization of existing research and an in-depth analysis of significant milestones in the field of CPPS, leading to the development of a taxonomy for categorizing various drivers. Furthermore, this paper elucidates current strategies for defining clear terms, models, methodologies, and attributes essential to cybersecurity policies within CPPS. The incorporation of relevant standards employed in the CPPS domain is also a paramount aspect of this review. In addition to these contributions, the paper identifies areas warranting further research and highlights emerging trends within CPPS, aiming to offer valuable insights to industry practitioners and to catalyze future research endeavors.
... Shakya, aimed at the problem that solar power plants are prone to faults and defects, and the efficiency of manual monitoring is low and difficult, which affects the efficiency of power plants, built a self-monitoring system for solar power plants Based on DM technology. The system could obtain and analyze relevant data from the IoT, so as to predict and monitor the status of the solar power plant, quickly monitor the fault area, and improve the power generation efficiency of the power plant [9]. Edastama et al. used the apriori to mine and analyze the glasses transaction data, so as to help enterprises formulate marketing plans and increase the sales of glasses [10]. ...
... In formula (8), X is the dataset where the data object i x is located. The average density of data points in this dataset can be deduced from formulas (6), (7), and (8), as shown in formula (9). ...
... The system provided in Shakya (2021), based on the generated current and voltage from the solar panels, produces a maintenance alert. In comparison to the solar panel's calibrated values based on various solar radiations, observations from the solar panel systems were made. ...
... Maintenance alert based on the generated current and voltage (Shakya 2021) 2021 Notifies the maintenance team when there is a significant change in the amount of power produced by the solar panels. ...
The Internet of Things (IoT) stands out as one of the most captivating technologies of the current decade. Its ability to connect people and things anytime and anywhere has led to its rapid expansion and numerous impactful applications that enhance human life. With billions of connected devices and substantial power and infrastructure requirements, the IoT system can pose a threat to the environment. However, the IoT’s vast range of resources and capabilities can also be leveraged to assist in environmental conservation in the evolution of technologies due to massive CO2 emissions, climate change, and environmental and health issues. In this study, with the two-way integration of IoT and green practices, two distinct concepts for green IoT are presented. Among green practices, energy solutions play a vital role in greening the IoT. In this study, the energy solutions for the IoT system are divided as reducing energy consumption and using green energy sources. Solutions for reducing IoT energy consumption are studied systematically through a five-layer framework to simplify its modular design and implementation. Then, the use of green energy resources is discussed for all components of the IoT ecosystem. Leveraging IoT to make the environment and other technologies green is the other concept of green IoT. IoT technology plays a crucial role in enhancing both energy management systems and the efficient harvesting of renewable energy sources. Switching to solar energy from fossil fuel energy is one of the most fundamental green practices today. In this study, the mutual relationship between solar energy harvesting and the IoT is addressed specifically. Several promising research directions in the realm of green IoT are also highlighted.
... It is scalable, cost-effective, and designed for easy deployment, ensuring continuous monitoring and performance optimization of PV plants. Additionally, Shakya et al. [147] propose in their paper an algorithm that uses IoT and data-mining techniques to monitor power generation and detect faults in solar power systems. The algorithm helps identify areas of failure or defects, enabling quick corrective actions to improve the efficiency of large-scale solar power stations. ...
In the rapidly evolving field of renewable energy, integrating Artificial Intelligence (AI) and the Internet of Things (IoT) has become a transformative strategy for improving solar energy monitoring and control. This paper provides a comprehensive survey of Artificial Intelligence of Things (AIoT) applications in solar energy, illustrating how IoT technologies enable real-time monitoring, system optimization through techniques such as Maximum Power Point Tracking (MPPT), solar tracking, and automated cleaning. Simultaneously, AI boosts these capabilities through energy forecasting, optimization, predictive maintenance, and fault detection, significantly enhancing system performance and reliability. This review highlights key advancements, challenges, and practical applications of AIoT in the solar energy sector, emphasizing its role in advancing energy efficiency and sustainability.
... With the continuous development of computer technology, especially the use of computer technology for data mining methods continue to innovate, a large amount of data generated by the power system can be analyzed by the application of data mining technology, and draw valuable conclusions [13][14]. In particular, decision tree, clustering, classification, regression analysis and other methods in data mining methods are most commonly used in power monitoring data collection, some of which can describe the current status of power monitoring and some can make predictions about future power monitoring data, which can provide valuable auxiliary effects for the formulation of power monitoring data collection strategies and the improvement of power monitoring prediction accuracy [15][16][17][18]. ...
In this paper, the data collection and preprocessing process in the power monitoring process is first described, and the collected data are preprocessed using normalization processing technique and sliding sampling technique. After that, the Local Outlier Factor (LOF) and Isolated Forest (iForest) methods are used to monitor abnormal power values. Finally, the samples and labels obtained are inputted into the improved Transformer model for tuning, training, prediction, and evaluation of the model. The results show that the improved LOF algorithm is able to significantly recognize power anomaly data. For the application effect of the improved Transformer model, it is found that the MAPE of the model is improved by 65.2% and 61.13% over the other models, and the R2 is almost close to 1. In different datasets and validation experiments, the R2 of the model is 99.63% and 97.71%, respectively, and the model’s accuracy is still extremely high. It shows that the prediction of power monitoring data using the proposed power data monitoring hair method is effective and can be applied in practice.
... This process is statistics, mathematics disciplines, modeling techniques, database technology and various, and is done using computer programs. The steps followed in the data mining process are generally as follows [28][29][30] 1. Business understanding: Critical to success in data mining studies is the definition of the business purpose for which the project is to be conducted and the way in which the success levels of the results to be obtained will be quantified. ...
This study investigates the energetic and exergetic performance of subcooled and superheated vapor compression refrigeration system utilizing data mining techniques. New-generation refrigerants R457A and R459B, considered alternatives to R404A, were utilized in the system. The analysis focuses on the impact of temperatures in the subcooling, superheating, condenser and evaporator. Data mining methods including multilayer perceptron (MLP), linear regression, M5 rules, M5P model tree (M5P), random committee and decision table models were used to estimate both energy and exergy efficiencies. The MLP model proved to be the most effective approach for predicting the energy (COP) and exergy efficiencies of R457A and R459B. When the predicted and actual COP values were compared, R-squared (R2) values of 0.9997 and 0.9994 were obtained for R457A and R459B, respectively. Similarly, the R2 values for exergy efficiency were 0.9984 and 0.9989 for the same refrigerants. These results demonstrate the successful application of data mining, in particular the MLP model, in evaluating the complex processes involved in refrigeration system performance analysis. This approach provides engineers with a fast, accurate and user-friendly method for predicting the behavior of refrigeration systems.
... LoRa technology has advantages such as low power consumption, flexible network deployment, and the ability to build networks independently [4]. LoRa has better coverage than WiFi, ZigBee, and other near-field communications, and is very suitable for building a 100% independent power IoT business architecture of power grid companies [5]. The main purpose of this study is to explore the feasibility and optimization of LoRa wireless technology in constructing a low-voltage power IoT monitoring system. ...
The operational efficiency of the current smart grid system is seriously affected by the stability of the operating system, and Internet of Things technology has good applicability in power grid information perception. This study uses LoRa technology to construct a monitoring system for the electric energy Internet of Things. Additionally, an optimization model based on a particle swarm optimization algorithm and backpropagation neural network for optimizing base station positioning and channel quality evaluation is proposed. In addition, a multi-channel adaptive frequency hopping technology has been developed. The experimental results showed that the adaptive frequency hopping technology of the system could complete frequency switching within 2 min, which was more efficient than the traditional sampling and statistical technology that took 4 min. In terms of coverage, the research method had a coverage radius of 25 km, which was superior to other communication technologies such as NB IoT and ZigBee. In terms of data transmission success rate, the research method achieved 98.11%, significantly higher than Sigfox’s 90.02%. In addition, the system had a latency of only 150ms and low power consumption. In summary, the PSO-BP LoRa model proposed in the study has high application value in smart grids and industrial environments, providing technical support for wide-area, low-power, and high-stability Internet of Things monitoring systems.
... The device should accept control commands as input and provide the realization of the measured signal in a standardized form as output. This external interface can be wired (based on standards like RS232, Ethernet, USB, etc.) or wireless (based on standards like Bluetooth, Wi-Fi, ZigBee, etc.) [27,28]. ...
The chapter is dedicated to the identification of vibroacoustic signals from power industry objects, with the goal of utilizing their informational resources for assessing the actual state of these objects. It discusses the peculiarities of identifying vibroacoustic signals and provides examples of the structure of conditional levels for the electrical equipment of a typical power station and the corresponding structure of conditional levels for a monitoring, identification, and diagnostics system for a specific power industry object, a typical power station. A mathematical model for the vibroacoustic signal of an electric machine’s bearing assembly is justified, represented as a linear random process—a stationary RLC-multiresonance noise. The identification of empirical distributions of vibroacoustic signals based on the Pearson curve system is discussed. Algorithmic software for statistically estimating empirical distribution laws of stationary vibroacoustic signals using smoothing curves from the Pearson curve system is provided. The final section of the fifth chapter presents a model and identification characteristics of vibroacoustic signals from power industry objects.
... With the development of global economic integration, complex market information has brought greater pressure to corporate decision-making. At the same time, the development of Internet-related technologies also provides support for accounting management work, [16]. Management accounting work based on data mining can conduct value analysis on massive data and provide information support for corporate decision-making. ...
With the development of the times, enterprises need to face more data in operational decision-making. Traditional data analysis strategies cannot handle the growing amount of data well, and the accuracy of analysis will also decrease when faced with uneven data types. The research uses a corporate accounting management risk analysis technology that combines big data algorithms and improved clustering algorithms. This method combines big data processing ideas with a clustering algorithm that incorporates improved weighting parameters. The results show that on the data sets DS1, DS2, and DS3, the NMI values of the GMM algorithm are all 0; while the NMI values of the MCM algorithm correspond to 0.9291, 0.9088 and 0.8881 respectively. At the same time, the Macro-F1 values of the Verify2 algorithm correspond to 0.9979, 0.9501, and 0.9375 respectively, and the recognition accuracy of the data remains above 85%. In the running time comparison, when the number of samples in the data set reaches 5,000, the calculation time of the Verify2 algorithm remains within 5 seconds. In terms of practical application results, the study selected the profitability risk indicators of 40 companies for analysis. After conducting risk ratings, it can be seen that companies No. 5, 6, 7, and 39 have the highest risk levels, and companies No. 33 and 34 have the highest risk levels. The lowest level. After conducting risk assessments on the 40 selected listed companies, the risk level of net asset income of each company remained at level 5, and the risk level of earnings per share remained at level 3. The above results show that this technology has good performance in terms of calculation accuracy and calculation time, can assess enterprise risks, and can provide data support for enterprise operation decisions.
... However, the structure of PTPP components is complex and diverse, and the power generation process involves multiple links. Its operation scheduling needs to consider many issues, including energy coupling relationships (Shakya 2021). Therefore, this study starts with the basic structure of PTPP, focuses on the internal energy flow characteristics (IEFCs) of PTPP, and establishes a PTPP self-operation and low-carbon scheduling optimization (LCSO) model. ...
Photo thermal power generation, as a renewable energy technology, has broad development prospects. However, the operation and scheduling of photo thermal power plants rarely consider their internal structure and energy flow characteristics. Therefore, this study explains the structure of a solar thermal power plant with a thermal storage system and analyzes its main energy flow modes to establish a self-operation and low-carbon scheduling optimization model for the solar thermal power plant. The simulation results of the example showed that for the self-operating model oriented towards power generation planning and peak valley electricity prices, the existence of a thermal storage system could improve the power generation capacity and revenue of the photovoltaic power plant. For example, when the capacity of the thermal storage system was greater than 6 h, the penalty for insufficient power generation in the simulation result was 0 to 1224.6 k $, and the carbon emissions decreased from 26.4 × 10³ ton to 22.1 × 10³ ton. Compared with the existing literature, this study provides a more comprehensive and systematic solution through detailed energy flow analysis and optimization model. The research has practical and far-reaching significance for promoting the development of clean energy technology, improving the sustainable utilization of renewable energy, and optimizing the overall performance of the energy system.
... SIP protocol is used to communicate with the video image acquisition and processing module, and the collected video data is transmitted to ARM, which then analyzes the obtained images through the video difference algorithm in DSP. When human violations such as large machinery approaching and pedestrians climbing the tower are found, the software can be linked with the call device to send an alarm to the staff [10]. At the same time, the background monitoring center MMS platform will receive on-site alarm information in the form of MMS real-time sent to the staff, the network server will synchronize the message with the PC, and through the mobile phone login system server for re-query. ...
The author proposes an intelligent early-warning system for preventing external damage of transmission lines. The system uses TI-TMS320DM6446 as the core, the peripheral circuit configuration and video monitoring; The moving objects captured by PTZ camera are detected and identified by using mixed Gaussian model, background difference and minimum tangent matrix, and alarm signals are provided. According to the particularity of the power supply of the equipment on the transmission line, the basic power management of the system is analyzed in detail. A reliable power management scheme is designed. The practical application proves that this method has good real-time performance and has obvious effect on preventing power cable damage by force.
... Bhau et al. designed and implemented Arduino based PV power plant monitoring system where the PV module is connected to a resistive load [14]. A self-monitoring system is proposed for maintenance and operation of a solar PV system in [15]. An energy monitoring system for solar power plant is presented based on 2W solar panel and battery load in [16]. ...
... By analyzing and mining production data, enterprises can identify potential problems and bottlenecks in resource utilization and make refined adjustments and optimizations. This will bring higher resource utilization efficiency and cost savings, thereby improving the economic benefits of the enterprise [5]. The sustainable manufacturing production process monitoring system can also provide more accurate prediction and decision support for enterprises. ...
The Internet of Things technology, as an emerging means of information technology, provides new possibilities for achieving sustainable manufacturing. This article explores sustainable manufacturing production process monitoring methods based on Internet of Things technology and analyzes their impact on economic benefits. The monitoring system of sustainable manufacturing production process is established by combining sensor network, cloud computing, Big data analysis, and other technical means. By real-time collection, transmission, and analysis of key parameters in the production process, comprehensive monitoring of the production process is achieved. The effectiveness of the production process monitoring system based on Internet of Things technology has been verified through analysis of actual industrial manufacturing. This system can monitor key indicators such as energy consumption, waste emissions, and production efficiency in real-time during the production process, and provide corresponding optimization suggestions through data analysis. Through real-time monitoring and data analysis, enterprises can timely identify problems and bottlenecks in the production process, take corresponding optimization measures, reduce energy consumption and waste emissions, improve production efficiency, and achieve maximum economic benefits. The results indicate that sustainable manufacturing production process monitoring based on IoT technology is a solution with potential economic benefits.
... Owing to the economic and sustainable characteristics, the RE is drawing considerable attention in research [1]. Solar energy has several benefits despite more RE being available. ...
Today, Solar Photovoltaic (SPV) energy, an advancing and attractive clean technology with zero carbon emissions, is widely used. It is crucial to pay serious attention to the maintenance and application of Solar Power Generation (SPG) to harness it effectively. The design was more costly, and the automatic monitoring is not precise. The main objective of the work related to designed and built up the Internet of Things (IoT) platform to monitor the SPV Power Plants (SPVPP) to solve the issue. IoT platform designing and Data Analytics (DA) are the two phases of the proposed methodology. For building the IoT device in the IoT platform designing phase, diverse lower-cost sensors with higher end-to-end delivery ratio, higher network lifetime, throughput, residual energy, and better energy consumption are considered. Then, Sigfox communication technology is employed at the Low-Power Wireless Area Network (LPWAN) communication layer for lower-cost communication. Therefore, in the DA phase, the sensor monitored values are evaluated. In the analysis phase, which is the most significant part of the work, the input data are first pre-processed to avoid errors. Next, to monitor the Energy Loss (EL), the fault, and Potential Energy (PE), the solar features are extracted as of the pre-processed data. The significance of utilizing the Transformation Search centered Seagull Optimization (TSSO) algorithm, the significant features are chosen as of the extracted features. Therefore, the computational time of the solar monitoring has been decreased by the Feature Selection (FS). Next, the features are input into the Gaussian Kernelized Deep Learning Neural Network (GKDLNN) algorithm, which predicts the faults, PE, and EL. In the experimental evaluation, solar generation is assessed based on Wind Speed (WS), temperature, time, and Global Solar Radiation (GSR). The systems are satisfactory and produce more power during the time interval from 12:00 PM to 1:00 PM. The performance of the proposed method is evaluated based on performance metrics and compared with existing research techniques. When compared to these techniques, the proposed framework achieves superior results with improved precision, accuracy, F-measure, and recall.
... In Shakya's proposed study [27], the primary objective is to establish a maintenance alert system contingent upon the analysis of generated current and voltage data from solar panels. The solar panel system's performance is monitored by comparing its observed values to pre-established calibrated values, which are determined based on various solar radiation conditions. ...
This research had the overarching goal of optimizing maintenance intervals and reducing the maintenance workload by enhancing accessibility for individuals lacking technical expertise in the upkeep of photovoltaic systems, with a particular focus on rooftop applications. The study achieved this objective by employing a linear regression algorithm to analyse climatic parameters such as wind speed, humidity, ambient temperature, and light intensity, collected from the installation site of a photovoltaic solar energy system. Simultaneously, the current and voltage values obtained from the system were also examined. This analysis not only facilitated the determination of power generation within the system but also enabled real-time detection of potential issues such as pollution, shadowing, bypass, and panel faults on the solar panels. Additionally, an artificial intelligence-supported interface was developed within the study, attributing any decline in power generation to specific causes and facilitating prompt intervention to rectify malfunctions, thereby ensuring more efficient system operation.
... Result. According to Shakya, [9], different students' learning capacity can be identified and the tendencies to sustain in the long term have been evaluated. The data mining of education aims at building the techniques for explaining virus data kinds occurring in the context of education. ...
In the fiercely competitive realm of sports and physical education, the application of data mining algorithms has emerged as a vital solution. Machine learning has streamlined processes, offering a seamless means of elevating the quality of education and training provided to students, particularly in the context of sports. This technological support empowers the sports education system to make more informed decisions pertaining to the physical development of aspiring athletes. In this comprehensive study, a blended approach of qualitative methods has been leveraged to gather intricate insights, enriching the overall understanding of the subject. Additionally, an in-depth exploration of articles and journals has been undertaken to scrutinize the practical implementation of data algorithm techniques geared towards enhancing physical training. The resultant findings underscore a substantial and tangible nexus between data algorithms and the domain of sports education. Of paramount significance is the central role played by data mining algorithms in augmenting performance. Notably, the National Sports Board (NSB) has extensively harnessed this technology to meticulously monitor players' on-field performance, ultimately leading to a granular comprehension of each player's capabilities. This paper emphasizes the methods of optimizing mistake detection and its joining systems for increasing the punishment in the operational procedures.
... Emamiam et al. [46] implemented different ML techniques and handled the data with different communication systems to provide efficient solutions for monitoring processes. Shakya [47] designed an IoT platform to monitor the electric parameters of large-scale PV power plants. An initial study of thermographic images was also presented by Udit Humar et al. [48] to obtain several patterns for dust detection, which results were plotted in an IoT platform. ...
Photovoltaic solar plants require advanced maintenance plans to ensure reliable energy production and maintain competitiveness. Novel condition monitoring systems based on thermographic sensors or cameras carried by unmanned aerial vehicles are being developed to provide reliable data with improved data acquisition rates. This new technique provides large volumes of thermal images, being requires advanced and robust fault detection and diagnosis techniques. This paper presents an Internet of Things platform that provides an integrated environment for analyzing thermal images. A novel approach based on hot spot detection in aerial thermographic images from photovoltaic solar plants is developed on a platform using Python, PHP, HTML, JavaScript and CSS. This work also presents a new distribution for image detection, combining two consecutive artificial neural networks, which is a novelty in the current state of the art where several authors compared the performance of different networks without combining them. A real case study with data from working photovoltaic solar plants is presented to test the reliability of the methodology. The obtained results achieved 100% accuracy for panel detection and approximately 93% accuracy for fault detection. It is concluded that photovoltaic maintenance activities can be enhanced using this platform, ensuring early fault detection and enabling effective decision-making processes.
... When a solar panel is exposed to sunlight, it generates electricity. To measure the output voltage of the solar panel, a voltage divider circuit is connected across it, which reduces the voltage to a measurable range [2,3,6,7,8,9,14,15]. The output voltage is then directed to pin A0 of the Arduino microcontroller. ...
In modern times, solar panels have become a common sight in many households as they provide electricity for various purposes. Typically, the solar panel's charges a battery, and any excess energy generated is usually wasted once the battery is fully charged. However, by utilizing this extra energy, heavy loads can be powered as well. This is where a solar power controller comes into play, which measures the parameters of the solar cell through multiple sensor and adjusts the load accordingly. When the power output of the PV cell is high, the load runs on solar power, and if the power is not sufficient, the load switches to the main supply. The load switches back to solar power when it becomes high again. Monitoring the solar cell parameters allows for real-time identification of the power produced by the solar panel.
... Shakya proposed a self-monitoring and analysis system for solar power plants using the IoT and data mining algorithms. The use of IoT technology helps human employers detect the regularity of power generation and fault or defect areas in solar systems [9]. The use of IoT technology to collect and analyze PG fault information can accurately monitor PG faults, but there is a lack of application of Geographic Information System (GIS) to accurately locate fault locations. ...
The power grid (referred to as PG for convenience) structure is becoming increasingly complex. Aiming at the problem that it is difficult for traditional PG monitoring methods to accurately detect PG faults, an intelligent PG fault monitoring system is constructed using Internet of Things (IoT) and geographic information system (GIS) to improve the effectiveness of fault monitoring. The sensor equipment is used to collect the current information in the circuit, and the change of induced current is used to judge the cause of the fault, and the fault information is transmitted to the monitoring center through communication technology. The staff can directly locate the geographical location of the fault in the visual interface. One hundred overhead lines of Xianyang Power Supply Company are selected for analysis, and the performance of the traditional PG monitoring method and intelligent PG fault monitoring system is compared. The average fault detection accuracy of the traditional PG monitoring method and the system proposed in this article is 72.0 and 94.8%, respectively. The average fault location accuracy of the traditional PG monitoring method and this system is 80.8 and 96.5%, respectively. The intelligent monitoring system of PG fault based on IoT and GIS has high accuracy in PG fault detection and fault location, which can improve the effectiveness of fault monitoring.
... The better the mining effect, the more people have made improvements based on the ID3 algorithm according to their needs, and created many new decision tree methods. Visualization technology: In order to allow users to analyze the data more clearly, the results of the data are transformed into graphs, images, Process visualization [7,21,22]. ...
With the advancement of the times, computer technology is also constantly improving, and people's requirements for software functions are also constantly improving, and as software functions become more and more complex, developers are technically limited and teamwork is not tacitly coordinated. And so on, so in the software development process, some errors and problems will inevitably lead to software defects. The purpose of this paper is to study the intelligent location and identification methods of software defects based on data mining. This article first studies the domestic and foreign software defect fault intelligent location technology, analyzes the shortcomings of traditional software defect detection and fault detection, then introduces data mining technology in detail, and finally conducts in-depth research on software defect prediction technology. Through in-depth research on several technologies, it reduces the accidents of software equipment and delays its service life. According to the experiments in this article, the software defect location proposed in this article uses two methods to compare. The first error set is used as a unit to measure the subsequent error set software error location cost. The first error set 1F contains 19 A manually injected error program, and the average positioning cost obtained is 3.75%.
... Finally, the authors describe the challenges machine learning practitioners face when working with production processes and equipment. Shakya [26] examined a self-monitoring and analysis system for a solar power plant using data mining and the internet of things (IoT). The system proposed by the author aims to provide a maintenance warning based on the current and voltage produced by the solar panels. ...
The use of refrigerants used in most refrigeration systems in use today has been or will be banned soon. Therefore, it is extremely important to search for alternative refrigerants. In this study, the thermodynamic properties of R471A, a very new refrigerant with low global warming potential, were estimated using a data mining approach. The results obtained from the data mining were compared with the actual data obtained from the REFROP program. The correlation coefficients (R2) for the saturation liquid enthalpy (hf), saturation vapor enthalpy (hg), saturation fluid entropy (sf), saturation vapor entropy (sg), superheated vapor enthalpy (hsh), superheated vapor entropy (ssh) have been found 0.9999, 0.9997, 1, 0.9884, 0.9992, and 0.9601, respectively. In addition, compared the hf, hg, sf, sg, hsh, and ssh values with the values calculated using the data mining and the actual values, and the percent error values. It was seen that the values calculated from the obtained formulations and the actual values are in good agreement. This study shows that the data mining approach can be successfully applied to determine enthalpy and entropy values for any temperature and pressure of R471A refrigerant. Thus, the determination of the thermodynamic properties of refrigerants and the simulation of vapor compression refrigeration systems become quite easy.
... The operation feature of this mode is to load all data into memory for calculation and analysis. When faced with hundreds of TB or even Pb of large-scale data, the traditional data mining algorithm is not only inefficient, but also may not be successfully implemented, resulting in the embarrassing situation of ''too much data but lack of knowledge'' (Shakya 2021;Sangaiah et al. 2021). This situation can be solved by most high-performance computers and optimization algorithms that provide the computing power required to process a large amount of data, and with the growth of data, the computing power can be improved by using clusters (Shukran et al. 2011). ...
Data mining algorithms can process target data and extract useful hidden information, which is helpful for decision making. However, current mining algorithms have some shortcomings such as time-consuming processing of big data or inability to process massive data. Since data mining technology cannot be used in the traditional cloud platform environment, it is necessary to improve the algorithm to make it more suitable for the cloud platform environment. By analyzing the actual application process of BP classification algorithm, this paper expounds the practicability of BP classification algorithm, analyzes the data mining process based on Hadoop cloud platform, and expounds the development ideas of BP classification algorithm. The source of data mining algorithm supported by cloud computing is discussed. Finally, Hadoop cloud platform. This paper designed the corresponding system architecture and data interface, and established a suitable test environment for this system, and completed the simulation experiment test through the design. The calculation time of this algorithm is proportional to the amount of data, showing a linear relationship. In data mining, the optimized BP algorithm in this paper can significantly save resources in terms of spatial features. This paper designs an optimized operating system based on Hadoop platform through comprehensive analysis and improvement algorithm.
... The operation feature of this mode is to load all data into memory for calculation and analysis. When faced with hundreds of TB or even Pb of large-scale data, the traditional data mining algorithm is not only inefficient, but also may not be successfully implemented, resulting in the embarrassing situation of "too much data but lack of knowledge" [3]. This situation can be solved by most high-performance computers and optimization algorithms that provide the computing power required to process a large amount of data, and with the growth of data, the computing power can be improved by using clusters [4]. ...
Data mining algorithms can process target data and extract useful hidden information, which is helpful for decision making. However, current mining algorithms have some shortcomings such as time-consuming processing of big data or inability to process massive data. Since data mining technology cannot be used in the traditional cloud platform environment, it is necessary to improve the algorithm to make it more adaptable to the cloud platform environment. By analyzing the actual application process of BP classification algorithm, this paper describes the practicability of BP classification algorithm, analyzes the process of data mining based on Hadoop cloud platform, and explains the development concept of BP classification algorithm. The source of data mining algorithm supported by cloud computing is discussed. Finally, based on the data mining system of Hadoop cloud platform, this paper designs the corresponding system architecture and data interface, and establishes a suitable testing environment for this system, and completes the simulation experiment test by design. It can be SEEN from the research results that the computation time of this algorithm is directly proportional to the amount of data, and it shows a linear relationship. Compared with the traditional data mining algorithm, the optimized BP algorithm in this paper can significantly save resources in terms of spatial features. This paper designs a kind of optimized operation system based on Hadoop platform through comprehensive analysis of data mining technology and improved algorithm, so as to promote the comprehensive development of data mining technology.
Monitoring an electrical panel is an activity performed to ensure the electrical panel’s condition is optimal, thus facilitating the proper distribution of electrical supply in a given location. To maintain such conditions, regular maintenance and monitoring processes are necessary for an electrical panel. Monitoring of the electrical panel should ideally be carried out routinely to ensure its proper functioning, enabling effective distribution of electrical energy. The objective of creating an Internet of Things (IoT)-based electrical panel monitoring system in this research is to facilitate technicians in monitoring and assessing the condition of electrical panels. This enables them to perform these tasks at any time and from anywhere, solely through a smartphone, without the need to physically visit each individual electrical panel location. This also serves the purpose of promptly identifying any imbalances and early damages occurring within the electrical panel before they escalate into more severe issues. This research employs the PZEM-004T sensor to measure current, voltage, and power values, while also utilizing the DHT22 sensor to measure temperature values. The acquired data will be processed using the ESP32 microcontroller, which is connected to the internet and integrated with the Blynk application on a smartphone. This enables a process of Internet of Things (IoT)-based monitoring through the smartphone interface. Additionally, the electrical panel will also be analyzed using infrared thermography to obtain the results of heat distribution mapping. The research outcomes indicate the successful creation of the electrical panel monitoring system, which can perform measurement processes. The achieved accuracy levels are also considered satisfactory. Where the accuracy rates are 98.90% for current value, 99.84% for voltage value, 98.44% for power value, and 90.60% for temperature value. The results of heat mapping obtained using infrared thermography also demonstrate favorable outcomes, wherein the temperature mapping of components within the electrical panel remains within the range of normal temperature values.
As renewable energy generation grows globally, real-time asset management is crucial, particularly for offshore and remote systems. Electric grids are rapidly adopting renewable energy generation. Currently, there is no cost-effective condition monitoring method for real-time assessment of renewable energy sources, enabling intelligent asset management decisions to optimise utilisation and prevent unforeseen problems. Transformers are key assets that connect renewable generation plants to the grid. If one fails, generation can be lost for a lengthy time. The transformer in an on-grid system steps up or down voltage as needed. Transformer monitoring is crucial to Smart Grids. Transformer monitoring also allows demand analysis—what each family, business, or commercial institution consumes, where it consumes more, and when demand peaks. By its nature most renewable generation is intermittent, which places increased stress on transformers. To achieve an efficient, better and reliable generation of solar energy, it is necessary to monitor the transformers and solar generation system continuously. Hence in this work, real time health condition monitoring of devices in solar power transmission systems is presented. This system monitors the devices in real time with the help of IoT. Understanding transformer health and performance with real-time monitoring allows developing and optimizing proactive maintenance strategies for improving the performance of solar power transmission systems.
Electrical power systems are shifting to be more intelligent, creating smart grids that employ a widespread bi-directional communication system for monitoring the grid status and improving grid assets management. This chapter presents a case study for energy community data monitoring, which aims to provide real-time data monitoring using internet of things based hardware-in-the-loop approach. The information is received from several internet of things devices connected to the different loads within the energy community. The acquired data will be transferred in real-time into the energy community digital model; therefore, it will be able to provide real-time data monitoring of different metric quantities of the community thus enhancing the energy operations management. The case study presented in this paper demonstrates the potential of internet of thing and hardware-in-the-loop techniques for real-time data monitoring and the study of several operation scenarios under real-world conditions. The data monitoring is performed for two hours duration, also, a demand response event is implemented to enhance the voltage profile of the community.
Numerous investigations and research projects carried out over the past several years in a wide range of application domains have revealed the potential of IoT (Internet of Things). Solar energy is a renewable source of energy and a sustainable foundation for human civilization; thus, the use of IoT with solar energy-powered devices has definitely been a revolutionary reformation in technology. Researchers have looked into ways to use IoT to change the network structure by recognizing different ecosystem components for intelligent solar-powered city control. Furthermore, countless studies have been made on solar monitoring and solar tracking systems using different IoT technologies in order to target better efficiency, automated control, and monitoring, maximum energy generation etc. The contribution of this study is to make aware everyone about the integration of the renewable energy with the revolution 4.0 which is the major primary topic of the current technology nowadays. Also, the major projects like smart city are being pursued in many developing countries like India and so concepts like IoT are mandatory for these major projects. Also, the solar panel efficiency may be increased and maintenance expenses decreased with the help of the Internet of Things in monitoring and optimizing the panels. As this technology may aid in managing energy usage in real time, solar power can be more consistent and adaptable to fluctuating demand. This article provides a state-of-the-art review of the application of IoT in effective solar energy utilization. The use of IoT in solar energy tracking, power point tracking, energy harvesting, smart lighting system, PV panels, smart irrigation system, solar inverters, etc., is reviewed. Hence, by merging solar power with the Internet of Things, we can provide companies and households with long-term, affordable energy solutions that help encourage responsible expansion and a better future. The outcome of this study reveals that IoT is very much successful in providing smart and efficient solar energy output from countless devices. A vast scope of work and research on IoT applications for smart solar energy utilization still exists in the future.
This work draws a systematic literature review about the use of Machine Learning based recommender systems for crop selection in agriculture, following the PRISMA protocol for systematic reviews. Agriculture is one of the vital sectors of every country’s economy and crop selection is a paramount problematic to ensure optimal yield depending on economical, technological and environmental factors. Yet, it is up to today underrepresented research thematic, although our study shows a significant increasing trend in the number of studies in the last years. We present the outline of the study, the selection process, as well as the method of content analysis and a literature review table. A detailed analysis of 40 articles published about the CR problem as well as the main achievements, and current challenges are discussed. One of the main outcomes of this study is that, in future works, much attention should be paid to crop selection by using smart and automated solutions due to the huge positive impact it has on agricultural yields, as well as incorporating more diverse recommender-systems algorithms to address this problematic. Finally, we shed light on some future perspectives worthwhile pursuing, concerning the whole ML pipeline and including model evaluation.KeywordsRecommender systemsCollaborative filteringCrop recommendationCrop selectionMachine learningAgricultural management practices
Many languages and cultures are followed by the peoples in India. Most of the peoples are known only their mother tongue. But in everyday life, the peoples are in the position to get some essence from the bills and drafts passed by the government. These bills and drafts are commonly scripted by the language Hindi and English. These languages are not known to all the peoples of India. In this case, when a draft is passed within the specific languages, individuals of different states will not get the essence of this passed draft. They require an interpreter physically to communicate the pros and cons present in the drafts, bills or amendments. In this case, to make the individuals effortlessly get the essence of the drafts or bills passed by the government, a programmed territorial dialect interpreter is required. Here, it needs some language translation like Natural language Processing. This paper concentrates on various techniques used in language translation. In this proposed method using the NLP to convert the sentence into string and for the language translation. This paper uses the knuth morris pratt for searching the string and boyer moore horspool algorithm is used to find the substrings in the string. Through this idea all the peoples can able to know the essence in the bills or drafts passed by the individual as well as by the government.KeywordsNatural language processingKnuth morris pratt string searching algorithmBoyer moore horspool algorithmSummarization
Consideration of safety is one of the current requirements to design a new system that is often implemented by defining the system failure probability. Renewable energy systems (RESs) do have the same requirements when it comes to safety and reliability. When designing a wind turbine, as a RES, its reliability is of the highest importance. So, efficient reliability models are required to ensure the turbine is working safely to generate electricity. A new model is introduced in this paper by taking into account the wind speed and the wind angle as two effective factors. These two random variables are reported to follow the Gaussian and Weibull probability distributions, and so are employed to define a limit-state function for the turbines. This limit-state function, which is also called system performance function, will then be used to find out the system failure probability.
Recently, the image reconstruction study on EIT plays a vital role in the medical application field for validation and calibration purpose. This research article analyzes the different types of reconstruction algorithms of EIT in medical imaging applications. Besides, it reviews many methods involved in constructing the electrical impedance tomography. The spatial distribution and resolution with different sensitivity has been discussed here. The electrode arrangement of various methods involved in the EIT system is discussed here. This research article comprises of adjacent drive method, cross method, and alternative opposite current direction method based on the voltage driven pattern. The assessment process of biomedical EIT has been discussed and investigated through the impedance imaging of the existent substances. The locality of the electrodes can be calculated and fixed for appropriate methods. More specifically, this research article discusses about the EIT image reconstruction methods and the significance of the alternative opposite current direction approach in the biomedical system. The change in conductivity test is further investigated based on the injection of current flow in the system. It has been established by the use of Electrical Impedance Tomography and Diffuse Optical Tomography Reconstruction Software (EDITORS) software, which is open-source software.
Low-level and medium-level leg injury patients can be operated wheelchair independently in the clinical region. The construction of an electric wheelchair is one of the solutions to operate electric wheelchair by the patients themselves. The motor is an essential part of an electrical wheelchair for driving from one place to another place. The response of the system is very important for the optimization of the system. The existing methods fail in gradual sensitivity during motion and lack of response time to the user. This article is consist of a design for optimizing the existing DC motor transfer function for the smart wheelchair. The perfect angular tuning of the derivative controller provides a better executing time for our proposed model. The smoother responses from the smart wheelchair are obtaining by the dynamic response of closed-loop control. The design of DC motors is to drive smart wheelchair as per the needs. Besides, the construction of a mathematical model for proposing a system involves the DC motor drive to the smart wheelchair arrangement. The proposed model gives independent mobility of smart wheelchair with less response time and better sensitivity. Here, the mathematical model provides the details of immediate response to the user and less execution time of the complex system process. Finally, the authors discussed future improvements to the current DC motor design in the proposed system.
Recently, fake fingerprint detection is a challenging task in the cyber-crime sector in any developed country. Biometric authentication is growing in many sectors such as internet banking, secret file locker, etc. There spoof fingerprint detection is an essential element that is used to detect spot-on fingerprint analysis. This article focuses on the implementation and evaluation of suitable machine learning algorithms to detect fingerprint liveness. It also includes the comparative study between Ridge-let Transform (RT) and the Machine Learning (ML) approach. This article emphasis on research and analysis of the detection of the liveness spoof fingerprint and identifies the problems in different techniques and solutions. The support vector machine (SVM) classifiers work with indiscriminate loads and confined grayscale array values. This leads to a liveness report of fingerprints for detection purposes. The SVM methodology classifies the fingerprint images among more than 50K of real and spoof fingerprint image collections based on this logic. Our proposed method achieves an overall Journal of ISMAC (2021) high accuracy of detection of liveness fingerprint analysis. The ensemble classifier approach model is proving an overall efficiency rate of 90.34 % accurately classifies samples than the image recognition method with RT. This recommended method demonstrates the decrement of 2.5% error rate when compared with existing methods. The augmentation of the dataset is used to improve the accuracy to detect. Besides, it gives fake fingerprint recognition and makes available future direction.
Industry 4.0 promises reductions in maintenance costs through access to digital technologies such as the Internet of Things, cloud computing and data analytics. Many of the promised benefits to maintenance are, however, dependent on the quality of the data obtained through sensors and related technologies. In this work, we consider the effect of access to different levels of deterioration data quality, resulting in partial information about the underlying state of the system being monitored, by means of sensors, on condition-based maintenance policies. The sensors may be either internal company sensors, or more informative external sensors of which access is obtained at a cost. We analyze the structure of the optimal policy, where the actions are either to perform maintenance, to pay for external sensor information or to continue system operation with internal sensor information only. We show that the optimal policy consists of at most four regions based on the believed deterioration state of the system. The analysis allows us to numerically investigate the decision maker’s willingness to pay for more informative external sensor information with respect to the level of external sensor informativeness, when compared to that of the internal sensor, and the cost thereof.
There is a rapid development in Internet of Things and Smart Grid technologies in the recent days. In this paper, an extensive survey of Internet of Things (IoT) based Smart grid environments is done. These technologies, when used in combination offer energy optimization and user friendliness in terms on monitoring and controlling of electronic devices. The software solutions, challenges such as stability in connection, communication, cost and information privacy and security is also discussed broadly. This work exposes new perspectives and knowledge for researchers who work on interdisciplinary domains.
Ubiquitous Networks powered by Wireless Sensor Networks (WSN) is cutting across many technologies assisting day-to-day human activities. This technology confers the ability to sense and surmise the external environmental factors of various ecologies. Interconnection of these sensing devices for Machine to Machine (M2M) communication leads to the origination of Internet-of-Things (IoT). Recent advancements in the technology of Internet-of-Things guides the production of smart objects that can accomplish location, identification, connection and measurement of external factors. This leads to a new type of communication paradigm between objects and humans. One of the important problem due to the population explosion that can be addressed by IoT is the Healthcare of individual human beings. Remote health monitoring is one of the greatest technology exploited in medical professionals to keep a check on the patient’s important health factors periodically. This was done in a smaller geographical area before the era of IoT. As IoT can communicate to other Internet, This remote healthcare monitoring can now be applied over a wider geographical topology. This paper extensively analyses the performance of 6LoWPAN and RPL IoT for healthcare applications. This paper especially focuses on monitoring an athlete's thermoregulation. Also, a new technique to identify and train marathon athletes to the race topography has been proposed. In this technique, each athlete is fitted with wearable sensors in their body in the training session to monitor and analyze the thermoregulation process occurring during training. After a detailed analysis of the athletes’ thermoregulation process, personal training schedules are charted down according to variation in the thermoregulation process in each athlete. This technique helps to monitor each athlete’s progress personally with less number of coaches and medical professionals leading to the prevention of unexpected death of a healthy athlete.
In construction of smart cities, Internet of Things and Fog computing have a crucial role to play which requires the need for management and exchange of large amount of information. Both Internet of Things as well as Fog computing are two predominant fields that have emerged in recent years to enable the development of transportation, tourism, industries as well as business in a proficient manner. Hence the introduction of a smart city will require proper study as well as ways to improve the strength’s of the city using technological advancement. This will also enhance the strength of city in many fronts. In this paper, we have examined the positive aspects of fog computing using an IoT architecture that is integrated with fog computing in order to address the issues of network scalability and big data processing. Accordingly, the architecture of the IoT system is built such that the smart city will be able to function in a more efficient manner by means of network transmission, information processing and intelligent perceptions.
Signal processing is considered as an efficient technique to detect the faults in three-phase induction motors. Detection of different varieties of faults in the rotor of the motor are widely studied at the industrial level. To extend further, this research article presents the analysis on various signal processing techniques for fault detection in three-phase induction motor due to the damages in rotor bar. Usually, Fast Fourier Transform (FFT) and STFT are used to analyze the healthy and faulty motor conditions based on the signal characteristics. The proposed study covers the advantages and limitations of the proposed wavelet transform (WT) and each technique for detecting the broken bar of induction motors. The good frequency information can be collected from FFT techniques for handling multiple faults identification in three-phase induction motor. Despite the hype, the detection accuracy gets reduced during the dynamic condition of the machine because the frequency information on sudden time changes cannot be employed by FFT. The WT method signal analysis is compared with FFT to propose fault detection method for induction motor. The WT method is proving better accuracy when compared to all existing methods for signal information analysis. The proposed research work has simulated the proposed method with MATLAB / SIMULINK and it helps to effectively detect the healthy and faulty conditions of the motor.
This research article focuses on industrial applications to demonstrate the characterization of current and vibration analysis to diagnose the induction motor drive problems. Generally, the induction motor faults are detected by monitoring the current and proposed fine-tuned vibration frequency method. The stator short circuit fault, broken rotor bar fault, air gap eccentricity, and bearing fault are the common faults that occur in an induction motor. The detection process of the proposed method is based on sidebands around the supply frequency in the stator current signal and vibration. Moreover, it is very challenging to diagnose the problem that occur due to the complex electromagnetic and mechanical characteristics of an induction motor with vibration measures. The design of an accurate model to measure vibration and stator current is analyzed in this research article. The proposed method is showing how efficiently the root cause of the problem can be diagnosed by using the combination of current and vibration monitoring method. The proposed model is developed for induction motor and its circuit environment in MATLAB is verified to perform an accurate detection and diagnosis of motor fault parameters. All stator faults are turned to turn fault; further, the rotor-broken bar and eccentricity are structured in each test. The output response (torque and stator current) is simulated by using a modified winding procedure (MWP) approach by tuning the winding geometrical parameter. The proposed model in MATLAB Simulink environment is highly symmetrical, which can easily detect the signal component in fault frequencies that occur due to a slight variation and improper motor installation. Finally, this research article compares the other existing methods with proposed method.
Fault detection in the transmission is a challenging task when examining the accuracy of the system. This fault can be caused by a man-made force or by using concurrent overvoltage in the power distribution line. This research focuses on two sections to handle the power transmission line problem and can be rectified as previously stated. An intelligent approach is utilized for monitoring and controlling line faults in order to improve the accuracy of the equipment in transmission line fault detection. After several iterations of the procedure, the combination of line and master unit improves the system's accuracy and reliability. The master unit identifies faulty poles in the network based on the variation of current and voltage of each node and calculates the distance between the station and the faulty node to reduce manual effort. In the proposed work, many sensors are used to detect the line fault in a network by placing the appropriate point. The pure information can be transferred to an authorized person or unit after many iterations due to knowledgeable devices. The faulty status of the pole information is displayed in the control unit by a display unit comprised of an alarm unit to alert the corresponding section using ZigBee techniques. The GSM unit provides the faulty status of an authorized person to rectify the problems immediately which further improve the reliability of the system. When compared to existing methods, our hybrid proposed method achieves a higher accuracy of 90%. This method aids to reduce the labor costs gradually to visit all-pole points instead of faulty pole points and thereby increasing the reliability of the electrical consumers.
Generally, a soil nutrients test has been performed for determining the productivity measures of any plant. It includes many challenges of environmental impacts and climate adaptation. To maintain the crop nutrients quality without affecting previous performance from the soil, it is required to minimize the challenges in the soil health sector can be increased economic returns from crop productivity. This article represents the review on improving productivity for soil nutrition. Soil nutrition was tested and assessed using the existing method, and deficiencies in the soil were identified that could be improved using some standardized methods. This productivity function of soil supply is measured by a various spatial scale which is a part of this research. The objective aims to achieve high productivity in the context of soil and also to realize environmental impact for soil functionality, productivity function, and resources information. The classification of soils corresponding multitude of approaches developed globally for potential soil productivity. The main focus is to determine strategies for the effects of a balanced nutrition system of maize-chickpea. The treatment and control can be developed and tested every year on crop yield. Besides, this research presents a future enhancement of improved productivity tests for a balanced soil nutrition system for better crop yield. The soil classification will be categorized with a knowledge base algorithm for further accuracy for the system.
This article focuses on evaluation of in-service power transformerphysical health condition using Health Index (HI) approach. The Health Index (HI) approach is applied by incorporating three key stages such as input for health index assessment, health index estimation and output health index for maintenance decision process of each transformer unit. The first stage is based on condition index, and importance index assessment and also through applying scoring and weight scheme for each test parameter. The condition index of a specific power transformer is evaluated by twelve different diagnostic tests and importance index is assessed from five different factors such as age, loading history, maintenance records, failure/faults, and its location, etc. Numerical weighting and scoring factors were assigned for every test/factor to determine the actual condition of the power transformers with regard to condition and importance aspects. In second stage, By combining the condition and importance index assessment evaluation, the numerical value called Health Index (HI) was estimated, which represent the overall health of a power transformer asset. In third stage, health index estimation results were used to plan for effective maintenance tasks. Through this approach, a case study was performed for 21 in-service power transformers belonging to Tamil Nadu electric utility. The HI results of 21 transformer units were ranked and classified into poor/failed, fair and good, which were further facilitated for Inspection, Repair, and Replacement (IRR) maintenance decisions. Thus, the study is very useful to utility maintenance engineers for better understanding the transformer physical health condition and required maintenance actions timely, which prevents unexpected failure and also reduce cost of maintenance in electric utilities.
For a clean energy source, renewable energy plays a vital role. Biomass, wind energy and solar energy used to power up the cities and large scale industries. It shows there is a gap between the generation of power and usage. Solar panel based energy generation system is familiar in many countries over a year. The adjustment of photo voltaic cell to the inclination angle of the sun is a major crisis. The sun sets an angular movement throughout the day. From dawn to set, we calculate the position of the sun. So that automatic panel adjustment can be made to increase the efficiency of the panel on generations. Another factor to note is the efficiency of the panel depends on the deposition of dust particles. The performance of the panel can improve with automatic cleaning. Internet of things devices that can sense the dust deposition on the panel and it is cleans them in a semi- automated system. With the electrostatic precipitator methodology the solar cells are isolated. The power deployment found in many countries and globally enormous demand for energy arise in this era. With the smart meter installed wecan control the energy lost and miss handled. This paper describes about positioning of the panel and removal of dust particles and a smarter way to identify the energy lost.
Solar energy forecasting represents a key element in increasing the competitiveness of solar power plants in the energy market and reducing the dependence on fossil fuels in economic and social development. This paper presents an approach for predicting solar energy, based on machine and deep learning techniques. The relevance of the studied models was evaluated for real-time and short-term solar energy forecasting to ensure optimized management and security requirements in this field while using an integral solution based on a single tool and an appropriate predictive model. The datasets we used in this study, represent data from 2016 to 2018 and are related to Errachidia which is a semi-desert climate province in Morocco. Pearson correlation coefficient was deployed to identify the most relevant meteorological inputs from which the models should learn. RF and ANN have provided high accuracies against LR and SVR, which have reported very significant errors. ANN has shown good performance for both real-time and short-term predictions. The key findings were compared with Pirapora in Brazil, which is a tropical climate region, to show the quality and reproducibility of the study.
Lithium-ion batteries have become an integral parts of our lives, and it is important to find a reliable and accurate long-term prognostic scheme to supervise the performance degradation and predict the remaining useful life of batteries. In the perspective of information fusion methodology, an interacting multiple model framework with particle filter and support vector regression is developed to realize multi-step-ahead estimation of the capacity and remaining useful life for batteries. During the multi-step-ahead prediction period, the support vector regression model with sliding windows is used to compensate the future measurements online. Thus, the interacting multiple model with particle filter can relocate the particles and update the capacity estimation. The probability distribution of the remaining useful life is also obtained. Finally, the proposed method is compared and validated with particle filter model using the benchmark data. The experimental results prove that the proposed model yields stable forecasting performance and narrows the uncertainty in remaining useful life estimation.
The independent micro-grid with photovoltaic and energy storage has the problems of unknown line resistance, large load fluctuation, large control voltage error and poor application stability. In order to solve these problems, big data mining technology is applied to the design of control algorithm, which helps to achieve the coordinated control of the independent micro-grid. Firstly, the discrete consistency controller is constructed as the implementation medium of the control algorithm, and the photovoltaic cell, energy storage unit and DC-DC converter are combined to obtain the independent micro-grid model. In this model, mining the data of the independent micro-grid, and the micro-grid operation mode is determined by the data. According to different operation modes, the goal and constraints of the coordinated control are set, and the coordinated control mode is selected. The coordinated control of the independent micro-grid with PV and energy storage is realized from three aspects: photovoltaic unit, energy storage unit and operation mode switching. Through the comparison with the traditional control algorithm, it is concluded that under the grid connected condition, the control error of the grid voltage can be effectively reduced by applying the designed control discrete algorithm, and the control error can be reduced by 2V under the island condition.
In the present-day competitive environment, industries are facing with a new crisis of shrinking profit margins. Organizations’/companies cannot ill afford quality, safety, poor environment and productivity issues. There is thus the requirement of an integrated approach towards management of maintenance. The aim is to present a framework for a programme for an effective continuous improvement of issues related to maintenance. Maintenance undoubtedly plays a key role in an organization’s long-term profitability. In this article, there is a proposal for an integrated maintenance management. The suggested proposal is based on maintenance management, maintenance operation and equipment management (predictive maintenance, preventive maintenance, total productive maintenance). This article explores the benefits of integrated maintenance management compared with the traditional maintenance approach and discusses some of the latest tools in this area.
The sustainability of the global energy production systems involves new renewable energies and the improvement of the existing ones. Photovoltaic industry is growing thanks to the development of new technologies that increase the performance of photovoltaic systems. These systems are commonly subject to harsh environmental conditions that decrease their energy production and efficiency. In addition, current photovoltaic technologies are more sophisticated, and the size of photovoltaics solar plants is growing. Under this framework, research on failures and degradation mechanisms, together with the improvement of maintenance management, becomes essential to increase the performance, efficiency, reliability, availability, safety, and profitability of these systems. To assess maintenance needs, this paper presents a double contribution: an exhaustive literature review and updated survey on maintenance of photovoltaic plants, and a novel analysis of the current state and a discussion of the future trends and challenges in this field. An analysis of the main faults and degradation mechanisms is done, including the causes, effects, and the main techniques to detect, prevent and mitigate them.
The objective of this work is to design a sensor-fault detection and diagnosis system for the Internet of Things and Cyber-Physical Systems. The challenge is, however, achieving this objective within the limited computation, memory, and energy resources of the sensors. More importantly, the detection of faults is time-sensitive, whereas the diagnosis does not necessarily need to be fast. We propose a distributed sensor-fault detection and diagnosis system based on machine learning algorithms where the fault detection block is implemented in the sensor in order to achieve output immediately after data collection. This block consists of an auto-encoder to transform the input signal into a lower-dimensional feature vector, which is then provided to a Support Vector Machine (SVM) for classification as normal or faulty. Once detected, fault diagnosis is performed at a central node, such as a network server, to reduce the computational load on the sensor. In this work, a Fuzzy Deep Neural Network (FDNN) is used for diagnosis to provide further information, such as the type of fault. Here, the input propagates through a deep neural network and a fuzzy representation process. The output of these two components is then fused through densely connected layers. This multi-modal technique learns high-level representations in the data that are missed by conventional methods. To assess the performance of the proposed model, we utilize data obtained from a healthy temperature-to-voltage converter that are then injected with five types of fault: drift, bias, precision degradation, spike, and stuck faults. The performance from fault detection is analyzed in terms of detection accuracy, area under the ROC curve (AUC-ROC), false positive rate, and F1 score. Furthermore, the efficiency of fault diagnosis is shown by the classification accuracy parameter. The experimental results show the efficiency of the proposed fuzzy learning-based model over classic neuro-fuzzy and non-fuzzy learning approaches.
There has been revolutionary developments in the healthcare industry with the advancement of technology over the past years. Internet of Things, Cloud Computing, Blockchain technology, lab-on-chip, non-invasive and minimally invasive surgeries and so on has simplified several dreadful diseases. The research as well as healthcare industry have been greatly impacted by these new technologies. Clinical exams and self-health tracking can be done by means of miniaturized healthcare sensors that are powered by IoT. They help in early diagnosis and treatment guidance by clinicians at remote locations without directly being in contact with the users. The access control structures and inconsistent security policies have been a hinderance in meeting the security requirements of these data. Blockchain based smart contracts and enterprise-distributed ledger framework can be used for monitoring the vital signs of the patient. This enables accessing medical information of patients globally at any time along with immutable and extensive history log. In comparison with the traditional patient monitoring system, the proposed system offers better monitoring, improved connectivity and enhanced data security.
This article deals with Remaining Useful Life (RUL) estimation of Lead Acid Battery using a probabilistic approach which is Bayesian inference of Linear Regression. RUL estimation of lead acid battery plays a very crucial role as it can prevent the catastrophic failure for the system in which it is used to serve as a power supply mainly in automobiles. Although there are various methods for age estimation of lead acid battery, machine learning algorithms always played a major role in the same. In this paper we have implemented one such algorithm for the RUL estimation. Bayesian approach is a probabilistic method which can be used for predicting the RUL of the battery. Firstly, we present a framework for feature extraction and then the RUL estimation model is trained on Bayesian inference of Linear Regression. The proposed approach is then applied to the collected dataset from five differently aged batteries which have undergone some charging/discharging and load cycle test. The experiment result shows that the proposed approach can improve the accuracy of RUL estimation than the regular methods.
The demand of highway lighting system is ubiquitous but its operation contributes to extensive financial cost and concerning environmental implications. For this reason, recent researches have investigated possible solutions to boost the efficiency of the existing lighting system. However, the ultimate guide for green energy enabled smart highway lighting system is still lacking in terms of quality and comprehensiveness. The purpose of this paper is to discuss divergent proceedings in the literature to establish procedures of designing and developing energy efficient green highway lighting system, taking into account performance and environmental impact perspectives. A complete taxonomy is presented to identify and organize the literature into several categories, including fundamental design principles with their advantages, disadvantages and research challenges. This paper also intends to give a possible framework to the readers to bridge the gaps among the existing studies. These findings are anticipated to inform researchers and policymaker on perceiving the benefits of the ameliorated energy efficiency in the highway lighting set-up. Furthermore, open issues identified in this paper will pave the way on achieving future highway lighting systems that are not only facilitating safe and seamless driving experience, but also energy-efficient for environmental sustainability.
Automatic crack defect detection for multicrystalline solar cells is a challenging task, owing to inhomogeneously textured background, disturbance of crystal grains pseudo defects, and low contrast between crack defect and background. In this paper, a novel structure-aware-based crack defect detection scheme (SACDDS) is proposed. Firstly, the structure features of crack defect and randomly distributed crystal grains are analyzed, and corresponding mathematical models are used to represent two structure features. Secondly, according to Hessian eigenvalues of the above mathematical models, the identification functions of linear-structure and blob-structure are obtained. Then, a novel structure similarity measure (SSM) function is designed by using the identification functions of two structures, which can highlight crack defect, suppress crystal grains simultaneously. It significantly weakens the interference of inhomogeneous texture and obtains uniform background. Further, in order to overcome non-uniform response of crack region and extract crack defect, a tensor voting-based non-maximum suppression (TV-NMS) method is developed. It improves the uniformity of crack defect response and extracts candidate crack defect pixels. Finally, an effective morphological operation is applied to remove non-crack pixels and complete crack defect can be located in the EL images. Experimental results show that the proposed method can completely extract crack defect in the inhomogeneously textured background, which is well effective and outperforms the previous methods.