Power transformers are major elements of the electric power transmission and distribution infrastructure. Transformer failure has severe economical impacts from the utility industry and customers. This paper presents analysis, design, development, and experimental evaluation of a robust failure diagnostic technique. Hopfield neural networks are used to identify variations in physical parameters of the system in a systematic way, and adapt the transformer model based on the state of the system. In addition, the Hopfield network is used to design an observer which provides accurate estimates of the internal states of the transformer that can not be accessed or measured during operation. Analytical and experimental results of this adaptive observer for power transformer diagnostics are presented.
Neural Network-Based Adaptive Monitoring System for Power Transformer
Contributed by the Dynamic Systems and Control Division for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received by the Dynamic Systems and Control Division February 11, 1999. Associate Editor: S. Nair.
Ottele , A., and Shoureshi, R. (February 11, 1999). "Neural Network-Based Adaptive Monitoring System for Power Transformer ." ASME. J. Dyn. Sys., Meas., Control. September 2001; 123(3): 512–517. https://doi.org/10.1115/1.1387248
Download citation file: