|
Feng Zhipeng
Department of Precision
Instruments
and Mechanology,
Tsinghua University,
Beijing 100084, China
Song Xigeng
Institute of Internal Combustion Engine,
Dalian University of Technology,
Dalian 116024, China
Chu Fulei
Department of Precision Instruments
and Mechanology,
Tsinghua University,
Beijing 100084, China |
|
|
FAULT DIAGNOSIS BASED ON INTE- GRATION
OF CLUSTER ANALYSIS, ROUGH SET METHOD AND FUZZY NEURAL NETWORK
Abstract: In order to increase the efficiency and decrease the cost of machinery diagnosis, a hybrid system of computational intelligence methods is presented. Firstly, the continuous attributes in diagnosis decision system are discretized with the self-organizing map (SOM) neural network. Then, dynamic reducts are computed based on rough set method, and the key conditions for diagnosis are found according to the maximum cluster ratio. Lastly, according to the optimal reduct, the adaptive neuro-fuzzy inference system (ANFIS) is designed for fault identification. The diagnosis of a diesel verifies the feasibility of engineering applications.
Key words:
Fault diagnosis Self-erganizing map Rough sets Adaptive neuro-fuzzy inference system
|