A new engine fault diagnosis model based on sound intensity signal and BP neural network integration was proposed. Firstly, the sound intensity signals were decomposed and recomposed by using wavelet packets. Afterwards, the signal energy values were extracted from each frequency band, and were used as input features into the BP neural network integration for fault pattern recognition. It has been testified by the experimentation of the 3Y Toyota 2.0 engine and the results showed that it could increase the efficiency and accuracy of the system.
参考文献
相似文献
引证文献
引用本文
李增芳,何勇,徐高欢.基于声强信号分析和组合神经网络的发动机故障诊断[J].农业机械学报,2008,39(12):170-173.[J]. Transactions of the Chinese Society for Agricultural Machinery,2008,39(12):170-173.