A review of performance monitoring and assessment techniques for univariate and multivariate control systems

摘要

A comprehensive approach for assessing the effectiveness of control systems requires: (i) determination of the capability of the control system, (ii) development of suitable statistics for monitoring the performance of the existing system, (iii) development of methods for diagnosing the underlying causes for changes in the performance of the control system, and (iv) incorporation of these methods in an industrial setting. This framework for analyzing the performance of control loops will be reviewed. These concepts were initially developed using a performance benchmark of minimum variance control for single-input single-output systems (SISO). Extensions to multiple-input single-output (MISO) and multiple-input multiple-output (MIMO) processes have also been developed by a number of authors. Regulation of stochastic and deterministic disturbances, as well as set-point tracking are readily accommodated with these methods. A number of alternate approaches based on fault-detection have also been proposed and several of these methods will also be reviewed. Although these performance benchmarks and monitoring methods have proven to be extremely useful in large scale industrial applications, there remain a number of outstanding theoretical and practical issues.