Title :
A novel approach for fault diagnosis of steam turbine based on neural network and genetic algorithm
Author :
Guo, Qinglin ; Zhang, Ming
Author_Institution :
Dept. of Comput. Sci. & Technol., Peking Univ., Beijing
Abstract :
A novel approach for data mining of steam turbine based on neural network and genetic algorithm is brought forward, aimed at overcoming shortages of some current knowledge attaining methods. The historical fault data of steam turbine is processed with fuzzy and discrete method firstly, a multiplayer backpropagation neural network is structured secondly, the neural network is trained via teacherpsilas guidance thirdly, and the neural network is optimized by genetic algorithm lastly. Based on the ontology of neural network, the data mining algorithm for classified fault diagnosis rules about steam turbine is brought forward; its realization process is as follows: (1) computing the measurement matrix of effect; (2) extracting rules; (3) computing the importance of rules; (4) shearing the rules by genetic algorithm. An experimental system for data mining and fault diagnosis of steam turbine based on neural network and genetic algorithm is implemented. Its diagnosis precision is 84%. And experiments do prove that it is feasible to use the method to develop a system for fault diagnosis of steam turbine, which is valuable for further study in more depth.
Keywords :
backpropagation; data mining; fault diagnosis; fuzzy neural nets; genetic algorithms; matrix algebra; ontologies (artificial intelligence); pattern classification; power engineering computing; power generation faults; steam turbines; data mining; fault diagnosis rule classification; fuzzy method; genetic algorithm; knowledge attaining method; measurement matrix; multiplayer backpropagation neural network; neural network training; ontology; steam turbine fault diagnosis; teacher guidance; Backpropagation; Computer networks; Data mining; Fault diagnosis; Fuzzy neural networks; Genetic algorithms; Neural networks; Ontologies; Optimization methods; Turbines; Data mining; Fault diagnosis; Genetic algorithm; Neural network; Ontology; Steam turbine;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4633762