Joan Colomer

• University of Girona

Heating, ventilation, and air conditioning (HVAC) systems account for up to 40% of the total energy consumption in buildings. Improving the modeling of HVAC components is necessary to optimize energy efficiency, maintain indoor thermal comfort, and reduce their carbon footprint. This work addresses the lack of a general methodology for data preproc...

The objective of microgrid operation is to supply the energy demanded by the loads at minimum cost. To achieve this goal, new tools are being proposed in the literature, such as the use of optimal schedulers in the field of multi-vector management systems. An optimal scheduler provides the hourly schedule of the flexible loads that exist in a micro...

Today, in the field of energy, the main goal is to reduce emissions with the aim of maintaining a clean environment. To reduce energy consumption from fossil fuels, new tools for micro-grids have been proposed. In the context of multi-vector energy management systems, the present work proposes an optimal scheduler based on genetic algorithms to man...

Background In recent years, the monitoring of occupant presence patterns has become an imperative for building energy optimization. Very often, there is a significant discrepancy between the building energy performance predicted at the design stage and the actual performance rendered during the building operation. This stems from the difference in...

Background In recent years monitoring of user behavior became an imperative for building energy optimization. Very often there is a significant discrepancy between predicted building energy performance at the design stage and the actual one rendered during the building operation. This stems from the difference in users’ behavior. In spite of that,...

This paper presents a complete methodology, together with its implementation as a web application, for monitoring smart buildings. The approach uses unfold-Principal Component Analysis (unfold-PCA) as a batch projection method and two statistics, Hotelling’s T-squared (T²) and the squared prediction error (SPE), for alarm generation resulting in tw...

This article focuses on the issue of a sustainable space-use in public facilities and beneficial arrangement of services. Uncorrelated facility planning and service programming as well as environmental factors cause discrepancies between space demand and space supply leading to space overuse or underuse. To enhance the functional and economic effic...

A model for day-ahead scheduling of batteries and branch switches in the low voltage grid, considering forecasts uncertainties, is proposed. The objective is to reduce the energy losses of the distribution lines and avoid critical events such as congestions or over and under-voltages in the local network. Simulations of different day-ahead situatio...

This paper deals with inefficient space management of public real estate resulting in discrepancy between the amount of space required for provision of public services and the amount of space that is available. This situation causes either waste of resources, in case of underused spaces, or affects quality of service if the space is overused. To ad...

This work presents the development of a web service module for monitoring energy consumption data recorded in buildings. This software is based on the application of Multivariate Principal Component Analysis (MPCA) to implement a fault detection and diagnosis tool that detects anomalies or misbehaviors in energy consumptions. The result can be inte...

This article reports on the issue of arrangement of public services. We argue that public services offered together in one building are often combined without consideration of citizens’ needs. It is not unusual for services to be arranged only according to organizational charts of public administration bodies or space availability. Thus we postulat...

An accurate short-term load forecasting system allows an optimum daily operation of the power system and a suitable process of decision-making, such as with regard to control measures, resource planning or initial investment, to be achieved. In a previous work, the authors demonstrated that an SVR model to forecast the electric load in a non-reside...

The paper describes an ongoing work to embed several services in a Smart City architecture with the aim of achieving a sustainable city. In particular, the main goal is to identify services required in such framework to define the requirements and features of a reference architecture to support the data-driven methods for energy efficiency monitori...

Pubic facilities provide spatial conditions for public services delivery. In the ideal case the amount of space available in a facility should be adjusted to the amount of space demanded by the service. However demand for space is very susceptible to fluctuations of the socio-economic environment and changes with time. This causes maladjustment bet...

A complete methodology for energy building monitoring based on Principal Component Analysis (PCA) is proposed. The method extends the Unfolding or Multiway Principal Component Analysis (MPCA) used in statistical batch process control in terms of building and neighbourhood monitoring. Relationships between energy consumption and independent variable...

Correct interpretation of measured process data is essential for the supervision of control systems. Qualitative representation of signals based on episodes is presented. A new classification of episodes based on the second derivative sign is performed. Qualitative information associated to each episode is completed with quantitative information. T...

The electric grid is evolving. Smart grids and demand response systems will increase the performance of the grid in terms of cost efficiency, resilience and safety. Accurate load forecasting is an important issue in the daily operation and control of a power system. A suitable short term load forecasting will enable a utility provider to plan the r...

Multiway Principal Component Analysis (MPCA) and Case-Based Reasoning (CBR) approaches are applied in a biological nutrient removal process. The goal is monitoring of normal and abnormal operation conditions in this process. MPCA is used as a compression tool where with few variables the process can be described, as well as, to detect batches with...

In this paper Principal Component Analysis (PCA) is proposed for monitoring electric consumption of building. PCA allows modeling correlations between independent variables (weather, calendar) and energy consumption at different time scales (hourly, daily, weekly monthly). Multiway principal component analysis (MPCA) is used to model time dependenc...

This paper focuses on process diagnosis based on symptoms described by qualitative trends extracted from signals. Main contributions are a new similarity algorithm between qualitative sequences and a generalised approach for on-line diagnosis based on that similarity measure. Process situations are identified by converting sensor time series into q...

In this paper we put forward two ideas for monitoring the Smart Cities initiative in a better way. In developing the first idea, we study past and on-going initiatives in the field of sustainable cities and livable cities and their respective monitoring indicators to demonstrate that not only is a set of indicators needed for efficient monitoring,...

Aerobic granulation from floccular sludge is difficult to detect in first stages with the naked eye. This work proposes a combination of multi-way principal components and case-based reasoning to predict the granulation state of a sequencing batch reactor, based solely on the on-line registered profiles of common sensors (i.e. pH, dissolved oxygen...

Background The main goal of wastewater treatment is to obtain high quality effluent. This study proposes a methodology to estimate in real-time the effluent quality in a biological nutrient removal (BNR) sequencing batch reactor (SBR) process. ResultsThis is achieved by: (i) detecting the batch quality; and (ii) predicting the classification of the...

The main idea of this paper is to develop a methodology for process monitoring, fault detection and predictive diagnosis of a WasteWater Treatment Plant (WWTP). To achieve this goal, a combination of Multiway Principal Component Analysis (MPCA) and Case-Based Reasoning (CBR) is proposed. First, MPCA is used to reduce the multi-dimensional nature of...

This work is focused on defining and implementing a new similarity criterion for sequences of symbolic representations. The proposed algorithm returns a normalized index related to the degree of matching between sequences of qualitative labels. Performance of this method has been tested in the classification of voltage sags (transient reduction of...

The diagnosis of qualitative variables in certain types of batch processes requires time to measure the variables and obtain the final result of the released product. With principal component analysis (PCA) any abnormal behavior of the process can be detected. This study proposes a method that uses contribution plots as fault signatures (FS) on the...

Voltage sags, whether they occur in transmission or distribution systems, may severely damage the loads connected to the power system. As these problems could cost a great deal financially, electric utilities are very interested in finding the origins of sags, that is, whether they have been originated in the transmission network (high voltage (HV)...

This paper presents a tool developed to obtain qualitative trend representations from signals, Qualtras. The aim of such a type of description is to offer an understandable representation of process behavior based on the concept of qualitative episode. The tool is intended to be used as a numeric to qualitative interface for supervisory application...

A methodology based on Principal Component Analysis (PCA) and clustering is evaluated for process monitoring and process analysis of a pilot-scale SBR removing nitrogen and phosphorus. The first step of this method is to build a multi-way PCA (MPCA) model using the historical process data. In the second step, the principal scores and the Q-statisti...

Occurring in transmission or distribution networks, voltage sags (transient reductions of voltage magnitude) can cause serious damage to end-use equipment (domestic appliances, precision instruments, etc.) and industrial processes (PLC and controller resets, time life reduction, etc.) resulting in important economic losses. We present a statistical...

The design of control, estimation or diagnosis algorithms most often assumes that all available process variables represent the system state at the same instant of time. In actual networked systems, this is never true, because of unknown deterministic or stochastic transmission delays that are introduced by the communication network. When diagnosis...

The work presented in this paper belongs to the power quality knowledge area and deals with the voltage sags in power transmission and distribution systems. Propagating throughout the power network, voltage sags can cause plenty of problems for domestic and industrial loads that can financially cost a lot. To impose penalties to responsible party a...

The design of control, estimation or diagnosis algorithms most often assumes that all available process variables represent the system state at the same instant of time. However, this is never true in current network systems, because of the unknown deterministic or stochastic transmission delays introduced by the communication network. During the d...

In this paper, we introduce a new framework for classification of short duration voltage reductions in the area of Power Quality Monitoring using Multiway Principal Component Analysis (MPCA). Firstly, we recast the sags occurred in High Voltage (HV) and Medium Voltage (MV) lines in a format which is suitable for MPCA. Then, MPCA technique is emplo...

After each Ariane mission, data flight analysis is intended to prevent not only the upcoming failures but also even the slightest drop of launcher performances. In this work, the benefits of using Principal Component Analysis (PCA) to achieve this goal have been evaluated. PCA method has confirmed, in a simple example, its capacity for fault detect...

The paper focuses on the development of a classification strategy to identify critic situation in batch process control. Data acquired from a batch execution is reduced by means of multiway principal component analysis in order to be assessed according to the statistical model of the process. Multiple situations have been categorized by a classific...

A diagnostic structure based on modular expert system architecture is presented in this paper. An illustrative example shows how expert knowledge is used to deduce fault situations. In this example, qualitative representation of numerical variables of process is used to interface expert knowledge and process variables. The goal is to use this new i...

This paper discusses the analysis of differential pressure signals in a blast furnace stack by using principal component analysis (PCA) and qualitative trend analysis (QTA) based on episodes. These methods can work jointly or separately and are applied using two toolboxes developed within the European CHEM project.1 The objective in this paper is t...

A pilot plant sequencing batch reactor (SBR) was applied in a wastewater treatment plant treating urban wastewater focused on carbon and nitrogen removal. From an initial predefined step-feed cycle definition, the evolution of the on-line monitored pH and calculated oxygen uptake rate (OUR) were analysed in terms of knowledge extraction. First, the...

The data set of batch biological and biotechnological processes can be organized in a three-way data matrix. In this paper the usefulness of different PCA approaches for monitoring is analyzed. Different ways of unfolding and scaling of data have been applied to a pilot-scale SBR data. PCA is used to reduce the dimensionality and to remove the non-...

A combination of Multivariate Statistical Process Control (MSPC) and an automatic classification algorithm is applied to monitor a Waste Water Treatment Plant (WWTP). The goal of this work is to evaluate the capabilities of these techniques for assessing the actual state of a WWTP. The research was performed in a pilot WWTP operating with a Sequenc...

Control de la qualitat de la Xarxa elèctrixa

This paper focuses on the on-line Oxygen Uptake Rate (OUR) as a new tool for identifying the state of the plant during the aerobic phases of the SBR cycle and as a control parameter to optimize the SBR process. A real-time control system has been designed to adjust the aerobic phases length using on-line OUR as the endpoint of the aerobic phase. Th...

This paper presents the development and implementation of a real-time control strategy based on end-point detection of biological reactions responsible for carbon and nitrogen removal in order to optimize the sequencing batch reactor (SBR) process. The control system is an algorithm that automatically adjusts the cycle length to the influent wastew...

This work is focused on controlling the Dissolved Oxygen in a SBR pilot plant fed with real wastewater. Two different implementations of Dissolved Oxygen control are presented. On the one hand, an ON/OFF control produces oscillations around the set point, this cycling behavior affects other process variables and makes the supervisory tasks more dif...

Experiences in heterogeneous application domains treated with dif- ferent data mining approaches are presented in this paper: Case based reasoning and self organising maps have used to diagnose beams and pipes after analys- ing their responses using wavelet decomposition. Also case based reasoning methodology has been used to improve electronic cir...

A challenging problem that motivates this work is the network delay efiects in residual computation. Residuals are assumed to be identically zero in fault-free situations whereas deviations from zero alert the presence of fault in the system. In practice residuals are not identically zero due to various factors (measurements noises, modelling uncer...

La qualitat d'ona en el servei elèctric

Nowadays there are several Artificial Intelligence techniques developed to diagnose electronic circuits. But, in the analog electronic circuit field, it is much left to solve. The purpose of this paper is to contribute with a new methodology. It is intended to develop a methodology to be applied to analog electronic circuits that is based on the im...

There are plenty of methods proposed for analog electronic circuit diagnosis, but the most popular ones are the fault dictionary techniques. Admitting more cases in a fault dictionary can be seen as a natural development towards a CBR system. The proposal of this paper is to extend the fault dictionary towards a Case Based Reasoning system. The cas...

This paper discusses about voltage sags fault lo-cation using a temporal and phasorial descriptors. A dimen-sionality reduction technique is used to extract the significant features from voltage sags descriptors and a Neural Network is applied to located the fault.

In order to solve the problems by the perturbations in a voltage distribution system, is necessary the detection and identification of the different disturbing incidents: short-circuits, harmonic distortions, notchings, voltage dips (sags), etc. If it is possible, this detections can be effected automatically, without manual intervention, and as fa...

A qualitative trends representation based on episodes is proposed for the Oxidation Reduction Potential (ORP) and pH signals of a Sequencing Batch Reactor (SBR) for Wastewater treatment process. Tha aim of this work is showing the qual-itative representation for assessing important situations in the process and obtaining knowledge about wastewater...

A combination of Multivariate Statistical Process Control (MSPC) and an automatic classification algorithm has been devel- oped to be applied in a Waste Water Treatment Plant (WWTP). The goal of this work is to make a situation assessment of a WWTP to guarantee the normal behaviour of the process. The WWTP used is a Sequencing Batch Reactor (SBR)....

This contribution is focused on the formal definition of a di- agnosis methodology for dynamics systems founded on the Case Based Reasoning (CBR) principle. The proposal assumes the existence of sig- nals sensible to process behavior that can be transformed into symptoms. A general framework for diagnosis is proposed with learning capabilities cent...

Actualmente se dispone de numerosas técnicas de Inteligencia Artificial desarrolladas para diagnosticar circuitos electrónicos. Pero en el campo de los circuitos electrónicos analógicos todavía queda mucho por resolver. El propósito de este artículo es el de contribuir con una nueva metodología. La intención es desarrollar una metodología para circ...

En este artículo, se presenta una propuesta de clasificación para la categorización de clientes del banco Tatra Bank (Eslovaquia). En esta propuesta se realiza un análisis estadístico para extraer información útil acerca de los clientes del banco, seguido por una estrategia de clasificación basada en el algoritmo LAMDA (Learning Algorithm for Multi...

Resumen Existen multitud de aproximaciones al estudio de los sistemas que evolucionan en el tiempo. Este artículo revisa trabajos previos relacionados con series tem-porales y evalúa tres aproximaciones enfocadas a la comparación de dicho tipo de series. Dos aproxima-ciones están basadas en los principios del algoritmo Dynamic Time Warping (DT W Ab...

The new regulatory frameworks have converted the reliability issue and its increase, in a critical issue. This document presents the evaluation of reliability indexes and the development of restoration strategies for ten transmission substations of the Colombian transmission company (ISA). An example is also presented emphasizing the reduction of E...

There have been some Artificial Intelligence applications developed for electronic circuits diagnosis, but much remains to be done in this field, above all in the analog domain. The purpose of this paper is not to give a general solution, but to contribute with a new methodology. Our aim is to develop a methodology for analog circuit diagnosis base...

This work is focused on evaluation of symptoms for situation assessment. Symptoms are described as episodes representing qualitative trends. The aim is to reproduce reasoning and evaluation performed by experienced operators observing signal evolution. The use of qualitative representations of signal trends is proposed to manage previous experience...

This paper discuss about voltage sags classification using a previous characterization of this type of electrical disturbances. An automatic classification algorithm, working under a non-supervised strategy is proposed. The method helps to determine the possible fault cause and location of voltage sags using a prototype definition and the pertinenc...

The existing methods to characterise voltage sags use the lowest of the three voltages and the longest duration. Basic quantitative | qualitative voltage sag attributes have been obtained from recorded waveforms in order to increase the number of measures to characterise a voltage sag. Also a method to compare voltage sags have been proposed and ap...

This paper discusses the analysis of differential pressure signals in a blast furnace stack, by a hybrid approach based on temporal representation of process trends and classification techniques. The objective is to determine whether these can be used to predict unstable conditions (slips). First, episode analysis is performed on each individual tr...

This work shows how to supervise a set of controllers designed by different specification to be applied at requested constrained trajectory for the autonomous mobile robot. In this paper are explained part of the control structure from local controllers to the agent level, the communication between the high supervisor and the local controller are d...

Situation assessment in complex systems is often achieved by expert operators taking into account evolution of signals and comparing it with previous experiences. The criteria used by operators to compare actual situations with previous ones are not easily explainable and in fact they are part of the cognitive procedure. This paper proposes to use...

Case Based Reasoning (CBR) is proposed as a methodology for the diagnosis and fine tuning of PID controllers. CBR methodology is used to retrieve knowledge acquired in previous situations of process operation. Then, this knowledge is represented as associations between symptoms and diagnostics. These associations are conceived as cases. Symptoms ar...

Situation assessment in complex systems is often achieved by expert operators taking into account evolution of signals and comparing it with previous experiences. The criteria used by operators to compare actual situations with previous ones are not easily explainable and in fact they are part of the cognitive procedure. This paper proposes to use...

The paper focuses on taking advantage of large amounts of data that are systematically stored in plants (by means of SCADA systems), but not exploited enough in order to achieve supervisory goals (fault detection, diagnosis and reconfiguration). The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial proc...

The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial process. An outlook of main difficulties in applying this methodology in dynamic systems is contrasted with the benefits of applying it. A generic case definition is proposed to achieve supervisory tasks in the domain of dynamic systems. This methodo...

This work is oriented towards symptom-based methods of control systems diagnosis, where the main tasks are to extract process trends by means of qualitative representations of signals. Symbolic (qualitative) representations of signal trends are usually based on a temporal segmentation of signals into episodes depending on their slope or convexity,...

The paper focuses on taking advantage of large amounts of data that are systematically stored in plants (by means of SCADA systems), but not exploited enough in order to achieve supervisory goals (fault detection, diagnosis and reconfiguration). The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial proc...

This paper presents a new method for getting a discrete differentiator that approximates ideal derivative in the range low frequency components and eliminates the noise amplification for high frequency components of input signal. The proposal is based on the estimation of the derivative in a time-windowed signal by means of the slope of a first ord...

Obtaining qualitative information from a process can facilitate the elaboration and implementation of an expert system for the process supervision. This paper shows the results obtained by means of the elaborated information abstraction applied to a simple process. In order to take advantage of these tools a good knowledge of the obtained signals f...

Analysis of measured process data and extraction of process trends are essential for reasoning about the process behaviour. In this paper a symbolic representation of signals is presented, this representation is based on a segmentation of signals in episodes depending on their convexity, and a classification of these episodes. In order to apply the...

A set of tools from the Artificial Intelligence domain have been integrated into Matlab/Simulink taking benefit of its capabilities as a CACSD framework. Abstraction tools, a representation language for qualitative reasoning and expert systems (ES) have been selected with this purpose. The main goal is to extend this known framework to represent ex...

Se propone el Razonamiento Basado e n Casos (RBC) como metodología para la diagnosis y re-sintonía de reguladores PID. El RBC permitirá recuperar situaciones anteriores y aprovechar el conocimiento adquirido en forma de casos de un proceso y su regulación. Con este enfoque se pretende aplicar el RBC a la re-sintonía de regulado PID de forma que cum...

This paper introduces how artificial intelligence technologies can be integrated into a known computer aided control system design (CACSD) framework, Matlab/Simulink, using an object oriented approach. The aim is to build a framework to aid supervisory systems analysis, design and implementation. The idea is to take advantage of an existing CACSD f...

Supervisory systems evolution makes the obtaining of significant information from processes more important in the way that the supervision systems' particular tasks are simplified. So, having signal treatment tools capable of obtaining elaborate information from the process data is important. In this paper, a tool that obtains qualitative data abou...

This paper attempts to explain an example of applying fuzzy vs. qualitative techniques to a tracking control problem. In the first instance, the qualitative technique is considered as fuzzy controllers with less knowledge. This facility can make qualitative control more feasible for certain problems when little precision is necessary. It is possibl...