Fault Diagnosis In Dynamic Systems Research Articles

Soft Computing Approaches to Fault Diagnosis for Dynamic Systems

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 and studied in some detail. SC methods are considered an important extension to the quantitative model-based approach for residual generation in fault detection and isolation (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. The paper describes some powerful NN methods, taking into account the dynamic as well as non-linear system behaviour. Sometimes, further insight is required as to the explicit behaviour of the model-involved and it is then that fuzzy and even neurofuzzy methods come to their own in data-driven FDI applications. The paper also discusses the use of evolutionary programming tools for observer and NN design. The paper provides many powerful examples of the use of SC methods for achieving good detection and isolation of faults in the presence of uncertain plant behaviour, together with their practical value for fault diagnosis of real process systems.

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

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.

Editorial

International Journal of Robust and Nonlinear ControlVolume 10, Issue 14 p. 1153-1154 EditorialFree Access Editorial Henrik Niemann, Henrik Niemann Guest Editor Department of Automation, Technical University of Denmark, DK-2800 Lyngby, DenmarkSearch for more papers by this author Henrik Niemann, Henrik Niemann Guest Editor Department of Automation, Technical University of Denmark, DK-2800 Lyngby, DenmarkSearch for more papers by this author First published: 21 November 2000 https://doi.org/10.1002/1099-1239(20001215)10:14<1153::AID-RNC577>3.0.CO;2-ECitations: 3AboutPDF ToolsRequest permissionExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL No abstract is available for this article. REFERENCES 1 Patton R. Fault tolerant control: the 1997 situation. In Proceedings of the IFAC Symposium SAFEPROCESS'97, Hull, England, 1997; 1033– 1055. 2 Beard RV. Failure accommondation in linear systems through self-reorganization. Ph.D. Thesis, Department of Aeronautics and Astronautics, MIT, Cambridge, MA, 1971. 3 Jones HL. Failure detection in linear systems. Ph.D. Thesis, Department of Aeronautics and Astronautics, MIT, Cambridge, MA, 1973. 4 Basseville M, Nikiforov IV. Detection of Abrupt Changes — Theory and Application. Prentice Hall: Englewood Cliffs, NJ. 1993. 5 Chen J, Patton R. Robust Model-Based Fault Diagnosis for Dynamic Systems. Kluwer: Dordrecht, 1998. 6 Gertler J. Fault Detection and Diagnosis in Engineering Systems. Marcel Dekker: New York, 1998. 7 Mangoubi RS. Robust Estimation and Failure Detection: A Concise Treatment. Springer: Berlin, 1998. 8 Patton R, Frank P, and Clark R. Fault Diagnosis in Dynamic Systems — Theory and Applications. Prentice Hall: Englewood Cliffs, 1989. 9 Willsky AS. A survey of design methods for failure detection in dynamic systems. Automatica 1976; 12: 601– 611. 10 Massoumnia M, Verghese GC, Willsky AS. Failure detection and identification. IEEE Transactions on Automatic Control 1989; 34: 316– 321. Citing Literature Volume10, Issue14Special Issue: Fault Detection and Identification15 December 2000Pages 1153-1154 ReferencesRelatedInformation

Optimal auxiliary input design for fault diagnosis

An optimal input design problem in frequency domain is discussed for quick fault diagnosis of dynamical systems without affecting the original system in normal mode. Since the optimal auxiliary input for detecting a certain fault mode is not always good for detection of other fault modes, i.e., it may reduce the the distance between the normal mode and the other fault modes and make harder to detect true fault mode, the max-min approach is proposed in this paper. The auxiliary input is designed to maximize the minimum distance measured by the Kullback discrimination information measure between system models corresponding to the normal and each fault mode in order to detect the true fault mode. Results of a numerical simulation result indicate the applicability of the proposed auxiliary input in fault diagnosis.

Fault detection and identification in dynamic systems with noisy data and parameter/modeling uncertainties

A probabilistic approach is presented which can be used for the estimation of system parameters and unmonitored state variables towards model-based fault diagnosis in dynamic systems. The method can be used with any type of input–output model and can accommodate noisy data and/or parameter/modeling uncertainties. The methodology is based on Markovian representation of system dynamics in discretized state space. The example system used for the illustration of the methodology focuses on the intake, fueling, combustion and exhaust components of internal combustion engines. The results show that the methodology is capable of estimating the system parameters and tracking the unmonitored dynamic variables within user-specified magnitude intervals (which may reflect noise in the monitored data, random changes in the parameters or modeling uncertainties in general) within data collection time and hence has potential for on-line implementation.

A model-based probabilistic approach for fault detection and identification with application to the diagnosis of automotive engines

A model based parameter and state estimation technique is presented toward fault diagnosis in dynamic systems. The methodology is based on the representation of the system dynamics in terms of transition probabilities between user-specified sets of magnitude intervals of system parameters and state variables during user-specified time intervals. These intervals may reflect noise in the monitored data, random changes in the parameters, or modeling uncertainties in general. The transition probabilities are obtained from a given system model that yields the current values of the state variables in discrete time from their values at the previous time step and the values of the system parameters at the previous time step. Implementation of the methodology on a simplified model of the air, inertial, fuel, and exhaust dynamics of the powertrain of a vehicle shows that the methodology is capable of estimating the system parameters and tracking the unmonitored dynamic variables within the user-specified magnitude intervals.

Incipient fault diagnosis of dynamical systems using online approximators

Detection of incipient (slowly developing) faults is crucial in automated maintenance problems where early detection of worn equipment is required. In this paper, a general framework for model-based fault detection and diagnosis of a class of incipient faults is developed. The changes in the system dynamics due to the fault are modeled as nonlinear functions of the state and input variables, while the time profile of the failure is assumed to be exponentially developing. An automated fault diagnosis architecture using nonlinear online approximators with an adaptation scheme is designed and analyzed. A simulation example of a simple nonlinear mass-spring system is used to illustrate the results.

Survey of robust residual generation and evaluation methods in observer-based fault detection systems

The paper outlines recent advances of the theory of observer-based fault diagnosis in dynamic systems towards the design of robust techniques of residual generation and residual evaluation. Emphasis will be placed upon the latest contributions using frequency domain techniques including H∞ theory, nonlinear unknown input observer theory, adaptive observer theory, artificial intelligence including fuzzy logic, knowledge-based techniques and the natural intelligence of the human operator. Two representative examples illustrate the efficiency of the observer-based approach.

A Comparison Between Neural and Genetic Classifiers for Fault Diagnosis in Dynamic Systems

Abstract This paper investigates some aspects of the application of neural networks and genetic algorithms to fault diagnosis in dynamic systems. It refers to a fault diagnosis scheme based on parameter estimation; fault detection and identification are carried out by means of suitable classifiers. Three kinds of classifiers are considered, which use the parameters estimated by means of a parameter estimator; one is a neural network with a vectorial output; another is a neural network with a scalar output; the last one is developed by means of the application of genetic algorithms and consists of a scalar function. A simulation example is reported; the genetic classifier is simpler than the neural ones and shows a certain robustness with respect to input noise.

Fault Diagnosis Using Adaptive Observer Based Techniques

This paper presents a novel robust adaptive observer based approach for the actuator fault diagnosis in dynamic systems which are expressed by a state space model and are subjected to structured model uncertainties, external disturbances and dynamic uncertainties. An adaptive observer, whose adaptive tuning part only involves the estimation of the fault, is initially constructed to demonstrate the possibility of using adaptive updating rules to estimate the fault This is followed by a description of how to select a fixed observer gain matrix in order to make the resulting adaptive observer sensitive to the fault and insensitive to the model uncertainties and external disturbances. The method is demonstrated through its application to the monitoring of a simulated distillation column.

Fault diagnosis of dynamic systems using neural networks : T. Sorsa, J. Suontausta, H.N. Koivo, pp 433–436

Fault diagnosis of dynamic systems using neural networks : T. Sorsa, J. Suontausta, H.N. Koivo, pp 433–436

On-line multiple component and instrument fault diagnosis in dynamic systems : M.N. Barkesseh, N.A. Kheir, pp 815–821

On-line multiple component and instrument fault diagnosis in dynamic systems : M.N. Barkesseh, N.A. Kheir, pp 815–821

On-Line Multiple Component and Instrument Fault Diagnosis in Dynamic Systems

This paper presents a methodology, for on-line implementation, to diagnose failure(s) when it occurs in physical plant component(s) and/or Instrument(s). This methodology allows detectingcomponent faults by a bank of matched filters. The detection of instrument failures is accomplished by a bank of full-order Luenberger .observers. A rule-based technique is also developed and used to Identify a failure. Simulation results of an aircraft model have shown that this diagnostic approach is applicable to a large number of failures, and the action to remove these failures is also possible via an automated process.

Fault Diagnosis of Dynamic Systems Using Neural Networks

A method for detecting faults of nonlinear systems is developed using dynamic nonlinear predictor models which are realized with neural networks. Separate predictor models are identified for the process operating normally and for the situations where one of the potential faults has occurred. In monitoring the state of the process, the best fitting predictor of the bank is selected according to the Bayes rule. Radial basis function networks are used in identifying dynamic predictor models and the parameters of the networks are estimated with the orthogonal least squares algorithm. The performance of the proposed method is demonstrated in the simulation studies of a jacketed reactor.

On-Line Residual Compensation in Robust Fault Diagnosis of Dynamic Systems

This paper deals with the robust fault diagnosis problem for systems with unstructured uncertainties, for which disturbance de-coupling methods are not applicable. A technique for compensating the residual is proposed. By compensation, the effects of modelling errors on the residual will not adversely affect the detection and isolation of faults. The idea is to estimate approximately the bias term in the residuals due to modelling errors, then compensate it on-line. These estimates are used to form a compensated residual to decrease the effect of modelling errors on the residuals. The compensated residuals are then used to make the fault diagnosis decision. Simulation results illustrate the effect of incipient faults in sensors of a complex jet engine can be reliably detected with the method developed.

On-line residual compensation in robust fault diagnosis of dynamic systems

This paper deals with the robust fault diagnosis problem for systems with unstructured uncertainties, for which disturbance de-coupling methods are not applicable. A technique for compensating the residual is proposed. By compensation, the effects of modelling errors on the residual will not adversely affect the detection and isolation of faults. The idea is to estimate approximately the bias term in the residuals due to modelling errors, then compensate it on-line. These estimates are used to form a compensated residual to decrease the effect of modelling errors on the residuals. The compensated residuals are then used to make the fault diagnosis decision. Simulation results illustrate the effect of incipient faults in sensors of a complex jet engine can be reliably detected with the method developed.

Fault Diagnosis of Machine-Tools by Estimation of Signal Spectra

In this paper a method for the signal model based estimation of frequency spectra from sampled signals is presented. The algorithm uses discrete, parametric signal models in z-space, whose parameters are determined by a two step identification algorithm. From these parameters significant oscillations, described by their frequency and concatenated amplitude, are calculated to develop a method for the supervision and fault diagnosis of dynamic systems. The shown results and conclusions are taken from practical tests at machine-tools.

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results

The paper reviews the state of the art of fault detection and isolation in automatic processes using analytical redundancy, and presents some new results. It outlines the principles and most important techniques of model-based residual generation using parameter identification and state estimation methods with emphasis upon the latest attempts to achieve robustness with respect to modelling errors. A solution to the fundamental problem of robust fault detection, providing the maximum achievable robustness by decoupling the effects of faults from each other and from the effects of modelling errors, is given. This approach not only completes the theory but is also of great importance for practical applications. For the case where the prerequisites for complete decoupling are not given, two approximate solutions—one in the time domain and one in the frequency domain—are presented, and the crossconnections to earlier approaches are evidenced. The resulting observer schemes for robust instrument fault detection, component fault detection, and actuator fault detection are briefly discussed. Finally, the basic scheme of fault diagnosis using a combination of analytical and knowledge-based redundancy is outlined.

Evaluation of Analytical Redundancy for Fault Diagnosis in Dynamic Systems

The paper reviews the key concepts of fault detection and isolation in dynamic systems using analytical redundancy, and outlines the state of the art. It focuses on the methods of residual generation with emphasis to the latest attempts to achieve robustness with respect to modelling errors. In this connection a unified approach that provides complete decoupling of the effects of faults among each other and from the effects of modelling errors is presented. Two novel approaches - in the time and frequency domain - to the optimal solution of the robustness problem are outlined. Finally a framework of observer schemes for different kinds of fault detection and isolation is presented.

多仮説検定によるダイナミックシステムの故障診断

多仮説検定によるダイナミックシステムの故障診断