一种基于输入训练神经网络的非线性PCA故障诊断方法

Input-training neural network-based nonlinear principal component analysis approach for fault diagnosis

简要讨论了线性 PCA故障诊断方法存在的问题 ,提出一种基于输入训练神经网络的非线性PCA故障诊断方法。该方法首先利用输入训练神经网络和 BP网络双网络机制 ,实现非线性主元的识别 ,并采用统计方法进行故障检测与故障分离。对 CSTR的仿真研究结果表明 ,该方法能够克服线性PCA方法在提取过程变量的非线性特征方面存在的不足 ,并能够准确地进行故障检测和分离。

Some problems existing in the linear principal component analysis methodology are discussed briefly. A nonlinear principal component analysis methodology based on input-training neural network is presented for fault diagnosis. Input-training neural network and BP neural network are used to estimate the nonlinear principal component scores. Fault detection and diagnosis are performed by means of statistical methods. The simulation research to continuous stirred tank reactor (CSTR) is performed to show its advantages in extracting the nonlinear features compared with the linear principal component analysis methodology.