Performance monitoring of model-predictive controllers via model residual assessment

Zhijie SUN, S. Joe QIN*, Ashish SINGHAL, Larry MEGAN

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

66 Citations (Scopus)


Model quality is a main factor that affects the control performance of model-based controllers. In this paper, a new closed-loop model assessment approach is proposed to assess model deficiency from routine closed-loop data. The proposed model quality index is a minimum variance benchmark for the model residuals obtainable from closed-loop data. From the feedback invariant principle the disturbance innovations are shown to be unaffected by the feedback controller. Then it is shown that the disturbance innovations can be estimated from closed loop data by an orthogonal projection of the current output onto the space spanned by past outputs, inputs or setpoints. With the estimated disturbance innovations as the benchmark, a model quality index is developed by using the ratio of a quadratic form of model residuals and that of the estimated disturbance innovations. The effectiveness of the proposed methods is demonstrated by simulations.© 2013 Elsevier Ltd. All rights reserved.
Original languageEnglish
Pages (from-to)473-482
Number of pages10
JournalJournal of Process Control
Issue number4
Early online date24 Feb 2013
Publication statusPublished - Apr 2013
Externally publishedYes

Bibliographical note

Financial support from Praxair as a member of the Texas-Wisconsin-California Control Consortium (TWCCC) and from Chevron through the Center for Interactive Smart Oilfield Technologies (CiSoft) of University of Southern California is gratefully acknowledged.


  • Control performance monitoring
  • Feedback invariant principle
  • Model predictive control
  • Model quality assessment
  • Time series modeling


Dive into the research topics of 'Performance monitoring of model-predictive controllers via model residual assessment'. Together they form a unique fingerprint.

Cite this