Fault diagnosis method based on Petri nets considering service feature of information source devices

The Petri net is a powerful tool for fault diagnosis, yet at present the determination of the certainty factor and weight of Petri net initial place is on basis of an insufficient reality. This paper mainly presents a calculation method of the certainty factor and weight of Petri net initial place by use of reliability. The reliability of information source devices is proposed by using two-parameter Weibull distribution, minimum vertical and horizontal residual sums of squares are used to estimate parameters of the reliability, then these reliabilities are used to measure the initial information certainty, and the relative values of reliabilities are used to determine the weights of places during reasoning. As an example, we use this proposed method to diagnose fault of devices of a power supply system. And the result of the example shows that the degree of diagnostic results confidence are related to service time of the source device, which makes the result more consistent with actual operating conditions.