Robust fault detection using set membership estimation and T-S fuzzy neural network
Authors:
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 07431619,p. 893-898
Abstract
A robust fault detection method is proposed for nonlinear dynamical systems with unknown but bounded noises. The Takagi-Sugeno (T-S) fuzzy neural network is used to build a model of the nonlinear dynamical system when the system is fault-free, taking into account that it is a universal approximator. The input space is partitioned by means of a fuzzy clustering algorithm based on the input and output data of the system. Supposing that the system noise and approximation error are unknown but bounded, the consequence parameters of the T-S fuzzy neural network are determined using a linear-in-parameter set membership estimation algorithm. An interval guaranteed to contain the actual output of the fault-free system is obtained by propagating the effect of model uncertainty to the model output. An occurrence of the fault is signaled when the measured output crosses the computed interval. Simulation results show the effectiveness of the proposed method.Keywords
This publication has 16 references indexed in Scilit:
- Improved zonotopic method to set membership identification for systems with time-varying parametersIET Control Theory & Applications, 2011
- Fault detection and diagnosis based on parameter set estimationIET Control Theory & Applications, 2011
- Confidence estimation of the multi-layer perceptron and its application in fault detection systemsEngineering Applications of Artificial Intelligence, 2008
- Robust fault detection using zonotope‐based set‐membership consistency testInternational Journal of Adaptive Control and Signal Processing, 2008
- Computationally efficient algorithms for state estimation with ellipsoidal approximationsInternational Journal of Adaptive Control and Signal Processing, 2002
- A clustering algorithm for fuzzy model identificationFuzzy Sets and Systems, 1998
- Fault diagnosis of machines via parameter estimation and knowledge processing—Tutorial paperAutomatica, 1993
- Fuzzy basis functions, universal approximation, and orthogonal least-squares learningIEEE Transactions on Neural Networks, 1992
- Process fault detection based on modeling and estimation methods—A surveyAutomatica, 1984
- A survey of design methods for failure detection in dynamic systemsAutomatica, 1976