Research on marine turbine rotor fusion diagnosis system based on neural network and D-S evidence theory
Chun-li Xie · Applied science and technology · 2004
The marine turbine rotor is the main work component of a turbine, and it has faults easily. The data fusion technology was applied to the fault diagnosis field. The fusion diagnosis system of a turbine rotor was built for diagnosing the faults of a rotor,by using neural network and D-S evidence theory. The data were classified in the data fusion level, which can reflect the system state in multi-aspect, and it lays the foundations of exactly diagnosing the faults . In the feature level multi-neural networks were used to overcome the disadvantage of the network convergence speed slow.The results were calculated and fused through the decision level, and the precision of diagnosis was improved. The diagnostic tests and comparison experiments prove that the diagnosis system can improve the diagnostic precision, and satisfy the requirement for real time.