论文信息 - Neural observer-based approach to fault detection and isolation of a three-tank system

Neural observer-based approach to fault detection and isolation of a three-tank system

The simulated laboratory set-up Three-Tank System is investigated from the standpoint of fault-tolerant control. The problem of robust model-based diagnosis is therefore addressed. Dynamic neural networks with mixed structure are used to design different observer-based schemes. Symptom evaluation is based on static neural nets. They are used to classify the obtained residuals. Different classifiers and decision criteria are analysed. Experimental results of simulation are included into a comparative study. This refers to actuator, component and instrument fault detection and isolation.

P. M. Frank | T. Marcu | M. H. Matcovschi

[1] B. Dubuisson. An adaptive decision system using pattern recognition , 1992 .

[2] Paul M. Frank,et al. Neural observer schemes for robust detection and isolation of process faults , 1998 .

[3] Ron J. Patton,et al. Fault-Tolerant Control: The 1997 Situation , 1997 .

[4] Paul M. Frank,et al. New developments using AI in fault diagnosis , 1996 .

[5] Susanne Ernst,et al. Identification with Dynamic Neural Networks - Architectures, Comparisons, Applications , 1997 .

[6] Rolf Isermann,et al. Trends in the Application of Model Based Fault Detection and Diagnosis of Technical Processes , 1996 .

[7] P. M. Frank,et al. Neural observer-based approach to fault-tolerant control of a three-tank system , 1999, 1999 European Control Conference (ECC).