Indirect Fault Diagnosis of Fixed Marine Observing Buoy Based on Bayesian Network

Abstract

Abstract Fault diagnosis of a fixed marine observing buoy (FMOB) is important for ensuring the reliability of an ocean observing system. Aiming at the difficulty that most FMOB instruments lack direct operational status information in fault diagnosis, an indirect fault diagnosis method based on a Bayesian network (BN) for FMOBs is presented, through which the ocean observing series collected by the FMOB are effectively utilized and analyzed for fault diagnosis of FMOB equipment. The ocean observing series not only reflects the characteristics of the marine environment but also includes the operating status of FMOBs. Based on the analysis of an ocean observing series, the different fault symptoms of FMOBs are confirmed. According to the BN theory, the indirect fault diagnosis model is developed. The model structure is defined based on a comprehensive analysis of the causal relationships among faults and their symptoms. The model parameters are estimated according to experts' knowledge and statistical analysis of historical data. Three typical fault cases of FMOBs are selected for verifying the method. The results show that the BN-based indirect fault diagnosis method is reliable and effective for fault diagnosis of an FMOB even when the fault diagnosis evidence is incomplete and uncertain. Furthermore, this approach can work in a real-time way and help technicians to take effective measures to avoid big losses.