摘要
为了提高故障检测准确率,提出了基于动态受控主元分析(dynamic controlled principal component analysis,DCPCA)模型的故障检测方法。首先,利用DCPCA提取动态受控主元(dynamic controlled principal component,DCPC),所得DCPC包含过程的自回归特性和与控制输入之间的动态因果关系,使得构建的DCPCA模型更精确。然后,针对传统方法只对过程变量进行静态空间结构的故障检测,忽略了动态特性的问题,基于DCPCA模型适时应用检测综合指标,对系统进行静态重构误差和动态模型误差的双重检测,使得检测结果更全面。最后,基于田纳西-伊斯曼(Tennessee-Eastman,TE)过程的仿真结果验证了所提方法的可行性和有效性。
In order to improve the accuracy of fault detection,a fault detection method based on dynamic controlled principal component analysis(DCPCA)model is proposed.Firstly,DCPCA is used to extract the dynamic controlled principal component(DCPC),and the DCPC contains the autoregressive characteristics of the process and the dynamic causal relationship with the control input,which makes the DCPCA model accurate.Then,to solve the problem that traditional methods only detect the static spatial structure faults of process variables and ignore the dynamic characteristics,a comprehensive detection indicator is applied based on the DCPCA model to detect both static reconstruction errors and dynamic model errors in time,so that the detection results are more comprehensive.Finally,simulation results based on Tennessee-Eastman(TE)process verify the feasibility and effectiveness of the proposed method.
作者
陈硕
栾小丽
刘飞
CHEN Shuo;LUAN Xiaoi;LIU Fei(School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China)
出处
《控制工程》
CSCD
北大核心
2024年第7期1280-1285,共6页
Control Engineering of China
基金
国家自然科学基金资助项目(61991402,61833007,61991400)。
关键词
动态受控主元分析
故障检测
综合指标
静态重构误差
动态模型误差
Dynamic controlled principal component analysis
fault detection
comprehensive indicator
static reconstruction error
dynamic model error
