Figure 1 - uploaded by Thiago D'Angelo
Content may be subject to copyright.
Rollers failures and its consequences: (a) Roller seizure that shaves the rubber of the BC, as demonstrated on (b). (c) A bearing failure affecting only the central roller. (d) Another bearing failure, this time, also affecting the idler holder. (e) An impact roller on fire and (f) rollers damaged by this event.

Rollers failures and its consequences: (a) Roller seizure that shaves the rubber of the BC, as demonstrated on (b). (c) A bearing failure affecting only the central roller. (d) Another bearing failure, this time, also affecting the idler holder. (e) An impact roller on fire and (f) rollers damaged by this event.

Source publication
Article
Full-text available
Frequent and accurate inspections of industrial components and equipment are essential because failures can cause unscheduled downtimes, massive material, and financial losses or even endanger workers. In the mining industry, belt idlers or rollers are examples of such critical components. Although there are many precise laboratory techniques to as...

Contexts in source publication

Context 1
... extreme circumstances, the fire may spread to other equipment in the port, what is a dangerous situation entailing high financial losses. Figure 1 demonstrates examples of defective rollers with different consequences. ...
Context 2
... IoU metric is calculated between the areas of bounding boxes inferred by the model and bounding boxes of the ground truth. Figure 10 shows the Precision x Recall curve, as well as the AP and R metrics, for each class of the database. The overall AP and AR metrics were 88.3% and 91.8% respectively, which gives our model an F 1 score of 90.0%. ...
Context 3
... Figure 11 illustrates how the method works. For this image we used only the detector for REC, therefore, central and lateral rollers were not identified, but two regions of interest were delimited (Figure 11a). ...
Context 4
... Figure 11 illustrates how the method works. For this image we used only the detector for REC, therefore, central and lateral rollers were not identified, but two regions of interest were delimited (Figure 11a). Please note that there is a roller with a high temperature on the other side of the belt, but it is disregarded as we did not train it to detect opposite lateral rollers. ...
Context 5
... this context, it represents an example of an undesired interference, like the reflectance or a hot point, that was ignored as it is not part of the region of interest. Thus, only points inside the region selected are considered for temperature gathering by the morphological method, as demonstrated in the Figure 11b. The morphological processing starts with reading the temperature data stored in each pixel within the bound boxes. ...
Context 6
... this end, we used areas with size greater than 19 pixels, where each pixel is connected to 8 pixels that also have a temperature greater or equal to 45 • C. Finally, such regions can be plotted on the original image to highlight the defect to an inspector. The Figure 11b shows the result. ...
Context 7
... we classify the ROI as a defect only if the distance is lower than the threshold. Figure 12 illustrates this procedure. The cyan point represents the bounding box center, and the cyan circle represents the area within the distance threshold. ...
Context 8
... it is classified as a normal region (blue). Figure 12 also shows that this method reduces the number of false detections, but does not eliminate all of them. The roller on the far left of the figure has a region misclassified as a defect. ...
Context 9
... extreme circumstances, the fire may spread to other equipment in the port, what is a dangerous situation entailing high financial losses. Figure 1 demonstrates examples of defective rollers with different consequences. ...
Context 10
... IoU metric is calculated between the areas of bounding boxes inferred by the model and bounding boxes of the ground truth. Figure 10 shows the Precision x Recall curve, as well as the AP and R metrics, for each class of the database. The overall AP and AR metrics were 88.3% and 91.8% respectively, which gives our model an F 1 score of 90.0%. ...
Context 11
... Figure 11 illustrates how the method works. For this image we used only the detector for REC, therefore, central and lateral rollers were not identified, but two regions of interest were delimited (Figure 11a). ...
Context 12
... Figure 11 illustrates how the method works. For this image we used only the detector for REC, therefore, central and lateral rollers were not identified, but two regions of interest were delimited (Figure 11a). Please note that there is a roller with a high temperature on the other side of the belt, but it is disregarded as we did not train it to detect opposite lateral rollers. ...
Context 13
... this context, it represents an example of an undesired interference, like the reflectance or a hot point, that was ignored as it is not part of the region of interest. Thus, only points inside the region selected are considered for temperature gathering by the morphological method, as demonstrated in the Figure 11b. The morphological processing starts with reading the temperature data stored in each pixel within the bound boxes. ...
Context 14
... this end, we used areas with size greater than 19 pixels, where each pixel is connected to 8 pixels that also have a temperature greater or equal to 45 • C. Finally, such regions can be plotted on the original image to highlight the defect to an inspector. The Figure 11b shows the result. ...
Context 15
... we classify the ROI as a defect only if the distance is lower than the threshold. Figure 12 illustrates this procedure. The cyan point represents the bounding box center, and the cyan circle represents the area within the distance threshold. ...
Context 16
... it is classified as a normal region (blue). Figure 12 also shows that this method reduces the number of false detections, but does not eliminate all of them. The roller on the far left of the figure has a region misclassified as a defect. ...

Citations

... Roller damage detection method based on the measurement of transverse vibrations of the conveyor belt mines, these are not optimal solutions, which is why inspection robots [15,46] or drones [8] are being used more and more commonly. However, there are locations where their use is not possible due to the limited space of the excavation, e.g. ...
Article
Full-text available
The article presents the detection of damage to rollers based on the transverse vibration signal measured on the conveyor belt. A solution was proposed for a wireless measuring device that moves with the conveyor belt along of the route, which records the signal of transverse vibrations of the belt. In the first place, the research was conducted in laboratory conditions, where a roller with prepared damage was used. Subsequently, the process of validating the adopted test procedure under real conditions was performed. The approach allowed to verify the correctness of the adopted technical assumptions of the measuring device and to assess the reliability of the acquired test results. In addition, an LSTM neural network algorithm was proposed to automate the process of detecting anomalies of the recorded diagnostic signal based on designated time series. The adopted detection algorithm has proven itself in both laboratory and in-situ tests.
... A blocked idler causes the abrasion process to accumulate on the limited surface of the tube. An important element of prevention is the supervision of the correct installation of idler sets [160,161]. ...
Article
The belt is the most important working element of any conveyor. Damages to this element cause costly downtimes in the operation of the transport system. Due to the working conditions and contact with the material, it is exposed to damage. Proper operation can be the way to effectively extend the life cycle of a belt. The experience of users shows that the majority of belt damages are due to improper operation of the conveyor or the technical condition of components. The article presents an overview of the types of belt damages and the authors’ classification of their causes, not directly related to the quality of production of the belt itself. For each type of damage, the right method of prevention and condition monitoring is presented. Decision diagrams were constructed to form the basis for proper management of the work and durability of the belt.
... Most recent demands on cars, trailers and trains are a challenge and an opportunity to capitalize on new vehicle technologies and also in the process reap developmental benefits economically. Vehicle trains creates additional economic development opportunities by improving the quality of transportation that is of benefit, such as reducing energy spending and decreasing its reliance on most foreign and local transportation medium (see Dern et al, 1947;Fenn & Marsh, 1935;Fugl-Meyer et al, 1980;Carvalho et al, 2020). Some of its hurdles to development and possible solutions to transportation means are vividly illustrated in Table 1. ...
Article
Full-text available
One of the most important components of engine systems on power train is its sole purpose of transmitting engine power to its tracks. This paper demonstrates an engine system by illustrating belt conveyors attached to power train which serves as a booster for motor drives and also speed control for its induction unit. The emphases was mostly on the converters by modeling the frequency converter element which requires an AC voltage and Speed controllers or torque controls. A real time simulation was made and frequent observation of its motor controls was conducted by running simulations on all control motors and comparing the bit error rate of each machine. The result shows synchromesh transmission or accelerated patterns based on friction, the strand velocity, air Gap and torque controls, and this would help build advanced engine drive systems for future power trains on heavy machines.
... Inspection robotic devices are increasingly common, such as a terrestrial articulated mobile robotic device with an attached manipulator arm to inspect BCs through color and thermal images, audio information, and vibrations measured on the conveyor (Garcia et al., 2019) or diagnostics based on acoustic signals using an autonomous legged inspection robot (Skoczylas et al., 2021). It is also possible to inspect with an unmanned aerial vehicle (UAV) with a coupled thermal camera that flies over BC structures and maps divergences from the usual conditions (Carvalho et al., 2020) or using wheel robots with the same technology (Szrek et al., 2020). Morales et al. (2017) present a technology review of idler condition-based monitoring systems for critical overland conveyors in open-pit mining applications. ...
Article
Full-text available
Conveyor belts play an essential role in mining, making belt splicing a critical operation in the maintenance process. Currently, this procedure is performed manually and can last up to 48 h, exposing operators to risks while performing the task. Additionally, the process is error prone, and the splicing quality depends directly on the maintenance team’s expertise. As a first attempt to automate belt splicing preparation, the Instituto Tecnológico Vale, together with the Brazilian mining company Vale S.A., is investigating the use of a rotary rubber cutting tool attached to a robotic manipulator arm. In this work, we propose a new multistep concept for automating the traditional belt splicing process. Our proposal includes a virtual environment simulator, allowing the verification of critical components of the system prior to real-world execution: the appropriate sensor set for modeling the conveyor belt and validation of the manipulator motions to remove the rubber using the cutting tool. After virtual validation, we developed two instrumented test benches for experimental validation: a belt modeling prototype using a small-scale industrial manipulator and a customized instrumented bench with a cutting tool prototype, developed to evaluate the efforts involved in the rubber removal process. This paper focuses on rubber cutting bench design and modeling to calculate the resulting forces and moments applied to the robotic manipulator during the process. The simulated and preliminary real-world experiments have shown that the magnitude of these efforts is compatible with a robot working class with a 200 kg payload. In this sense, the proposed robotic and mechanical system design is a feasible first step to fully automating belt splicing preparation within mining environments.
... The identification of the damage in mine infrastructure via image analysis (RGB, IR) was presented in [31]. The authors analyzed the existing idlers inspection techniques and proposed their own solution based on an Unmanned Aerial Vehicle and an RGB and IR camera sensory system. ...
... A legged robot was proposed for inspection in [43], a wheeled robot equipped with a manipulator was discussed in [44], and finally, a specially designed robot with a self-leveling system and hybrid wheel-legged locomotion was discussed in [45]. Other solutions based on robots suspended on a rope above the conveyor [46] or UAV [31] are also interesting solutions. ...
Article
Full-text available
Complex mechanical systems used in the mining industry for efficient raw materials extraction require proper maintenance. Especially in a deep underground mine, the regular inspection of machines operating in extremely harsh conditions is challenging, thus, monitoring systems and autonomous inspection robots are becoming more and more popular. In the paper, it is proposed to use a mobile unmanned ground vehicle (UGV) platform equipped with various data acquisition systems for supporting inspection procedures. Although maintenance staff with appropriate experience are able to identify problems almost immediately, due to mentioned harsh conditions such as temperature, humidity, poisonous gas risk, etc., their presence in dangerous areas is limited. Thus, it is recommended to use inspection robots collecting data and appropriate algorithms for their processing. In this paper, the authors propose red-green-blue (RGB) and infrared (IR) image fusion to detect overheated idlers. An original procedure for image processing is proposed, that exploits some characteristic features of conveyors to pre-process the RGB image to minimize non-informative components in the pictures collected by the robot. Then, the authors use this result for IR image processing to improve SNR and finally detect hot spots in IR image. The experiments have been performed on real conveyors operating in industrial conditions.
... Inspection robots for mining applications have already been developed by several research teams [12][13][14][15][16][17][18][19][20]. A specific case is related to conveyor belt inspection [15,[21][22][23][24][25][26][27]. ...
Article
Full-text available
Mechanical systems (as belt conveyors) used in the mining industry, especially in deep underground mines, must be supervised on a regular basis. Unfortunately, they require high power and are spatially distributed over a large area. Till now, some elements of the conveyor (drive units) have been monitored 24 h/day using SCADA systems. The rest of the conveyor is inspected by maintenance staff. To minimize the presence of humans in harsh environments, we propose a mobile inspection platform based on autonomous UGV. It is equipped with various sensors, and in practice it is capable of collecting almost the same information as maintenance inspectors (RGB image, sound, gas sensor, etc.). Till now such experiments have been performed in the lab or in the mine, but the robot was controlled by the operator. In such a scenario the robot is able to record data, process them and detect, for example, an overheated idler. In this paper we will introduce the general concept of an automatic robot-based inspection for underground mining applications. A framework of how to deploy the inspection robot for automatic inspection (3D model of the tunnel, path planing, etc.) are defined and some first results from automatic inspection tested in lab conditions are presented. Differences between the planned and actual path are evaluated. We also point out some challenges for further research.
... UAV refers to a vehicle that flies automatically or semi-automatically according to a pre-programmed route without an actual inspector boarding it. Carvalho et al. [89] conducted a semi-automatic examination of accessibility and mobility using a system equipped with an infrared camera on the UAV. Deane et al. [90] conducted a study on the detection of defects in aerospace structures that reduced inspection time and cost by performing PPT and PCT signal processing on images acquired using UAV. ...
Article
Full-text available
Non-destructive testing (NDT) is a broad group of testing and analysis techniques used in science and industry to evaluate the properties of a material, structure, or system for characteristic defects and discontinuities without causing damage. Recently, infrared thermography is one of the most promising technologies as it can inspect a large area quickly using a non-contact and non-destructive method. Moreover, thermography testing has proved to be a valuable approach for non-destructive testing and evaluation of structural stability of materials. Pulsed thermography is one of the active thermography technologies that utilizes external energy heating. However, due to the non-uniform heating, lateral heat diffusion, environmental noise, and limited parameters of the thermal imaging system, there are some difficulties in detecting and characterizing defects. In order to improve this limitation, various signal processing techniques have been developed through many previous studies. This review presents the latest advances and exhaustive summary of representative signal processing techniques used in pulsed thermography according to physical principles and thermal excitation sources. First, the basic concept of infrared thermography non-destructive testing is introduced. Next, the principle of conventional pulsed thermography and signal processing technologies for non-destructive testing are reviewed. Then, we review advances and recent advances in each signal processing. Finally, the latest research trends are reviewed.
... In recent times, there has been a sharp growth in the application of UAVs [77]. They are being used in surveillance [78,79], 2D and 3D mapping [80,81], agriculture [82], search and rescue [83,84], military applications [85], mining [86], and many more. ...
Article
In a world with rapidly growing levels of automation, robotics is playing an increasingly significant role in every aspect of human endeavour. In particular, many types of mobile robots are increasingly being utilised in places and for tasks that are difficult and dangerous for humans. Although the vision of fully autonomous mobile robotic platforms that can perform complex tasks without direct guidance from a human operator is compelling, the reality is that the current state of robotics technology is still a long way from being able to achieve this capability outside of very narrowly constrained contexts. Technology advancement for improved mobile robotic teleoperation and remote control is vital to enable robotic vehicles to operate with increasing autonomy levels while allowing for effective remote operation when task complexity is too great for the autonomous systems. Being motivated to bridge this gap, we present a review of existing teleoperation methods and enhancement techniques for control of mobile robots. After defining teleoperation, we provide a detailed review that analyses, categorises, and summarises existing mobile robot teleoperation methods. Next, we highlight existing enhancement techniques that have been applied to these teleoperation methods, along with their relative advantages and disadvantages. Finally, several promising future research directions are identified. The paper concludes with a discussion of research challenges and future research possibilities.
... Belt conveyors are widely recognized as interesting objects for condition monitoring [1]. There are plenty of articles focused on the diagnostics of drive units (gearboxes, pulleys) using vibration analysis or infrared thermography [2][3][4][5][6] or temperature [7]. The conveyor belt has been defined as one of the most expensive component in conveyor, thus various NDT techniques (image analysis, laser scanning, magnetic field measurement) have been applied [8][9][10][11][12][13]. ...
... Researches on idlers were rather focused on rolling resistance, their energy consumption, load distribution, and failure analysis until now [14][15][16][17][18], however, some infrared thermography applications can be found in [5,8,9], among others. ...
... As mentioned, due to the number of idlers located along the conveyor, there is a need to have a method for quick and automatic acoustic measurement and analysis. Thus, there are intensive works on inspection robots equipped with various sensors and data acquisition systems, including sound recording [5,6,8,9,[49][50][51]. In the paper, we propose a combination of robotics inspection, acoustic data measurement, and finally signal processing for fault detection in idlers. ...
Article
Full-text available
Belt conveyors are commonly used for the transportation of bulk materials. The most characteristic design feature is the fact that thousands of idlers are supporting the moving belt. One of the critical elements of the idler is the rolling element bearing, which requires monitoring and diagnostics to prevent potential failure. Due to the number of idlers to be monitored, the size of the conveyor, and the risk of accident when dealing with rotating elements and moving belts, monitoring of all idlers (i.e., using vibration sensors) is impractical regarding scale and connectivity. Hence, an inspection robot is proposed to capture acoustic signals instead of vibrations commonly used in condition monitoring. Then, signal processing techniques are used for signal pre-processing and analysis to check the condition of the idler. It has been found that even if the damage signature is identifiable in the captured signal, it is hard to automatically detect the fault in some cases due to sound disturbances caused by contact of the belt joint and idler coating. Classical techniques based on impulsiveness may fail in such a case, moreover, they indicate damage even if idlers are in good condition. The application of the inspection robot can “replace” the classical measurement done by maintenance staff, which can improve the safety during the inspection. In this paper, the authors show that damage detection in bearings installed in belt conveyor idlers using acoustic signals is possible, even in the presence of a significant amount of background noise. Influence of the sound disturbance due to the belt joint can be minimized by appropriate signal processing methods.
... Wodecki et al. [25] proposed a monitoring system that could identify major possible causes of machine failure events using the operational parameters of LHD in mines. Carvalho et al. [26] developed a system that could automatically identify the failure of a roller, one of the important components of a belt conveyor, by combining a thermal imaging camera with an unmanned aerial vehicle (UAV). ...
Article
Full-text available
This study proposes a method for diagnosing problems in truck ore transport operations in underground mines using four machine learning models (i.e., Gaussian naïve Bayes (GNB), k-nearest neighbor (kNN), support vector machine (SVM), and classification and regression tree (CART)) and data collected by an Internet of Things system. A limestone underground mine with an applied mine production management system (using a tablet computer and Bluetooth beacon) is selected as the research area, and log data related to the truck travel time are collected. The machine learning models are trained and verified using the collected data, and grid search through 5-fold cross-validation is performed to improve the prediction accuracy of the models. The accuracy of CART is highest when the parameters leaf and split are set to 1 and 4, respectively (94.1%). In the validation of the machine learning models performed using the validation dataset (1500), the accuracy of the CART was 94.6%, and the precision and recall were 93.5% and 95.7%, respectively. In addition, it is confirmed that the F1 score reaches values as high as 94.6%. Through field application and analysis, it is confirmed that the proposed CART model can be utilized as a tool for monitoring and diagnosing the status of truck ore transport operations.