KL散度多模块滑动窗口慢特征分析的故障诊断方法

KL divergence multi-block moving window slow feature analysis method for fault diagnosis

针对传统分块方法根据经验划分子块导致变量特征信息无法充分利用,其单一的建模方式忽略局部信息以及离线模型无法适应时变特性的问题,提出了一种KL (Kullback-Leibler)散度多模块滑动窗口慢特征分析方法。在正常工况数据集中,利用KL散度来度量变量间的距离,同时引入最小误差平方和准则进行聚类,分成两个距离最小的子模块;在此基础上利用慢特征分析方法对每个子模块进行建模,结合滑动窗口对每次采样的数据进行更新,得到最优模型,分别计算监测统计信息,利用支持向量数据描述对故障监测结果进行融合,实现故障诊断。并将该方法应用于田纳西伊斯曼过程的监控中,得到了较高的故障检测率和较低的虚警率,验证了该方法的可行性和有效性。

A KL(Kullback-Leibler) divergence multi-block moving window slow feature analysis method was proposed to solve the problems that the variable feature information cannot be fully utilized by the traditional block segmentation method based on experience,the local information is ignored by a single modeling method,and the off-line model cannot adapt to the time-varying characteristics.KL divergence was used to measure the distance between variables in the normal working condition data set,and the minimum error sum criterion was introduced to cluster,which was divided into two sub-blocks with the minimum distance.On this basis,the slow feature analysis method was utilized to model each sub-block,and the optimal model was obtained by updating the sampled data with moving window.Monitoring statistics were calculated respectively,and the fault monitoring results were fused with support vector data description to achieve fault diagnosis.The proposed method was applied to the monitoring of Tennessee Eastman process,and higher fault detection rate and lower false alarm rate are obtained,verify the feasibility and effectiveness of this method.