2017年 第3卷 第2期
《工程（英文）》 >> 2017年 第3卷 第2期 doi: 10.1016/J.ENG.2017.02.004
过程操作性能的在线评估与诊断
Department of Chemical and Materials Engineering, University of Alberta, Edmonton, Alberta T6G 1H9, Canada
下一篇 上一篇
摘要
随着时间的推移，过程性能会因为过程变动和不确定性从其初始状态偏移，这使系统性地发展基于日常过程操作数据的在线最优性评估方法变得必要。一些过程，由于其关键过程变量操作点的变动，会产生多个不同操作模态，以满足不同的产品要求。另外，每一个操作模态的操作区域会由于系统的不确定性产生变动。本文中，我们建立了一个用于多模态、多操作区域的典型过程的最优性评估，该方法也能够处理模态切换时的过渡状态的最优性评估。在该框架中，核密度方法被改进，并被用于操作模态检测。在在线阶段，结合过程系统的先验知识，基于模型的聚类判别分析方法(model-based clustering discriminant analysis，MclustDA) 被用于模态检测。此外，稳态模态的多模态特性由混合概率主成分回归方法(mixture probabilistic principal component regression，MPPCR) 处理；动态主成分回归方法(dynamic principal component regression，DPCR) 被用来探究不同模态间的过渡状态的性能评估。除此以外，一种基于序列浮动前向搜索(sequential forward floating search,SFFS) 的概率因果关系检测方法被引入，用以检测系统的不良或非最佳性能。最后，本文提出的算法被应用于田纳西- 伊斯曼(Tennessee Eastman) 过程之中，用以评估本文算法的性能。
图片
图1
图2
图3
图4
图5
图6
图7
参考文献
[ 1 ] Ye L, Liu Y, Fei Z, Liang J. Online probabilistic assessment of operating performance based on safety and optimality indices for multimode industrial processes. Ind Eng Chem Res 2009;48(24):10912–23 链接1
[ 2 ] Liu Y, Chang Y, Wang F. Online process operating performance assessment and nonoptimal cause identification for industrial processes. J Process Contr 2014;24(10):1548–55 链接1
[ 3 ] Liu Y, Wang F, Chang Y, Ma R. Comprehensive economic index prediction based operating optimality assessment and nonoptimal cause identification for multimode processes. Chem Eng Res Des 2015;97:77–90 链接1
[ 4 ] Liu Y, Wang F, Chang Y, Ma R. Operating optimality assessment and nonoptimal cause identification for non-Gaussian multimode processes with transitions. Chem Eng Sci 2015;137:106–18 链接1
[ 5 ] Kariwala V, Odiowei PE, Cao Y, Chen T. A branch and bound method for isolation of faulty variables through missing variable analysis. J Process Contr 2010;20(10):1198–206 链接1
[ 6 ] Quiñones-Grueiro M, Prieto-Moreno A, Llanes-Santiago O. Modeling and monitoring for transitions based on local kernel density estimation and process pattern construction. Ind Eng Chem Res 2016;55(3):692–702 链接1
[ 7 ] Srinivasan R, Wang C, Ho WK, Lim KW. Dynamic principal component analysis based methodology for clustering process states in agile chemical plants. Ind Eng Chem Res 2004;43(9):2123–39 链接1
[ 8 ] Chen T, Sun Y. Probabilistic contribution analysis for statistical process monitoring: A missing variable approach. Control Eng Pract 2009;17(4):469–77 链接1
[ 9 ] Chen T, Martin E, Montague G. Robust probabilistic PCA with missing data and contribution analysis for outlier detection. Comput Stat Data Anal 2009;53(10):3706–16 链接1
[10] Pudil P, Novovičová J, Kittler J. Floating search methods in feature selection. Pattern Recognit Lett 1994;15(11):1119–25 链接1
[11] Fraley C, Raftery AE. Model-based clustering, discriminant analysis, and density estimation. J Am Statist Assoc 2002;97(458):611–31 链接1
[12] Ge Z, Song Z. Mixture Bayesian regularization method of PPCA for multimode process monitoring. AIChE J 2010;56(11):2838–49 链接1
[13] Downs JJ, Vogel EF. A plant-wide industrial process control problem. Comput Chem Eng 1993;17(3):245–55 链接1
[14] Ricker NL. Decentralized control of the Tennessee Eastman Challenge Process. J Process Contr 1996;6(4):205–21 链接1
京公网安备 11010502051620号
