Hopfield/ART-1 Neural Networks based Fault Detection and Isolation

A new approach to detect and isolate faults in linear dynamic systems is proposed. System parameters are estimated by Hopfield type neural network, while the system is in certain operating stage. When the system dynamics changes, estimated parameters go through a transition period and this is used to detect faults. But the estimates are not reliable enough to be used for isolating faults. The judgement on the instance at which the system moves out of the transition zone is made through a user specified threshold on the sum of squares of residuals in a moving window. Once the system is out of the transition zone and settles to a new operating level, the estimated parameters are classified using an ART-1 based network. The proposed scheme is implemented to detect faults in a position servo system.

[1]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results , 1990, Autom..

[2]  George Vachtsevanos,et al.  Managing ignorance and uncertainty in system fault detection and identification , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[3]  Rolf Isermann,et al.  Process fault detection based on modeling and estimation methods - A survey , 1984, Autom..

[4]  R. Li,et al.  Dynamic fault detection and diagnosis using neural networks , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[5]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .

[6]  George C. Verghese,et al.  Optimally robust redundancy relations for failure detection in uncertain systems , 1986, Autom..

[7]  W. B. Ribbens,et al.  Detection and Isolation of Plant Failures in Dynamic Systems , 1991, 1991 American Control Conference.

[8]  S. Naidu,et al.  Application of Neural Networks on the Detection of Sensor Failure During the Operation of a Control System , 1989, 1989 American Control Conference.

[9]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Alan S. Willsky,et al.  A survey of design methods for failure detection in dynamic systems , 1976, Autom..

[12]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[13]  Wallace E. Vander Velde,et al.  Failure Detection And Isolation Experiments With The Langley Mini-Mast , 1990 .

[14]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.