Discovery of potential risks for the gas transmission station using monitoring data and the OOBN method

Gas transmission stations (GTS) are significant infrastructure for cities and critical components of natural gas delivery, with severe consequences in the case of an accident. As a result, it necessitates the importance of potential risk discovery and accident precursor identification. However, existing models for risk analysis of GTS systems are too complex and only periodically update the risk of GTS, making it difficult to discover its potential risk in time. Some data used as input to the models are not from the system under consideration, leading to results inconsistent with the actual working conditions. This study proposes a structure mapping method based on failure modes and effects analysis (FMEA) to form the GTS's object-oriented Bayesian network (OOBN) framework, making the model more user-friendly. An accident precursor identification approach is proposed based on the piecewise aggregate approximation-cumulative sum (PAA-CUSUM) algorithm, which can better discover the potential risks in real-time. The proposed method identifies process anomalies through monitoring data and analyzes the events and propagation patterns with the highest potential risk. A case study of a GTS in China is conducted. The results demonstrate that the proposed method is beneficial for assisting station operators in identifying possible hazards and providing a foundation for daily risk mitigation.