Fault Diagnosis on Industrial Systems Based on a Multiple Model Approach

A variant of the particle swarm optimization for the improvement of fault diagnosis in industrial systems via faults estimation

"En el presente trabajo se presenta un estudio sobre la aplicación de estrategias bioinspiradas para la optimización al diagnóstico de fallos en sistemas industriales. El objetivo principal es establecer una base para el desarrollo de nuevos y viables métodos de diagnóstico de fallos basados en modelos que permitan mejorar las dificultades de los métodos actuales. Estas dificultades están relacionadas, fundamentalmente, con la sensibilidad ante la presencia de fallos y la robustez ante perturbaciones externas. En el estudio se consideraron los algoritmos Evolución Diferencial y Optimización por Colonia de Hormigas. La efectividad de la propuesta es analizada mediante experimentos con el conocido problema de prueba de los dos tanques. Los experimentos consideraron presencia de ruido en la información y fallos incipientes de manera que fuera posible analizar las ventajas de la propuesta en cuanto a diagnóstico robusto y sensible. Los resultados obtenidos indican que el enfoque propuesto y, principalmente, la combinación de los dos algoritmos, caracterizan una metodología prometedora para el diagnóstico de fallos."

Adaptive Filter Design for FDI in Nonlinear Systems Based on Multiple Model Approach

Most of the existing artificial neural network models use a significant amount of information for their training. The need for such information could be an inconvenience for its application in fault diagnosis in industrial systems, where the information, due to different factors such as data losses in the data acquisition systems, is scarce or not verified. In this chapter, a diagnostic system based on a Hopfield neural network is proposed to overcome this inconvenience. The proposal is tested using the development and application of methods for the actuator diagnostic in industrial control systems (DAMADICS) benchmark, with successful performance.

This paper explores the application of bioinspired cooperative strategies for optimization on Fault Diagnosis in industrial systems. As a first step, the Differential Evolution and Ant Colony Optimization algorithms are considered. Both algorithms have been applied to a benchmark problem, the two tanks system. The experiments have considered noisy data in order to compare the robustness of the diagnosis. The preliminary results indicate that the proposed approach, basically the combination of the two algorithms, characterizes a promising methodology for the Fault Detection and Isolation problem.KeywordsDifferential EvolutionFault DiagnosisDifferential Evolution AlgorithmIndustrial SystemTank SystemThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This chapter presents the motivation for developing fault diagnosis application in industrial systems. Fault diagnosis methods can be broadly categorized into model-based and data-driven. Model-based strategies are briefly discussed while highlighting the increasing tendency to the use of data-driven methods given the increasing data available from process operations. The classic data-driven fault diagnosis loop is presented and each task is described in detail. A procedure is presented for the systematic design of data driven fault diagnosis methods. Finally, the fault diagnosis problem for multimode processes is briefly discussed.

This work presents two active fault tolerant control systems for aerospace applications. The former case study regards an aircraft longitudinal autopilot and the latter one a satellite attitude control system, both in case of faults affecting the actuators. The main features of the presented active fault tolerant control schemes are the fault detection and diagnosis module and its design technique, i.e. the nonlinear geometric approach. Such approach allows, using adaptive filters in the fault detection and diagnosis module, fault detection, isolation and estimation. The fault estimates, obtained by different methods including recursive least squares and neural network, are exploited by a controller reconfiguration mechanism. In particular, by means of the nonlinear geometric approach, relying on nonlinear differential algebra, it is possible to obtain fault estimates decoupled from wind components in case of aircraft and aerodynamic disturbances in case of spacecraft, thus giving to the overall control system very good robustness properties and performances. The effectiveness of the designed solutions is shown by means of high fidelity simulators, in different flight conditions and in the presence of faults on actuators, turbulence, measurement noise, and modelling errors.

In this paper, the main goal is to design an approach that performs fault detection, isolation and estimation for a large class of nonlinear systems. Fault diagnosis is established by regarding system as a convex combination of linear time invariant (LTI) stochastic models and not as a single global model. The nonlinear representation is based on a bank of decoupled Kalman filters. This paper consists in generating a robust model selection of the "best" representative linear model. Under fault isolation conditions, the main contribution is to design an adaptive filter which makes possible multiple faults detection which appear simultaneously or in a sequential way, isolation and estimation over the whole operating range of nonlinear system. The stability conditions of the adaptive filter are developed. These conditions result in convex linear matrix inequalities (LMIs) that can be solved efficiently with optimization techniques. Performances of the method are tested on an academic example.

Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach

The main objective of this research is to develop a fault detection and isolation (FDI) methodologies for Cylla-Haase polymerization reactor, and implement the developed methods to the nonlinear simulation model of the proposed reactor to evaluate the effectiveness of FDI methods. The first part of this research focus of this chapter is to understand the nonlinear dynamic behaviour of the Chylla-Haase polymerization reactor. In this part, the mathematical model of the proposed reactor is described. The Simulink model of the proposed reactor is set up using Simulink/MATLAB. The design of Simulink model is developed based on a set of ordinary differential equations that describe the dynamic behaviour of the proposed polymerization reactor. An independent radial basis function neural networks (RBFNN) are developed and employed here for an on-line diagnosis of actuator and sensor faults. In this research, a robust fault detection and isolation (FDI) scheme is developed for open-loop exothermic semi-batch polymerization reactor described by Chylla-Haase. The independent (RBFNN) is employed here when the system is subjected to system uncertainties and disturbances. Two different techniques to employ RBF neural networks are investigated. Firstly, an independent neural network is used to model the reactor dynamics and generate residuals. Secondly, an additional RBF neural network is developed as a classifier to isolate faults from the generated residuals. In the third part of this research, a robust fault detection and isolation (FDI) scheme is developed to monitor the Chylla-Haase polymerization reactor, when it is under the cascade PI control. This part is really challenging task as the controller output cannot be designed when the reactor is under closed-loop control, and the control action will correct small changes of the states caused by faults. The proposed FDI strategy employed a radial basis function neural network (RBFNN) in an independent mode to model the process dynamics, and using the weighted sum-squared prediction error as the residual. The Recursive Orthogonal Least Squares algorithm (ROLS) is employed to train the model to overcome the training difficulty of the independent mode of the network. Then, another RBFNN is used as a fault classifier to isolate faults from different features involved in the residual vector. In this research, an independent MLP neural network is implemented here to generate residuals for detection task. And another RBF is applied for isolation task performing as a classifier. The fault diagnosis scheme is developed for a Chylla-Haase reactor under open-loop and closed-loop control system. The comparison between these two neural network architectures (MPL and RBF) are shown that RBF configuration trained by (RLS) algorithm have several advantages. The first one is greater efficiency in finding optimal weights for field strength prediction in complex dynamic systems. The RBF configuration is less complex network that results in faster convergence. The training algorithms (RLs and ROLS) that used for training RBFNN in chapter (4) and (5) have proven to be efficient, which results in significant faster computer time in comparison to back-propagation one. Another fault diagnosis (FD) scheme is developed in this research for an exothermic semi-batch polymerization reactor. The scheme includes two parts: the first part is to generate residual using an extended Kalman filter (EKF), and the second part is the decision making to report fault using a standardized hypothesis of statistical tests. The FD simulation results are presented to demonstrate the effectiveness of the proposed method. In the lase section of this research, a robust fault diagnosis scheme for abrupt and incipient faults in nonlinear dynamic system. A general framework is developed for model-based fault detection and diagnosis using on-line approximators and adaptation/learning schemes. In this framework, neural network models constitute an important class of on-line approximators. The changes in the system dynamics due to fault are modelled as nonlinear functions of the state, while the time profile of the fault is assumed to be exponentially developing. The changes in the system dynamics are monitored by an on-line approximation model, which is used for detecting the failures. A systematic procedure for constructing nonlinear estimation algorithm is developed, and a stable learning scheme is derived using Lyapunov theory. Simulation studies are used to illustrate the results and to show the effectiveness of the fault diagnosis methodology. Finally, the success of the proposed fault diagnosis methods illustrates the potential of the application of an independent RBFNN, an independent MLP, an Extended kalman filter and an adaptive nonlinear observer based FD, to chemical reactors.

This study investigates estimation and fault diagnosis of fractional-order Lithium-ion battery system. Two simple and common types of observers are designed to address the design of fault diagnosis and estimation for the fractional-order systems. Fractional-order Luenberger observers are employed to generate residuals which are then used to investigate the feasibility of model based fault detection and isolation. Once a fault is detected and isolated, a fractional-order sliding mode observer is constructed to provide an estimate of the isolated fault. The paper presents some theoretical results for designing stable observers and fault estimators. In particular, the notion of stability in the sense of Mittag-Leffler is first introduced to discuss the state estimation error dynamics. Overall, the design of the Luenberger observer as well as the sliding mode observer can accomplish fault detection, fault isolation, and estimation. The effectiveness of the proposed strategy on a three-cell battery string system is demonstrated.

Self-adaptive selection graph pooling based fault diagnosis method under few samples and noisy environment

In this work we present a study on the application of bio-inspired strategies for optimization to Fault Diagnosis in industrial systems. The principal aim is to establish a basis for the development of new and viable model-based Fault Diagnosis Methods which improve some difficulties that the current methods cannot avoid. These difficulties are related with fault sensitivity and robustness to external disturbances. To get start the study, we consider the Differential Evolution and the Ant Colony Optimization algorithms. This application is illustrated using simulation data of the Two Tanks System benchmark. In order to analyze the merits of these algorithms to obtain a diagnosis which needs to be sensitive to faults and robust to external disturbances, some experiments with incipient faults and noisy data have been simulated. The results indicate that the proposed approach, basically the combination of the two algorithms, characterizes a promising methodology for Fault Diagnosis.

The paper presents the application of various classification schemes for actuator fault diagnosis in industrial systems. The main objective of this study is to compare either single or meta-classification strategies that can be successfully used as reasoning means in off-line as well as on-line diagnostic expert systems. The applied research was conducted on the assumption that only classic and well-practised classification methods would be adopted. The comparison study was carried out within the DAMADICS benchmark problem which provides a popular framework for confronting different approaches in the development of fault diagnosis systems.

Online automatic fault diagnosis in industrial systems is essential for guaranteeing safe, reliable and efficient operations. However, difficulties associated with computational overload, ubiquitous uncertainties and insufficient fault samples hamper the engineering application of intelligent fault diagnosis technology. Geared towards the settlement of these problems, this paper introduces the method of dynamic uncertain causality graph, which is a new attempt to model complex behaviors of real-world systems under uncertainties. The visual representation to causality pathways and self-relied “chaining” inference mechanisms are analyzed. In particular, some solutions are investigated for the diagnostic reasoning algorithm to aim at reducing its computational complexity and improving the robustness to potential losses and imprecisions in observations. To evaluate the effectiveness and performance of this method, experiments are conducted using both synthetic calculation cases and generator faults of a nuclear power plant. The results manifest the high diagnostic accuracy and efficiency, suggesting its practical significance in large-scale industrial applications.