Carlos J. Alonso

Verified

Carlos verified their affiliation via an institutional email.

Learn more

Verified

Carlos verified their affiliation via an institutional email.

Learn more

• Ph.D.
• Associate Professor at University of Valladolid

Industry 4.0 aims for a digital transformation of manufacturing and production systems, producing what is known as smart factories, where information coming from Cyber-Physical Systems (core elements in Industry 4.0) will be used in all the manufacturing stages to improve productivity. Cyber-physical systems through their control and sensor systems...

Les techniques de diagnostic des défauts, en particulier pour les systèmes exigeants qui nécessitent fiabilité, disponibilité et sécurité, posent de nombreux défis.Diagnostic et commande à tolérance de fautes 1 présente un panorama complet des avancées récentes en matière de diagnostic des défauts dans les systèmes dynamiques complexes. Le besoin d...

The proper operation of Heating, Ventilation, and Air Conditioning (HVAC) systems is crucial to reduce energy consumption because they are the major consumers of energy in buildings. Prognostic and Health Management Systems (PHMS) can assist both operators and managers of Smart Buildings, anticipating potential problems that can reduce the energy e...

This work deals with the problem faced to perform prognostics of electronic devices using a data-driven approach to generate degradation models for predicting their Remaining Useful Life. To be able to generate good models, a lot of experimental data are required. Moreover, the high frequency sampling required for electronic devices implies that hu...

In this chapter, the artificial intelligence approach to model-based diagnosis is introduced. First, we present the main ideas of the Consistency-Based Diagnosis (CBD) methodology (the no-function-in-structure principle, the use of models of correct behavior, and the requirement of local propagation in the models), together with its logical formali...

In this chapter, we analyze main problems found by the Artificial Intelligence approach to Model-based diagnosis (DX): the online computation of minimal conflicts by means of an ATMS-like dependency-recording engine, and the need for an extension to deal with dynamic systems diagnosis. To cope with the first problem we will see different options: f...

Nowadays hybrid systems are everywhere: vehicles, planes, electronic devices, industrial factories, and so on. All these systems exhibit different behavior patterns depending on the actual operation mode. In this work we propose a framework for fault diagnosis of those dynamic systems characterized by continuous behavior commanded by discrete actua...

Model-based fault isolation and identification in hybrid systems is computationally expensive or even unfeasible for complex systems due to the presence of uncertainty concerning the actual state, and also due to the presence of both discrete and parametric faults coupled with changing modes in the system. In this work we improve fault isolation an...

Consistency-based diagnosis is a model-based diagnosis approach for the artificial intelligence community which relies upon models of correct behaviour and allows automatic multiple fault detection and isolation. The theory for static systems diagnosis is well established but there is a lack of free available tools implementing these ideas for dyna...

Possible Conflicts (PCs) are those minimally redundant subsystems, computed offline, that can be used for consistency-based diagnosis of physical systems. In this work we characterize Possible Conflicts for hybrid systems diagnosis in the Hybrid Bond Graph modelling framework, introducing the notion of HBG-PCs. We provide a method to compute the co...

Accurate and efficient fault identification is a nec-essary task for system reconfiguration, fault prog-nostics, and fault adaptive control in complex dy-namic systems. However, timely on-line fault identification for large systems can be computa-tionally expensive. In this paper, we show how we can decompose a system model into sub-models, diagnos...

In this work we introduce DXPCS, a software tool capable of performing consistency-based diagno-sis of continuous dynamic systems whose mod-els can be represented as a set of Ordinary Differ-ential Equations. The diagnosis approach relies upon the Possible Conflict, PC for short, concept. DXPCS is able to automatically build the sim-ulation models...

The systems dynamics and control engineering (FDI) and the artificial intelligence diagnosis (DX) communities have developed complementary approaches that exploit structural relations in the system model to find efficient solutions for the residual generation and residual evaluation steps in fault detection and isolation in dynamic systems. This pa...

The development of efficient and reliable fault detection approaches is necessary to improve performance, safety, and reliability in engineering systems. Moreover, these approaches have to be simple enough to provide quick diagnosis results and to reduce development and maintenance costs. Consistency-based diagnosis using possible conflicts (PCs) r...

This work studies potential ways of integration of two techniques for fault detection, isolation, and identification in dynamic systems: Lydia-NG suite of diagnosis algorithms and Consistency-based Diagnosis with Possible Conflicts. By integrating both techniques, Lydia-NG will benefit from a more efficient fault detection and isolation task, and P...

Hybrid systems diagnosis requires different sets of equations for each operation mode in order to estimate the continuous system behaviour. In this work we rely upon Hybrid Possible Conflicts (HPCs), which are an extension of Possible Conflicts (PCs) for hybrid systems, that introduce the information about potential system modes as control specific...

A GIS-based Decision Support System has been developed within the OCEANLIDER project to find optimal placement for green energy generation from oceanic energy. The DSS performs Multi-Criteria Evaluation, MCE, to help in the decision making. The scenario is defined as a combination of the device (power generation from wave or sea current energy) and...

This work proposes a common framework for Fault Detection and Isolation of discrete and parametric faults in hybrid systems using Hybrid Possible Conflicts , HPCs. Fault detection is based on residual activation for the set of HPCs in the current mode. Using the structural information in each HPC we first search for discrete –related to actuators–...

This work presents a novel approach to multivariate time series classification. The method exploits the multivariate structure of the time series and the possibilities of the stacking ensemble method. The basics of the method may be described in three steps: first, decomposing the multivariate time series on its constituent univariate time series;...

Hybrid systems, whose behaviour exhibit continuous and discrete event dynamics, are present in many industrial environments. The complexity of such behaviour makes the on-line fault diagnosis task very challenging. In this work we propose an accurate and timely online fault diagnosis approach for hybrid systems. Our approach uses the Hybrid Bond Gr...

Microarray data classification is a task involving high dimensionality and small samples sizes. A common criterion to decide on the number of selected genes is maximizing the accuracy, which risks overfitting and usually selects more genes than actually needed. We propose, relaxing the maximum accuracy criterion, to select the combination of attrib...

This paper introduces a factoring method for Dynamic Bayesian Networks (DBNs) based on Possible Conflicts (PCs), which aim to reduce the computational burden of Particle Filter inference. Assuming single fault hypothesis and known fault modes, the method allows performing consistency based fault detection, isolation and identification of continuous...

Rotation Forest (RF) is an ensemble method that has shown effectiveness on microarray data set classification problems. RF works by generating sparse rotation matrixes of the input space, a method that creates accurate and diverse base classifiers. In its original formulation, elemental rotations were obtained by Principal Component Analysis (PCA)....

This work presents an on-line diagnosis algorithm for dynamic systems that combines model based diagnosis and machine learning techniques. The Possible Conflicts (PCs) method is used to perform consistency based diagnosis, providing fault detection and isolation. Machine learning methods are use to induce time series classifiers, that are applied...

Model based diagnosis of large continuous dy-namic systems requiring quantitative simulation has a high computational cost, which can be re-duced by distributing the computation. Distribu-tion can be obtained partitioning the original di-agnosis problem into the analysis of simpler sub-problems. In this work, Possible Conflicts are used to partitio...

Due to the high number of gene expressions contained on microarray data, feature extraction techniques are usually applied before inducing classifiers. A common criterion to decide on the number of selected genes is minimizing the classifier error. However, considering the risk of overfitting due to the small sample size, and the fact that the numb...

Diagnosis of real world problems demands the integration of different techniques from several research fields. In Model-based Diagnosis, both Artificial Intelligence and Control Theory communities have provided different but complementary approaches. Recent works, known as BRIDGE proposal, provided a common framework for the integration of techniqu...

Consistency-based diagnosis of dynamic systems using possible conflicts rely upon a semi-closed loop simulation of numerical models. Simulation approaches need to know the initial state, which is a nontrivial requirement in real-world systems. Prognosis approaches also require techniques for predicting the future system states under nominal and fau...

This work presents an on-line diagnosis algorithm for dynamic systems that combines model based diagnosis and machine learning techniques. The Possible Conflicts method is used to perform con-sistency based diagnosis. Possible conflicts are in charge of fault detection and isolation. Machine learning methods are use to induce time series clas-sifie...

Behaviour simulation in Consistency-based Diagnosis requires knowing the initial value. This assumption is not easily fulfilled in real systems, even in the presence of measurements related to state variables due to noise and parameter uncertainties. This work proposes the integration of state observers to estimate initial states for simulation in...

This work explores the capacity of Stacking to generate multivariate time series classifiers from classifiers of their univariate time series components. The Stacking scheme proposed uses k-nearest neighbors (K-NN) with dynamic time warping (DTW) as a dissimilarity measure for the level 0 learners. Support vector machines and Na ̈ıve Bayes are appl...

This paper explores an integrated approach to diagnosis of complex dynamic systems. Consistency-based diagnosis is capable of performing automatic fault detection and localization using just correct behaviour models. Nevertheless, it may exhibit low discriminative power among fault candidates. Hence, we combined the consistency based approach with...

Consistency-based diagnosis automatically provides fault detection and localization capabilities, using just models for correct behavior. However, it may exhibit a lack of discrimination power. Knowledge about fault modes can be added to tackle the problem. Unfortunately, it brings additional complexity issues, since it will be necessary to discrim...

We propose a method for generating classifier ensembles based on feature extraction. To create the training data for a base classifier, the feature set is randomly split into K subsets (K is a parameter of the algorithm) and Principal Component Analysis (PCA) is applied to each subset. All principal components are retained in order to preserve the...

Ensemble methods allow to improve the accuracy of clas- sification methods. This work considers the application of one of these methods, named Rotation-based, when the classifiers to combine are RBF Networks. This ensemble method, for each member of the ensemble, trans- forms the data set using a pseudo-random rotation of the axis. Then the classif...

In this paper we introduce a system for early classification of several fault modes in a continuous process. Early fault classification is basic in supervision and diagnosis systems, since a fault could arise at any time, and the system must identify the fault as soon as possible. We present a computational framework to deal with the problem of ear...

In previous works, a time series classification system has been presented. It is based on boosting very simple classifiers, formed only by one literal. The used literals are based on temporal intervals. The obtained classifiers were simply a linear combination of literals, so it is natural to expect some improvements in the results if those literal...

In Machine Learning, ensembles are combination of classifiers. Their objective is to improve the accuracy. In previous works, we have presented a method for the generation of ensembles, named rotation-based. It transforms the training data set; it groups, randomly, the attributes in different subgroups, and applies, for each group, an axis rotation...

This paper describes an integrated approach to diagnosis of complex dynamic systems, combining model based diagnosis with machine learning techniques, proposing a simple framework to make them cooperate, hence improving the diagnosis capabilities of each individual method. First step in the diagnosis process resorts to consistency-based diagnosis,...

In previous works, a time series classification system has been presented. It is based on boosting very simple classifiers, formed only by one literal. The predicates are based on temporal intervals. The obtained classifiers were simply a linear combination of literals, so it is natural to expect some improvements in the results if that literals ar...

Consistency-based diagnosis is one of the most widely used approaches to model-based diagnosis within the artificial intelligence community. It is usually carried out through an iterative cycle of behavior prediction, conflict detection, candidate generation, and candidate refinement. In that process conflict detection has proven to be a nontrivial...

A new method for ensemble generation is presented. It is based on grouping the attributes in different subgroups, and to apply, for each group, an axis rotation, using Principal Component Analysis. If the used method for the induction of the classifiers is not invariant to rotations in the data set, the generated classifier can be very different. H...

A most common requirement in the development of Knowledge Based Systems in dynamic environments is the capability of expressing time. This paper presents how it is possible to express time related requirements on KBS tasks and to include time explicitly in rules. Such kind of facilities is attained using UML diagrams embedded in the usual CommonKAD...

This work presents decision trees adequate for the classification of series data. There are several methods for this task, but most of them focus on accuracy. One of the requirements of data mining is to produce comprehensible models. Decision trees are one of the most comprehensible classifiers. The use of these methods directly on this kind of da...

En trabajos previos se ha presentado un sistema de clasificación de series. Dicho método se apoya en el método de combinación de clasificadores denominado boosting, utilizando clasificadores base muy simples, formados por únicamente un literal. Estos predicados se basan en intervalos temporales. Los clasificadores obtenidos son simplemente una comb...

A knowledge-based model for on-line diagnosis of complex dynamic systems is proposed. Domain knowledge is modelled via causal networks which consider temporal relationships among symptoms and causes. Inference and task knowledge is described using the Common-KADS methodology. The main feature of the proposal is that the diagnosis task is able to tr...

Contents 1 Introduction 2 2 Boosting 3 2.1 Selecting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 Multiclass Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 3 Base Classi ers 7 3.1 Dynamic Time Warping . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2 Literals Selection . . . . . . . . . . . . . . . ....

This work presents a system for supervised time series classification, capable of learning from series of different length and able of providing a classification when only part of the series are presented to the classifier.

This paper propose a diagnosis architecture that integrates consistency based diagnosis with induced time series classi ers, trying to combine the advantages of both methods. Consistency based diagnosis allows fault detection and localization without prior knowledge of the device fault modes. Machine learning techniques are able to induce time seri...

A novel method for constructing RBF networks is presented. It is based on Boosting, an ensemble method that combines several classifiers obtained us- ing any other classification method. If the classifiers that are going to be combined by boosting are radial- basis functions, then the boosting method produces a RBF network as result. The method for...

This paper proposes a diagnosis architecture that integrates consistency based diagnosis with induced time series classifiers, trying to combine the advantages of both methods. Consistency based diagnosis allows fault detection and localization without prior knowledge of the device fault modes. Machine learning techniques are able to induce time se...

We describe in this paper an ITS called SIAL that supports the learning of problem solving skills in computational logic from obtaining the clause form of simple well formed formulae to hyperresolution. The core function in SIAL is the error diagnosis module, that has the role of detecting and interpreting the mistakes of the learner while he/she...

A graphical language to represent rules is described. It has been designed for on-line applications on continuous systems. Rule conditions are represented using pipe diagrams and its edition is simple enough for a non-expert computer user. In order to use this language in dynamic systems, elements to deal with uncertainty and time has been introduc...

A supervised classification method for temporal series, even multivariable, is proposed. It is based on boosting very simple classifiers. They are formed only by one literal. The used predicates are based in similarity functions (i.e., euclidean and dynamic time warping) between time series.

A method for learning multivariate time series classifiers by inductive logic programming is presented. Two types of background predicate that are suited for this task are introduced: interval based predicates, such as "always", and distance based, such as the euclidean distance.

A supervised classification method for time series, even multivariate, is presented. It is based on boosting very simple classifiers: clauses with one literal in the body. The background predicates are based on temporal intervals. Two types of predicates are used: i) relative predicates, such as "increases" and "stays", and ii) region predicates, s...

This work proposes a novel method for constructing RBF networks, based on boosting. The task assigned to the base learner is to select a RBF, while the boosting algorithm combines linearly the different RBFs. For each iteration of boosting a new neuron is incorporated into the network. The method for selecting each RBF is based on randomly selectin...

A method for learning multivariate time series classifiers by inductive logic programming is presented. Two types of background predicate that are suited for this task are introduced: interval based predicates, such as always, and distance based, such as the euclidean distance.

Model-based diagnosis techniques have found several diculties when they have been applied to dynamic systems. This work proposes an architecture integrating a Consistency Based with Fault Modes approach, together with domain speci c knowledge, to diagnosis of dynamic systems.

A supervised classification method for time series, even multivariable, is proposed. It is based on boosting very simple classifiers. They are formed only by one literal. The used predicates, such as "always" and "sometime" operate over temporal intervals and regions in the dominion of the values of the variable. These regions are obtained previous...

In previous works, a system for supervised time series classification has been presented. It is based on boosting very simple classifiers: only one literal. The used predicates are based on temporal intervals. There are two types of predicates: i) relative predicates, such as "increases" and "stays", and ii) region predicates, such as "always" and...

Consistency-based diagnosis is the most widely used approach to model-based diagnosis within the Artificial Intelligence community. It is usually carried out through an iterative cycle of behavior prediction, conflict detection, and candidate generation and refinement. Many approaches to consistency-based diagnosis have relied on some kind of on-li...

A new tasks taxonomy for knowledge-based global supervision (GS) of continuous industrial processes is introduced in this work. Possible required tasks are specified together with the analysis of their dimensions, which should be useful in the selection of the final capabilities of supervision. Moreover, these dimensions would help end-users and de...

For more than ten years different techniques have been pro- posed to perform model-based diagnosis of dynamic systems. Neverthe- less, there is no general framework yet. Main part of the research effort has been devoted to modeling issues. Most approaches have relied upon qualitative models due to the lack of accuracy, certainty and precision in qu...

A supervised classification method for time series, even multivariate, is presented. It is based on boosting very simple classifiers: clauses with one literal in the body. The background predicates are based on temporal intervals. Two types of predicates are used: i) relative predicates, such as "increases" and "stays", and ii) region predicates, s...

Presented in this article is the description of the development of a diagnosis module in a supervisory system performing on-line diagnosis at a sugar plant. This module uses knowledge about the normal trajectory of some process' key variables to any problems. When problems occur, fault models involving temporal features are activated to filter cand...

This paper presents a detailed description of a knowledge-based system for on-line supervision and diagnosis of industrial continuous processes: TURBOLID. The system has been developed for a Spanish beet sugar factory, and it is in use in two plants. The system supports three main tasks; monitoring, operation mode and diagnosis. A detailed knowledg...

This work proposes a novel method for constructing RBF networks, based on boosting. The task assigned to the base learner is to select a RBF, while the boosting algorithm combines linearly the different RBFs. For each iteration of boosting a new neuron is incorporated into the network. The method for selecting each RBF is based on randomly selectin...

Este articulo nace con la intencion, por un lado, de presentar el estado actual de las investigaciones de diversos grupos españoles sobre la diagnosis y sobre la aplicacion de las metodologias cualitativas a los sistemas en general, centrando su estudio sobre los modelos socioeconómicos. Recientemente se han celebrado en Valladolid dos reuniones de...

El registro de dependencias en linea, mediante algun mecanismo de registro de dependencias, es una de las tecnicas mas utilizadas para calcular conflictos en el Diagnostico basado en Consistencia. No obstante, dados los problemas de efciencia que conlleva, se han propuesto distintas alternativas en los ultimos años. Entre ellas, se puede considerar...

The description of the development of a diagnosis module in a supervisory system performing on-line diagnosis over a sugar plant, is presented in this article. This module uses knowledge about the normal trajectory of some process' key variables to detect that something is wrong with it. When this is the situation, fault models involving temporal f...

A supervised classification method for temporal series, even multivariate, is presented. It is based on boosting very simple classifiers: clauses with one literal in the body. The background predicates are based on temporal intervals. Two types of predicates are used: i) relative predicates, such as "increases" and "stays", and ii) region predicate...

A method for learning multivariate time series classifiers by inductive logic programming is presented. Two types of background predicate that are suited for this task are introduced: interval based predicates, such as always, and distance based, such as the euclidean distance. Special purpose techniques are presented that allow these predicates to...

The reuse of task taxonomy for the analysis, comparison and development of Knowledge-based systems (KBS) devoted to supervision of industrial process, into a new domain is introduced in this work. Tasks are specified altogether with the analysis of their dimensions, which should be useful in the selection of the final capabilities of supervision. T...

A method for learning multivariate time series classifiers by inductive logic programming is presented. Two types of background predicate that are suited for this task are introduced: interval based predicates, such as "always", and distance based, such as the euclidean distance. Special purpose techniques are presented that allow these predicates...

A supervised classification method for temporal series, even multivariate, is presented. It is based on boosting very simple classifiers, which consists only of one literal. The proposed predicates are based in similarity functions (i.e., euclidean and dynamic time warping) between time series. The experimental validation of the method has been do...

An integrated advanced control and supervision system in operation in a sugar factory is presented. The system works on top of a commercial distributed computer control system, and combines artificial intelligence techniques for fault detection and diagnosis with advanced predictive controllers and models for other tasks.

SIAL is an intelligent system for the learning of first order logic. It has been developed as a laboratory tool for Artificial Intelligence courses of Computer Science curricula. Student modelling in this domain is a complex task, but it is necessary if we want to have a good interaction with the student. Interface design has a main role in the sys...

Consistency-based diagnosis is a main research area in Model-based diagnosis. Many approaches to consistency-based diagnosis need to compute the set of conflicts to generate diagnosis candidates. Possible conflicts are introduced as an alternative to dependency-recording engines for conflict calculation. Given a qualitative representation of system...

Consistency-based diagnosis is a main research area in Model-based diagnosis. Many approaches to consistency-based diagno- need to compute the set of conflicts to generate diagnosis candidates. Possible conflicts are introduced as an alternative to dependency-record- ing engines for conflict calculation. Given a qualitative representation of system...

Three Knowledge Based Systems (KBS's), performing diagnosis and integrated in a Knowledge Based Supervisory System (KBSS), are presented. The systems work on line in a continuos process factory and one of them is routinely used at the control room. The paper summarises the conceptual framework that guided the design of the KBSS, describing later th...

The artificial intelligence incidence in process control, although an active area in the researchers community and even with some implementations at industrial environment, is not sufficiently evaluated in numerical terms for the long term. The present article shows such an evaluation of a knowledge based system, developing supervisory control task...

An expert system performing tasks of supervisory control and fault detection and diagnosis was developed for a beet-sugar factory. Even when it can manage most usual alarm situations, the diagnosis method can not be easily extended to manage problems requiring a more complex analysis, such as phenomena involving nontrivial time evolution or multipl...

The article proposes a scheme for on-line fault detection and diagnosis using an expert system. This approach is being tested at a beet-sugar factory in Spain. A great deal of critical situations may arise in the normal operation of such a process. They are now managed by plant operators and cover both cases: faulty equipment diagnosis, which requi...

The following research paper describes a software implementation of a double coupled neural network for speaker independent, limited Spanish vocabulary word recognition. Spoken signal is preprocessed (pre-emphasized, framed and fft-transformed) to be converted in a data structure that contains time-frequency parameters, in a spectrogram way, descri...

In this paper, we describe a system designed to solve a control coordination problem of several processes in a sugar factory. We have designed an expert supervision and control system which relay on mathematical techniques to solve the flow coordination problem. The mission of the expert system is to supervise the state of the plant as a whole, try...