Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network

In this paper, fault detection and diagnosis of a permanent-magnet DC motor is discussed. Parameter estimation based on block-pulse function series is used to estimate the continuous-time model of the motor. The electromechanical parameters of the motor can be obtained from the estimated model parameters. The relative changes of electromechanical parameters are used to detect motor faults. A multilayer perceptron neural network is used to isolate faults based on the patterns of parameter changes. Experiments with a real motor validate the feasibility of the combined use of parameter estimation and neural network classification for fault detection and isolation of the motor.

[1]  Cw Chan,et al.  Fault detection of DC motors using nonlinear observer based on recurrent B-spline networks , 1999 .

[2]  Mo-Yuen Chow,et al.  Using a neural/fuzzy system to extract heuristic knowledge of incipient faults in induction motors. Part I-Methodology , 1995, IEEE Trans. Ind. Electron..

[3]  Dieter Filbert.  Intelligent measurement methods in technical diagnosis and quality assurance - a comparison , 1988 .

[4]  Mao Zongyuan,et al.  On-line incipient fault detection of induction motors using artificial neural networks , 1994, Proceedings of 1994 IEEE International Conference on Industrial Technology - ICIT '94.

[5]  Christian Schneider,et al.  Parameter Estimation and Residual Analysis A Comparison , 1994 .

[6]  Mo-Yuen Chow,et al.  On the application and design of artificial neural networks for motor fault detection. II , 1993, IEEE Trans. Ind. Electron..

[7]  R. Isermann.  Integration of Fault Detection and Diagnosis Methods , 1994 .

[8]  Jie Chen,et al.  Identification of physical parameters of ground vehicle using block-pulse function method , 1990 .

[9]  D. M. Himmelblau,et al.  Determination of optimal measuring sites for fault detection of non-linear systems , 1985 .

[10]  H. Y. Zhang,et al.  Identification of stochastic multivariable continuous-time systems , 1990 .

[11]  Giovanni Franceschini,et al.  Development of expert system knowledge base to on-line diagnosis of rotor electrical faults of induction motors , 1992, Conference Record of the 1992 IEEE Industry Applications Society Annual Meeting.

[12]  F. Filippetti,et al.  Neural networks aided on-line diagnostics of induction motor rotor faults , 1993, Conference Record of the 1993 IEEE Industry Applications Conference Twenty-Eighth IAS Annual Meeting.

[13]  T.G. Habetler,et al.  Motor bearing damage detection using stator current monitoring , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[14]  Mo-Yuen Chow,et al.  On the application and design of artificial neural networks for motor fault detection. I , 1993, IEEE Trans. Ind. Electron..

[15]  Dieter Filbert.  Advanced fault diagnosis for the mass production of small-power electric motors , 1993, Other Conferences.