Fault detection method for nonlinear systems based on probabilistic neural network filtering. (English) Zbl 1031.93083
Summary: A fault detection method for nonlinear systems, which is based on Probabilistic Neural Network Filtering (PNNF), is presented. PNNF limits the maximum estimation error of the asymptotic Bayes optimal result and describes the tracking process with an expression. On the basis of these properties of PNNF and the statistical characteristics of the noise of the system, a fault threshold can be better calculated, especially for the tracking process corresponding to a strong disturbance. According to the threshold, the fault can be detected by evaluating the residuals. Also, for some special cases in which a fault is potential but the system is in steady state, the information for fault detection may be insufficient and a group of disturbances are artificially input with definite amplitudes, so that the result of detection can be enhanced by comparing the real with the expected tracking processes of the filter. Examples are given to demonstrate the method of fault detection based on PNNF.
MSC:
| 93B51 | Design techniques (robust design, computer-aided design, etc.) |
| 93E11 | Filtering in stochastic control theory |
| 92B20 | Neural networks for/in biological studies, artificial life and related topics |
| 93C10 | Nonlinear systems in control theory |
References:
| [1] | DOI: 10.1109/TAC.1984.1103593 · Zbl 0542.90040 · doi:10.1109/TAC.1984.1103593 |
| [2] | DOI: 10.1109/TAC.1974.1100534 · Zbl 0278.49039 · doi:10.1109/TAC.1974.1100534 |
| [3] | FRANK, P. M. Fault diagnosis in dynamic systems via state estimation-A survey. Proceedings of the First European Workshop on Fault Diagnostics, Reliablity and Related Knowledge Based Approaches. Dordrecht. pp.35–98. Reidel. |
| [4] | DOI: 10.1016/0005-1098(94)90169-4 · Zbl 0799.93018 · doi:10.1016/0005-1098(94)90169-4 |
| [5] | DOI: 10.1080/00207729408949341 · Zbl 0822.93046 · doi:10.1080/00207729408949341 |
| [6] | DOI: 10.1109/9.58536 · Zbl 0729.93016 · doi:10.1109/9.58536 |
| [7] | DOI: 10.1016/0005-1098(84)90098-0 · Zbl 0539.90037 · doi:10.1016/0005-1098(84)90098-0 |
| [8] | KALMAN R. E., Transaction of the ASME, Series D: Journal of Basic Engineering. 83 pp 95– (1961) · doi:10.1115/1.3658902 |
| [9] | SCHMIDT S. F., Computational Techniques in Kaiman Filtering, in Theory and Application of Kaiman Filtering. (1970) |
| [10] | SPECHT, D. F. Probabilistic neural networks for classification, mapping or associative memory. Proceedings of the IEEE 1st International Conference on Neural Network. San Diego, CA. pp.525–532. |
| [11] | DOI: 10.1109/72.80210 · doi:10.1109/72.80210 |
| [12] | DOI: 10.1016/0893-6080(90)90049-Q · doi:10.1016/0893-6080(90)90049-Q |
| [13] | DOI: 10.1109/72.822513 · doi:10.1109/72.822513 |
| [14] | DOI: 10.1109/72.641464 · doi:10.1109/72.641464 |
| [15] | DOI: 10.1016/0005-1098(76)90041-8 · Zbl 0345.93067 · doi:10.1016/0005-1098(76)90041-8 |
| [16] | DOI: 10.1109/TAC.1987.1104682 · Zbl 0625.93071 · doi:10.1109/TAC.1987.1104682 |
| [17] | DOI: 10.1016/S0005-1098(96)00111-2 · Zbl 0876.93017 · doi:10.1016/S0005-1098(96)00111-2 |
| [18] | DOI: 10.1016/S0005-1098(98)00085-5 · Zbl 0961.93007 · doi:10.1016/S0005-1098(98)00085-5 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
