A stepwise method for identification of controlled discrete manufacturing systems

Abstract

This paper deals with the identification of discrete event manufacturing systems that are automated by a programmable logic controller (PLC). The behaviour of the closed loop system (PLC and Plant) is observed during its operation and is represented by a single long sequence of observed input/output signals vectors. The proposed method follows a black-box and passive identification approach; it allows building stepwise an interpreted Petri net (IPN) model. The identification method is composed of several polynomial time algorithms implemented in a software tool that generates and draws the IPN model.