Faisel J. Uppal

Soft Computing Approaches to Fault Diagnosis for Dynamic Systems: A Survey

Abstract Recent approaches to fault detection and isolation for dynamic systems using methods of integrating quantitative and qualitative model information, based upon soft computing (SC) methods are surveyed. In this study, the use of SC methods is considered an important extension to the quantitative model-based approach for residual generation in FDI. When quantitative models are not readily available, a correctly trained neural network (NN) can be used as a non-linear dynamic model of the system. However, the neural network does not easily provide insight into model behaviour; the model is explicit rather than implicit in form. This main difficulty can be overcome using qualitative modelling or rule-based inference methods. For example, fuzzy logic can be used together with state space models or neural networks to enhance FDI diagnostic reasoning capabilities. The paper discusses the properties of several methods of combining quantitative and qualitative system information and their practical value for fault diagnosis of real process systems.

Fault diagnosis of an industrial gas turbine using neuro−fuzzy methods

Abstract The paper focuses on the application of neuro-fuzzy techniques in fault detection and isolation. The objective of this paper is to detect and isolate faults to an industrial gas turbine, with emphasis on faults occurred in the actuator part of the gas turbine. A neuro-fuzzy based learning and adaptation of TSK fuzzy models is used for residual generation, while for residual evaluation a neuro-fuzzy classifier for Mamdani models is used. The paper is concerned on how to obtain an interpretable fault classifier as well as interpretable models for residual generation.

Reconfiguration in Networked Control Systems: Fault Tolerant Control and Plug-and-Play

: The last decade has seen a rapid increase and convergence in the use of (a) digital network technology, (b) embedded systems and (c) fault analysis and on-line diagnosis. This has resulted in an increase in complexity of the resultant system which must not only ensure performance but also monitor and compensate for faults and hence avoid total failure. The advances made have also facilitated a plug-and-play (PnP) characteristic of networked embedded systems. This paper provides (i) a suitable architecture for the fault tolerant operation and (ii) enables the above PnP feature.

NEURO-FUZZY BASED FAULT DIAGNOSIS APPLIED TO AN ELECTRO-PNEUMATIC VALVE

Abstract The early detection of faults (just beginning and still developing) can help avoid system shutdown, breakdown and even catastrophes involving human fatalities and material damage. Computational intelligence techniques are being investigated as extension of the traditional fault diagnosis methods. This paper discusses the properties of the TSK/Mamdani approaches and neuro-fuzzy (NF) fault diagnosis within an application study of an electro-pneumatic valve actuator in a sugar factory. The key issues of finding a suitable structure for detecting and isolating ten realistic actuator faults are described. Copyright© 2002 IFAC

A Hybrid Neuro-Fuzzy and De-Coupling Approach Applied to the DAMADICS Benchmark Problem

Abstract A novel multiple-model fault detection and isolation scheme for non-linear dynamic systems, that of a Neuro-Fuzzy Decoupling Fault Detection Scheme (NFDFDS) is presented, a hybrid scheme incorporating both neuro-fuzzy and model-based methods. The FDI scheme employs local optimal observers designed according to minimum state estimation variance. An application of FDI for an electro-pneumatic valve actuator in a sugar factory is presented. Key issues of finding a suitable structure for detecting and isolating nine realistic actuator faults are described.

RECONFIGURATION IN PLUG-AND-PLAY NETWORK OF EMBEDDED SYSTEMS

Abstract The last decade has seen a rapid increase and convergence in the use of (a) digital network technology, (b) embedded systems and (c) fault analysis and on-line diagnosis. This has resulted in an increase in complexity of the resultant system which must not only ensure performance but also monitor and compensate for faults and hence avoid total failure. The advances made have facilitated a “plug-and-play” (PnP) characteristic of networked embedded systems. This paper provides a framework for the analysis and development of strategies which enable a fault-tolerant PnP feature.

Application of B-Spline Neuro-Fuzzy Networks to Identification, Fault Detection and Isolation

Abstract Reliable fault detection and isolation is important for dynamical safety critical systems. This paper investigates the B-spline neuro-fuzzy approach for fault detection and isolation. It combines, in a single framework, both numerical and symbolic knowledge about the process. The method is also able to structure a quantitative model in a way that qualitative knowledge about the process could be included as well as extracted. The underlying concept is to structure a neural network, which can model highly non-linear systems efficiently, in a fuzzy-logic format; the network could therefore be trained more rapidly and will also provide a linguistic description about the causes of faults.

RECONFIGURATION IN NETWORKED CONTROL SYSTEMS: Fault Tolerant Control and Plug-and-Play

Abstract The last decade has seen a rapid increase and convergence in the use of (a) digital network technology, (b) embedded systems and (c) fault analysis and on-line diagnosis. This has resulted in an increase in complexity of the resultant system which must not only ensure performance but also monitor and compensate for faults and hence avoid total failure. The advances made have also facilitated a plug-and-play (PnP) characteristic of networked embedded systems. This paper provides (i) a suitable architecture for the fault tolerant operation and (ii) enables the above PnP feature.

DISTURBANCE DISTRIBUTION MATRIX COMPUTATION: NUMERICAL IMPROVEMENT

Abstract Prompt detection and diagnosis of process malfunctions are strategically important due to economic and environmental demands required for industries to remain competitive in world markets. In this paper a new formulation of the computation of the disturbance and fault distribution matrices is suggested for Neuro-Fuzzy and De-coupling Fault Diagnosis Scheme (NFDFDS). NFDFDS is a multiple-model fault detection and isolation (FDI) approach of non-linear dynamic systems. In this approach, powerful approximation and reasoning capabilities of neuro-fuzzy models are combined with the de-coupling capabilities of optimal observers to perform reliable fault detection and isolation. For determination of distribution matrices in this case it is shown that a least-squares approach is the most efficient compared with any other non-linear optimization technique.

B-Spline Neuro-Fuzzy Identification and Fault Diagnosis Applied to a Sugar Evaporization Plant

Abstract There is an increasing demand for man-made dynamical systems to become safer and more reliable. This paper presents a novel approach for fault detection and isolation (FDI): it combines, in a single framework, both numerical and symbolic knowledge about the process. The method is also able to structure a quantitative model in a way that qualitative knowledge about the process could be included as well as extracted. The underlying concept is to structure an ANN, which can model highly nonlinear systems efficiently, in a fuzzy-logic format; the network could therefore be trained more rapidly and will also provide a linguistic description about the causes of faults. Expert-knowledge could also be included in the same framework.