Hybrid expert system - neural network - Fuzzy Logic methodology for transient identification

摘要

A methodology is presented that demonstrates the potential of pretrained artificial neural networks (ANN's) as generators of membership functions for the purpose of transient identification in Nuclear Power Plants (NPP). In order to provide timely concise and task-specific information about the many aspects of the transient and to determine the state of the system based on the interpretation of potentially noisy data, a model-referenced approach is utilized, where pretrained ANNs provide the model. Membership functions -- that condense information about a transient in a form convenient for a rule-based identification system -- are produced through ANN'S. The results demonstrate the extremely good noise-tolerance of ANN's and suggest a new method for transient identification within the framework of Fuzzy Logic.