CIESC Journal ›› 2016, Vol. 67 ›› Issue (12): 5131-5139.DOI: 10.11949/j.issn.0438-1157.20160543

Previous Articles     Next Articles

Time constrained NPE for fault detection in chemical processes

YANG Jian, SONG Bing, TAN Shuai, SHI Hongbo   

  1. Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, China
  • Received:2016-04-26 Revised:2016-07-26 Online:2016-12-05 Published:2016-12-05
  • Supported by:

    supported by the National Natural Science Foundation of China(61374140) and the Young Scientists Fund of the National Natural Science Foundation of China(61403072).

时序约束NPE算法在化工过程故障检测中的应用

杨健, 宋冰, 谭帅, 侍洪波   

  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
  • 通讯作者: 侍洪波。hbshi@ecust.edu.cn
  • 基金资助:

    国家自然科学基金项目(61374140);国家自然科学基金青年科学基金项目(61403072)。

Abstract:

For fault detection in dynamic processes, a novel dimensionality reduction method was proposed on the basis of improved neighbor selection in neighborhood preserving embedding algorithm, i.e., time constrained neighborhood preserving embedding(TCNPE). Compared to neighborhood preserving embedding(NPE), which selected neighborhood only by Euclidean distance, TCNPE selected neighborhoods within certain timeframe by k-nearest neighboring method with a consideration of time series correlation between data points and constructed a localized constraining relationship between near and distant neighborhoods within this time window. First, TCNPE algorithm extracted main features of the process data and performed linear dimensionality reduction. Next, Hotelling's T2 and SPE statistics were established for online process monitoring and kernel density estimation(KDE) was used to determine control limits. Case study and simulation of Tennessee-Eastman Process demonstrated efficacy of the proposed method.

Key words: process control, dynamic modeling, neighborhood preserving embedding, linear dimensionality reduction, fault detection, experimental validation

摘要:

针对动态过程的故障检测问题,在邻域保持嵌入算法中改进邻域挑选,提出一种新的维度约简方法:时序约束邻域保持嵌入(time constrained neighborhood preserving embedding,TCNPE)算法。与邻域保持嵌入(neighborhood preserving embedding,NPE)算法只通过欧氏距离挑选邻域不同的是,TCNPE考虑到数据之间的时序相关性,在一定长度的时间窗之内采用k-近邻方法挑选邻域,并对时间窗内近邻与非近邻构造局部约束关系。首先,利用TCNPE提取数据特征,进行线性降维,然后构造T2和SPE统计量并利用密度估计(kernel density estimation,KDE)确定其控制限。最后,通过数值例子和TE过程(Tennessee-Eastman process)仿真来说明本文方法的有效性。

关键词: 过程控制, 动态建模, 邻域保持嵌入, 线性降维, 故障检测, 实验验证

CLC Number: