一种新的间歇过程故障检测方法  

A New Research of Fault Detection Method for Batch Processes

作　　者：王静[1] 侍洪波[1] 

机构地区：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237

出　　处：《华东理工大学学报（自然科学版）》2014年第4期506-510,532,共6页Journal of East China University of Science and Technology

摘　　要：针对间歇过程的多阶段问题,提出了一种新的划分阶段策略,可以将多阶段的数据进行准确的聚类,得到精确的阶段数目,避免陷入局部最优,提高了建模精度和故障检测准确度。首先采用不同展开方法相结合的方式对三维的间歇过程数据进行处理,消除了数据预估问题;其次结合图划分准则利用谱聚类方法将处理后的数据进行准确的阶段划分,并运用PCA建模方法分别对每一类进行建模;最后通过合适的模型对数据进行在线监控。通过青霉素仿真过程验证了本文方法的有效性。Abstract： A phase segmentation strate is proposed in this paper. It can not only o optimum, but also improve the precision of operation phases falling modeling and the accurate of fault detection. Firstly, into local the threedimension-batch process is handled by integrating several expansion methods such that the data estimation step may be removed. And then, the spectral clustering method together with graph partitioning criterion is utilized to divide the above data into several clusters which is further modeled via PCA. Finally, a suitable model is applied to monitor these data on-line. The effectiveness and flexibility of the proposed method is validated through penicillin simulation process.

关 键 词：间歇过程 故障检测 谱聚类 多阶段操作过程 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]