Title :
One method of translating the fuzzy rules into neural network of the fault diagnosis system
Author :
Wei, Li ; Junwei, Gao ; Xiping, Chen
Author_Institution :
Gansu Univ. of Technol., Lanzhou, China
fDate :
6/22/1905 12:00:00 AM
Abstract :
Based on the analysis of fuzzy rules and the certainty factor transitive algorithm of the fault diagnosis system, one method of translating the fuzzy rules into an artificial neural network is researched. According to the fuzzy rules and its certainty factor transitive algorithm, the teacher samples of the neural network can be obtained. The weights and thresholds matrix of the neural network can be obtained by samples learning, so the new fault samples can be diagnosed. According to the diagnosis result obtained from the testing samples, this method can diagnose rapidly, it also has strong generalization ability and high accuracy, at the same time the method can eliminate the conflict in the reasoning process
Keywords :
case-based reasoning; fault diagnosis; fuzzy neural nets; learning by example; certainty factor transitive algorithm; fault diagnosis system; fuzzy rules; samples learning; strong generalization ability; teacher samples; thresholds matrix; Algorithm design and analysis; Artificial neural networks; Fault diagnosis; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Hydroelectric power generation; Neural networks; Testing;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.860077