Extended PLS approach for enhanced condition monitoring of industrial processes

An wended partial-least squares (EPLS) algorithm is introduced to correct a deficiency of conventional partial least squares (PLS) when used as a tool to detect abnormal operating conditions in industrial processes. In the ab sence of feedback control, an abnormal operating condition that affects onl y, process response variables will not be propagated back to the process pr edictor (Or input) variables. Thus monitoring tools developed under the con ventional PLS framework and based only, on the predictor matrix will fail t o detect the abnormal condition. The EPLS algorithm described removes this deficiency by defining new scores that are based oil both predictor and res ponse variables. The EPLS approach provides two monitoring charts to detect abnormal process behavior, as well as contribution charts to diagnose this behavior. To demonstrate the utility, of the new approach, the extended al gorithm and monitoring tools are applied to a realistic simulation of a flu id catalytic cracking unit and to a real industrial process that involves a complex chemical reaction.