Neural Network Integration Fusion Model and Application

A new fusion model is proposed, which is the combination of BP neural networks and rough set algorithm, to solve the problems of low precision rate in aircraft engine fault diagnosis by traditional methods. The method realizes feature level fusion of all subjective data and expert experiments on different parts of engine, and the predominance compensation of different models. In simulation experiment, the method proposed in the paper can improve diagnosis precision 5.0% more than expert system.