THE USE OF CONNECTIONIST SYSTEMS TO RECONCILE INCONSISTENT PROCESS DATA

Since measurements of variables in chemical and metallurgical plants g enerally violate the conservation and other constraints of these syste ms owing to random measurement errors, these data have to be reconcile d with the constraints prior to further use. In multicomponent systems the reconciliation of process data normally results in a non-linear c onstrained optimization problem, which can constitute a formidable com putational burden when large systems have to be solved by conventional techniques. Connectionist systems, such as artificial neural networks , can be implemented to considerable advantage for the solution of opt imization problems such as these and in this paper their use is explor ed. Three variants of crossbar feedback connectionist systems were inv estigated, two are based on gradient descent techniques and one on a d irect search method. The results of simulations, as well as a comparis on with traditional computational procedures, indicate that systems su ch as these based on gradient descent techniques can be used to solve large systems efficiently.