Risk Assessment using Bayesian Belief Networks and Analytic Hierarchy Process applicable to Jet Engine High Pressure Turbine Assembly

In the jet engines manufacturing/overhauling process, risk analysis is essential to prevent engine failure. The selection and use of an adequate analysis method to ensure software, hardware and operation reliability is very important. This paper proposes a framework for identifying undesirable events related to software, hardware and operation failure, which might occur during HPT (High Pressure Turbine) assembly process, based on Analytic Hierarchy Process (AHP) and Bayesian Belief Network (BBN). Experts estimate the risks and the associated risk factors, which are loaded into Bayesian Belief Networks to assess the probability of occurrence of undesirable events. AHP is utilized to rank the relative importance (impact) of risks. The combination of probabilities and the impacts identifies the most significant risks. The novelty of the paper is the combination of Bayesian Belief Networks with AHP to select the most significant risk. The model has practical implications and allows decision makers to identify critical failure risks, in order to allocate resources to improve the quality and safety of the jet engine manufacturing and overhaul system.