FAULT-DETECTION BASED ON FUNCTIONAL-RELAT IONSHIP AMONG PROCESS VARIABLES BY AUTOASSOCIATIVE NEURAL NETWORKS

Some process variables measured in a plant are strictly constrained by the material and heat balance equations, rate equations and correlati ons. In this study, we propose a method to judge whether the state of plant operation is normal or not, by examining whether a set of proces s variables maintains the functional relationship specified at normal operation. The functional relationship at normal operation is identifi ed by an autoassociative neural network (AANN) which approximates the identity mapping for a set of measured values of process variables. An effective method to search for an adequate configuration of the AANN is also presented. Abnormal operation or fault is detected by the magn itude of discrepancy between the input vector and the output vector of the trained AANN. This fault detection method is applied to a continu ous flow polymerization process and compared with the conventional 3 s igma fault detection method for a single process variable.