基于提升小波和递归增量聚类的实时故障诊断方法

针对复杂时变工业过程实时故障诊断问题，提出了一种基于提升小波( lifting wavelet, LW) 与递归增量聚类（recursive incremental clustering, RICLUSTER）相结合的实时故障诊断方法（lifting wavelet recursive incremental clustering， LW-RICLUSTER）。该方法首先通过LW变换对数据实时去噪，再通过RICLUSTER实时监控。由于采用LW与RICLUSTER相结合的方法，节省存储空间和运算时间的同时提高了诊断精度。实验结果表明，LW RICLUSTER集合方法能有效实现时变过程监控, 在诊断精度、速度和适应性方面，优于传统单一型CLUSTER方法。

Real time fault diagnosis approach based on lifting wavelet and recursive incremental clustering

An ensemble real time fault diagnosis method based on lifting wavelet (LW) and recursive incremental clustering（RICLUSTER）, called LW-RICLUSTER, is proposed to realize real time monitoring for complex time varying industrial processes. Firstly, data are denoised by LW transform in real time, then RICLUSTER is used for real time monitoring. With the ensemble approach, storage space is saved and computing time is shortened, while the precision of diagnostic is increased. Experiment results show that the LW -RICLUSTER algorithm can monitor time varying process. The LW-RICLUSTER is superior to the traditional single CLUSTER in diagnosis precision, rate and adaptability.