非线性和非高斯性共存的序批次反应处理过程故障诊断（英文）  

Fault diagnosis of sequential batch reaction process with nonlinear and non-Gaussian coexistence

作　　者：常鹏 乔俊飞[1,2] 王普 高学金[3] CHANG Peng;QIAO Jun-fei;WANG Pu;GAO Xue-jin(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing 100124,China;Research Engineering Center of Digital Community Ministry of Education,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124 [2]北京工业大学计算智能和智能系统北京市重点实验室,北京100124 [3]北京工业大学数字社区教育部工程研究中心,北京100124

出　　处：《控制理论与应用》2019年第5期728-736,共9页Control Theory & Applications

基　　金：Supported by the National Natural Science Foundation of China(61364009,61174109);the Beijing Postdoctoral Research Foundation

摘　　要：序批式反应器(SBR)的处理过程的数据具有非高斯分布和高度非线性的特点,传统特征提取方法在进行特征提取时仅仅考虑信息最大化而忽略数据的簇结构信息导致数据特征提取的不完整.由于多向核熵成分分析是一种新的监测方法,在监测过程中的应用表明能够克服传统监测方法的缺陷,减少误报警率.因此本文结合多向核熵成分分析的的优势,提出多向核熵独立成分分析方法用于SBR过程监测及故障诊断.首先,将三维SBR过程数据利用一种新的数据展开技术变为二维数据;其次,利用核熵成分分析将展开后的二维数据映射到高维空间用独立成分分析进行独立成分提取;最后提出一种基于多向核熵独立成分分析的故障诊断方法进行故障诊断.将该方法和传统方法应用于80升的SBR处理过程的监测结果表明,本文提出的方法优于传统的多向独立成分分析方法.The data of sequencing batch reactor (SBR) has characteristics of non-Gaussian distribution and high nonlinearity, In order to solve the problem that SBR process monitoring algorithm can only maximize the use of data information and ignore the information in the structure of data cluster, a new multi-way kernel entropy component analysis (MKECA) method is proposed. It also address the shortcomings of the traditional monitoring method in omission failure rate. A novel contribution analysis scheme named bar plot is developed for MKEICA to diagnose faults. The proposed MKEICA method consist of three steps: 1) the three-dimensional data of SBR is unfolded into two-dimensional by a new data expanding method. 2) kernel entropy principal component analysis (KEPCA) is adopted to map the two-dimensional data into a high dimensional feature space and use independent component analysis (ICA) to extract independent components (ICs) in feature space. 3) in the stage of online monitoring,bar plot is used to identify the variables causing the fault. This method is successfully applied to an 80 L lab-scale SBR, and the experimental results demonstrate that, comparing with traditional MKICA, the proposed MKEICA method exhibits better performance in fault detection and diagnose.

关 键 词：序批式反应器 多向核熵独立成分 故障检测 故障诊断 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]