Application of integrated neural network based on information combination for fault diagnosis in steam turbine generator

In view of the disadvantage of single neural network, a fault diagnosis system based on the integrated neural network used information combination is proposed. The preliminary diagnosis is made for the equipment by using the sub-neural network. And then the sub-neural networks are combined to make the decision. The simulation of steam turbine generator setspsila fault diagnosis demonstrates that the system takes full advantages of diversified information and improves diagnosis precision.