Physical Parameter Estimation Based FDI with Neural Networks

Abstract A fault diagnosis scheme is proposed which is based on the parameter estimation with neural networks approach. The system physical parameters, which are used for characterisation the system's working situation, are directly estimated by a special neural networks. Using the universal approximation property of the neural networks, the system physical parameter estimation can be taken as general nonlinear function of the measured I/O data. These functions are approximated by the trained neural networks. The deviation of the estimated parameters to their nominal values are used for fault detection, isolation and identification of the fault severity. A simulation example is also provided to support the proposed method

[1]  M FrankPaul.  Fault diagnosis in dynamic systems using analytical and knowledge-based redundancya survey and some new results , 1990 .

[2]  Paul M. Frank,et al.  Fault Diagnosis in Dynamic Systems , 1993, Robotics, Mechatronics and Manufacturing Systems.

[3]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

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

[6]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[7]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[8]  Hubert A.B. Te Braake,et al.  Random activation weight neural net (RAWN) for fast non-iterative training. , 1995 .

[9]  Heikki N. Koivo,et al.  Artificial neural networks in fault diagnosis and control , 1994 .

[10]  R. Patton,et al.  A Review of Parity Space Approaches to Fault Diagnosis , 1991 .

[11]  Paul M. Frank,et al.  Observation Filtering: from Qualitative Simulation to Qualitative Observer , 1996 .

[12]  R. J. Kuo.  Intelligent diagnosis for turbine blade faults using artificial neural networks and fuzzy logic , 1995 .

[13]  J.J. Gertler,et al.  Survey of model-based failure detection and isolation in complex plants , 1988, IEEE Control Systems Magazine.

[14]  Marcello R. Napolitano,et al.  Aircraft failure detection and identification using neural networks , 1993 .

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

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