CONTROLLERS WITH DIAGNOSTIC CAPABILITIES - A NEURAL-NETWORK IMPLEMENTATION

Designing controllers with diagnostic capabilities is important as in a feedback control system, detection and isolation of failures is gene rally affected by the particular control law used. Therefore, a common approach to control and failure diagnosis problems has significant me rit. Controllers capable of performing failure diagnosis have addition al diagnostic outputs to detect and isolate sensor and actuator faults . A linear such controller is usually called a four-parameter controll er. Neural networks have proved to be a very powerful tool in the cont rol systems area, where they have been used in the modelling and contr ol of dynamical systems. In this paper*, a neural network model of a controller with diagnostic capabilities (CDC) is presented for the fir st time. This nonlinear neural controller is trained to operate as a t raditional controller, while at the same time it provides reproduction of the failure occurring either at the actuator or the sensor. The ca ses of actuator and sensor failure are studied independently. The vali dity of the results is verified by extensive simulations.