Fault Diagnosis System for Turbo-Generator Set Based on Self-Organized Fuzzy Neural Network

Abstract

Aiming at the problem of lower accuracy of vibration fault diagnosis system for turbo-generator set, a new diagnosis method based on self-organized fuzzy neural network is proposed and a self-organized fuzzy neural network system is structured for diagnosing faults of large-scale turbo-generator set in this paper by associating the fuzzy set theory with neural network technology. Especially, an effective fuzzy self-organized method for training samples of neural network is presented and the standard sample database for diagnosis neural network is established. Finally, supported by the 108DAI detecting system, a vibration fault diagnosis system of 600MW turbo-generator set is designed and realized by the proposed system structure, its running results in a thermal power plant of Guangdong Province show that this new diagnosis system can satisfy fault diagnosis requirement of large turbo-generator set. Its accuracy varies from 92 percent to 98 percent.