Aeroengine fault diagnosis based on IPSOElman neural network

An Elman neural network optimized by improved particle swarm optimization algorithm was proposed to improve the accuracy of aeroengine fault diagnosis. The input variables of the neural network were selected by MIV (mean impact value) to reduce the dimension. The improved particle swarm optimization algorithm was used to optimize the weights and thresholds of the Elman neural network, and the optimized neural network was trained. The trained neural network was used to diagnose the aeroengine fault and compared with the conventional BP（back propagation）, Elman neural networks, GM(1,n), SVM (support vector machines). The simulation results show that the diagnostic error of IPSOElman (improved particle swarm optimization Elman neural network) is smaller than other methods，and it has a good diagnosis ability and strong adaptability when the selection fault diagnosis performance parameters have changed.