Artificial Neural Networks Modeling as a Diagnostic and Decision Making Tool
Fault diagnosis of a complex system, such as nuclear power plant (NPP), is an important part of the operator task. Artificial neural networks (ANN) model learns from the plant past behavior and is easy to develop if enough data is available for training, be it from actual plant history or from full-scale simulator fault situations. The operator is reluctant to depend on a “black-box” advice, and any reasonable explanation is welcome. Two examples of using ANN modeling for fault diagnosis are presented. The first is based on NPP full-scale simulator time history data of three instrument or component faults. The second example is the diagnosis of a seemingly erratic excessive steam turbine bearing vibration. The ANN models were able to correctly classes the causes of the faults. In the first case a knowledge extraction technique from trained ANN models, Causal Index, was used. It was able to provide plausible explanations for the ANN faults classification. In the second case, Genetic Algorithm was used as an optimization technique, with the ANN model providing the target function. It was able to identify the cause of the excessive vibration in a power plant turbine bearing.
Unable to display preview. Download preview PDF.
- Baba K, Enbutu I, Yoda M (1990) Explicit representation of knowledge acquired from plant historical data using neural network, Proceedings of the International Joint Conference on Neural Networks. San Diego, 3: 155–160.Google Scholar
- Boger Z (1992) Application of neural networks to water and wastewater treatment plant operation. Instrument Society of America Transactions 31 (1): 25–33.Google Scholar
- Boger Z (1997) Experience in industrial plant model development using large-scale artificial neural networks. Information Sciences–Applications 101 (3:4): 203–212.Google Scholar
- Boger Z, Guterman, H (1997) Knowledge extraction from artificial neural networks models. Proceedings of the IEEE International Conference on Systems Man and Cybernetics, SMC’97, Orlando, Florida, pp. 3030–3035.Google Scholar
- Boger Z, Ratton L, Kunt TA, Mc Avoy TJ, Cavicchi RE, Semancik S (1997) Robust classification of “artificial Nose” sensor data by artificial neural networks. Proceedings of the IFAC ADCHEM ‘87 Conference, Banff, Canada.Google Scholar
- Boger Z (1998) Implementing artificial neural networks in nuclear power plants diagnostic systems: Issues and challenges. Proceedings of the IAEA Technical Committee Meeting on Diagnostic Systems in Nuclear Power Plants, Istanbul, Turkey, IAEA-IWG-NPPCI-98/2, pp 149–160.Google Scholar
- Boger Z, Weber R (2000) Finding an optimal artificial neural network topology in real-life modeling - two approaches. Proceedings of the International Conference on Neural Computation 2000, NC2000’, Berlin, Germany.Google Scholar
- Friedrich CM (2000) http://www.tussy.uni-wh.de/—chris/gann/chrisLit/chrisLit.htmlGoogle Scholar
- Por G, Vasko J (1997) Application of an artificial intelligence software to model the excess vibration of a bearing in a conventional power plant. Proceedings of the ESPRIT ICIMSNOE annual conference, ASI’97. Budapest, Hungary.Google Scholar
- Reifman J, Vitela JE (1994) Accelerating learning of neural networks with conjugate gradients for nuclear power applications. Nuclear Technology 106: 225–241.Google Scholar
- Reifman J (1997) Survey of artificial intelligence methods for detection and identification of component faults in nuclear power plants. Nuclear Technology 119: 76–97.Google Scholar
- Turkcan E, Ciftcioglu O, van der Hagen THJJ (1998) Surveillance and fault diagnosis for power plants in the Netherlands: Operational Experience. Proceedings of the IAEA Technical Committee Meeting on Diagnostic Systems in Nuclear Power Plants, Istanbul, Turkey, IAEA-IWG-NPPCI-98/2, pp 53–70.Google Scholar