Fuzzy Bayesian Network Applied to Modeling Vehicles Cooling Systems Failure Risk

In today’s competitive industrial landscape, the logistics sector faces escalating challenges in meeting customer demands while maintaining operational efficiency. One critical aspect is the risk of failure in vehicles cooling systems, which can disrupt production and distribution processes. To address this, risk assessment methodologies are crucial. In this study, we propose a novel approach utilizing Fuzzy Bayesian Networks (FBN) to assess the risk of vehicle’s cooling system failures. Leveraging Fuzzy Logic and experts’ knowledge, the FBN model integrates uncertain human knowledge to generate rules and calculate Conditional Probabilities (CPs). This method enables a comprehensive evaluation of the impact of various parameters on cooling system reliability. By amalgamating the causal relationship graph with CPs derived from the Fuzzy Logic system, our approach provides insights into the likelihood of system failures across different scenarios. Through the application of advanced computational tools such as FisPro and OpenMarkov, we validate our model and analyze the sensitivity of key factors affecting system performance. Our findings offer valuable insights for proactive maintenance strategies aimed at minimizing downtime and optimizing system reliability in industrial settings.