Reliability Analysis of PLC Systems by Bayesian Network

Reliability analysis is important in the life cycle of safety critical Programmable Logic Controller (PLC) system. The complexity of PLC system reliability analysis arises in handling the complex relations between hardware components and embedded software. Different embedded software may lead to different arrangements of hardware execution and different system reliability quantities. In this paper, we propose a novel probabilistic model, named hybrid relation model (HRM), for the reliability analysis of PLC systems. It is constructed based on the distribution of the hardware components and the execution logic of the embedded software. We map the hardware components to the HRM nodes and embed the failure probabilities of them into the well defined conditional probability distribution tables of the HRM nodes. Then, HRM model handles the failure probability of each hardware component as well as the complex relations caused by the execution logic of the embedded software, with the computational mechanism of Bayesian Network. Experiment results demonstrate the accuracy of our model.