基于数据及知识的工业过程监视及故障诊断综述.pdf

25 6 2010 6 Vol. 25 No. 6 Control and Decision Jun. 2010 : 1001-0920 (2010) 06-0801-07 a , , , (1. a. b. , 110819 2. 90089 3. 110032) : , , . . : : TP273 : A Progress of data-driven and knowledge-driven process monitoring and fault diagnosis for industry process a LIU Qiang , CHAI Tian-you , QIN S Joe , ZHAO Li-jie (1a. Key Laboratory of Process Industry Automation of Ministry of Education1b. Research Center of Automation, Northeastern University Shenyang 110819China 2. The Mork Family Department of Chemical Engineering and Materials Science University of Southern California Los Angeles 90089 USA 3. Information Engineering School, Shenyang Institute of Chemical TechnologyShenyang 110032China Correspondent LIU Qiang E-mail qiang liu1980@163.com) Abstract: Based on the analysis of complex data characteristics due to the process characteristics or the data collection and storage problem, the developments of theory the researches on complex industry process multivariate statistical monitoring are reviewed. The advantages, development, applicable domain of the data-based and knowledge-based diagnosis methods are discussed. And the possibility of these two types of methods’ combination are studied. Finally, some problems and their research tendencies in this field are presented. Key words: Multivariate statistical process monitoring Data-based fault diagnosis Knowledge-based fault diagnosis; Industry process [5,6] 1 . , ,