基于动态内并行潜结构投影的故障检测方法

Fault detection method based on dynamic inner concurrent projection to latent structure

针对实际工业过程故障检测时存在误报警现象及易缺失部分时段质量数据的问题,提出在线监测动态内潜结构投影(OM-DiPLS)模型.该模型通过引入时延的质量数据,使得在缺失部分时段质量数据时能够实现模型的更新.为了更好地监控质量变量中不可预测的信息,基于OM-DiPLS模型提出在线监测动态内并行潜结构投影模型.该模型将过程数据和质量数据投影到输入输出相关的协变子空间、输出无关但过程相关的输入主子空间、输入残差子空间、不可预测的输出主子空间及输出残差子空间,通过对各子空间构造相应的统计量,实现过程监测.田纳西-伊斯曼过程仿真的实验表明,利用所提算法有效提高了质量相关故障的有效检测率,降低了质量无关故障的误报率.

The online monitoring dynamic inner projection to latent structures(OM-DiPLS)model was proposed aiming at the problems of false alarm and missing quality data of some periods in actual industrial process fault detection.The model can be updated when quality data of some periods were missing by introducing quality data of time delay.An online monitoring dynamic internal concurrent latent structure projection(OM-DiCPLS)model was proposed based on the OM-DiPLS model in order to better monitor the unpredictable information in the quality variables.The process data and quality data were projected into the covariant subspace with relevant inputs and outputs,the input principal subspace with unrelated outputs but relevant processes,the input residual subspace,the unpredictable output principal subspace and the output residual subspace.Process monitoring was realized by constructing corresponding statistics for each subspace.The Tennessee-Eastman process simulation experiment shows that the proposed algorithm effectively improves the effective detection rate of quality-related faults and reduces the false alarm rate of quality-unrelated faults.