基于统计分析的多变量预测控制性能检测与诊断

• SYSTEM ENGINEERING • 上一篇下一篇

基于统计分析的多变量预测控制性能检测与诊断

张强; 李少远

Institute of Automation, Shanghai Jiao Tong University, Shanghai 200240, China

收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-04-28 发布日期:2006-04-28
通讯作者: 李少远

Performance Monitoring and Diagnosis of Multivariable Model
Predictive Control Using Statistical Analysis

ZHANG Qiang; LI Shaoyuan

Institute of Automation, Shanghai Jiao Tong University, Shanghai 200240, China

Received:1900-01-01 Revised:1900-01-01 Online:2006-04-28 Published:2006-04-28
Contact: LI Shaoyuan

摘要/Abstract

摘要： A statistic-based benchmark was proposed for performance assessment and monitoring of model predictive control; the benchmark was straightforward and achievable by recording a set of output data only when the control performance was good according to the user’s selection. Principal component model was built and an auto-regressive moving average filter was identified to monitor the performance; an improved T2 statistic was selected as the performance monitor index. When performance changes were detected, diagnosis was done by model validation using recursive analysis and generalized likelihood ratio (GLR) method. This distinguished the fact that the per-formance change was due to plant model mismatch or due to disturbance term. Simulation was done about a heavy oil fractionator system and good results were obtained. The diagnosis result was helpful for the operator to improve the system performance.

关键词: predictive control;performance monitoring;diagnosis;principal component analysis

Abstract: A statistic-based benchmark was proposed for performance assessment and monitoring of model predictive control; the benchmark was straightforward and achievable by recording a set of output data only when the control performance was good according to the user’s selection. Principal component model was built and an auto-regressive moving average filter was identified to monitor the performance; an improved T2 statistic was selected as the performance monitor index. When performance changes were detected, diagnosis was done by model validation using recursive analysis and generalized likelihood ratio (GLR) method. This distinguished the fact that the per-formance change was due to plant model mismatch or due to disturbance term. Simulation was done about a heavy oil fractionator system and good results were obtained. The diagnosis result was helpful for the operator to improve the system performance.

Key words: predictive control, performance monitoring, diagnosis, principal component analysis

张强, 李少远. 基于统计分析的多变量预测控制性能检测与诊断
[J]. , DOI: .

ZHANG Qiang, LI Shaoyuan. Performance Monitoring and Diagnosis of Multivariable Model
Predictive Control Using Statistical Analysis
[J]. , DOI: .

参考文献

1    Ender, D., “Process control performance: Not as good as you think”, Control Eng., 9, 180—190(1993).
2    Astrom, K., “Computer control of a paper machine—An application of linear stochastic control theory”, IBM J., 7, 389—396(1967).
3    DeVries, W.R., Wu, S.M., “Evaluation of process con-trol effectiveness and diagnosis of variation in paper ba-sis weight via multivariate time series analysis”, IEEE Trans. Auto. Control, 23(4), 702—708(1978).
4    Huang, B., Shah, S.L., Performance Assessment of Con-trol Loops: Theory and Applications, Springer (1999).
5    Harris, T.J., Seppala, C.T., Desborough, L.D., “A review of performance monitoring and assessment techniques for univariate and multivariate control systems”, J. Proc. Control, 9, 1—17(1999).
6    Harris, T.J., Seppala, C.T., “Recent developments in controller performance monitoring and assessment tech-niques” In: Proceedings of the Sixeh International Chemical Process Control Conference (CPC-Ⅵ), Tucson, Arizona, 220—250(2001).
7    Qin, S.J., “Control performance monitoring: A review and assessment”, Comp. Chem. Eng., 23, 173—186(1998).
8    Harris, T.J., Boudreau, F., MacGregor, J.F., “Perform-ance assessment of multivariable feedback controllers”, Automatica, 32, 1505—1518(1996).
9    Huang, B., Shah, S.L., Kwok, K.E., “Good, bad or opti-mal? Performance assessment of multivariable proc-esses”, Automatica, 6, 1175—1183(1997).
10    Ko, B.S., Edgar, T.F., “Performance assessment of cas-cade control loops”, AIChE J, 46, 281—291(2000).
11    Horch, A., Isaksson, A.J., “A modified index for control per-formance assessment”, J. Proc. Control, 9, 475—483(1999).
12    Thornhill, N.F., Oettinger, M., “Refinery-wide control loop performance assessment”, J. Proc. Control, 9,     109—124(1999).
13    Julien, R.H., Foley, M.W., Cluett, W.R. “Performance assesement using a model predictive control benchmark”, J. Proc. Control, 14, 441—456(2004).
14    Schafer, J., Cinar, A., “Multivariable MPC system per-formance assessment, monitoring, and diagnosis”，J. Proc. Control, 14, 113—129(2004).
15    Patwardhan, R.S., Shah, S.L., “Assessing the perform-ance of model predictive controllers”, Can. J. Chem. Eng., 80, 954—966(2002).
16    Garcia, C.E., Prett, D.M., Morari, M., “Model predictive control: Theory and practice –A survey”, Automatica, 25, 335—348(1989).
17    Ku, W., Storer, R.H., Georgakis, C., “Disturbance rejec-tion and isolation by dynamic principal component analy-sis”, Chemom. Intell. Lab. Sys., 30, 179—196(1995) .
18    Kruger, U., Zhou, Y., Irwin, G.W., “Improved principal component monitoring of large-scale processes”, J. Proc. Control, 879—888(2004).
19    Ljung, L., System Identification, 2nd ed., Englewood Cliffs, NJ:Prentice-Hall (1998).
20    Jackson, J.E., A User’s Guide to Principal Components, Wiley, New York (1991).
21    Patwardhan, R.S., Huang, B., “Multivariate controller performance analysis: Methods, applications and chal-lenges”, In: Proceedings of the Sixth International Chemical Process Control Conference (CPC-Ⅵ), Tucson, Arizona, 187—219(2001).
22    Basseville, M., “On-board component fault detection and isolation using the statistical local approach”, Auto-matica, 34(11), 1391—1415(1998).
23    Huang, B., “Multivariable model validation in the pres-ence of time-variant disturbance dynamics”, Chem. Eng. Sci., 55, 4583—4595(2000).
24    Prett, D., Morari, M., “Shell control problem”, Shell Process Control Workshop, Butterworth Publishers, Stoneham, MA, 355—360(1987).

编辑推荐 0

Metrics

阅读次数

全文

1994

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	1994

来源	本网站	其他网站

次数	84	1910
比例	4%	96%

摘要

2261

最新录用	在线预览	正式出版

0	0	2261

来源	本网站	其他网站

次数	64	2197
比例	3%	97%