Digital Twin Driven Fault Diagnosis Method for Subsea Control System

Abstract

Digital twin driven fault diagnosis shows good performance in fault diagnosis of subsea control systems. However, the relation between digital twin and fault diagnosis is not clear. This cannot bring substantial improvement to fault diagnosis. A digital twin driven fault diagnosis method for subsea control system is proposed. Simulink is used for building a digital twin model and a fault diagnosis model is established based on Bayesian networks. The diagnosis results are input into the digital twin model to verify them. The results of verification are feedback to fault diagnosis model. Through this method, a framework that improves fault diagnosis by digital twin is proposed and provide a reference for related research. The performance of this method is verified by a redundant control system. The results show that in this framework, the digital twin model can improve diagnostic performance effectively.