A PETRI-NET APPROACH TO EARLY FAILURE-DETECTION AND ISOLATION FOR PREVENTIVE MAINTENANCE

To improve preventive maintenance, this study uses a hybrid Petri net modelling method coupled with parameter trend and fault tree analysis to perform early failure detection and isolation. A Petri net arrangem ent is proposed that facilitates alarm, early failure detection, fault isolation, event count, system state description and automatic shutdo wn or regulation. These functions are very useful for health monitorin g and preventive maintenance of a system. A fault diagnosis system for district heating and cooling facilities is employed as an example to demonstrate the proposed method. (C) 1998 John Wiley Br Sons, Ltd.