基于EMD与PNN的机械故障检测

MACHINERY FAULT DIAGNOSIS BASED ON EMD AND PNN

故障特征提取和状态识别是机械设备故障检测的关键内容。经验模式分解是处理非线性、非平稳信号的新方法,EMD能将复杂的信号分解为有限个固有模态函数。将经验模式分解与概率神经网络结合起来用于机械故障检测中,实验结果表明该方法快速准确而且易于实现。

Feature extraction and condition identification are the two key processes of machinery fault diagnosis. Empirical Mode Decompo- sition （EMD） is a novel method of time-frequency analysis to process non-linear and unstable signals. The key process of EMD is that any complicated data set can be decomposed into a finite number of Intrinsic Mode Functions （IMF）. In this thesis Empirical Mode Decomposition and Probabilistic Neural Network （PNN） are jointly applied to machinery fault diagnosis. Simulation results show that the proposed method is featured by swiftness, accuracy and ease of practical application.