Improved Industrial Risk Analysis via a Human Factor-Driven Bayesian Network Approach

This paper develops the traditional Failure Modes, Effects and Criticality Analysis (FMECA) for quantitative risk assessment from a Bayesian Network (BN)-based perspective. The main purpose consists in endowing FMECA with a framework for analysing causal relationships for risk evaluation and deriving probabilistic relations between significant risk factors, which are represented by linguistic variables. The idea is to take advantage of BNs’ ability for inference incorporating uncertainty, and thus to enable analysts to obtain valuable information for risk assessment to support such crucial decision-making processes as planning, operation, maintenance, etc. in industry. The proposed framework includes the human factor as a key element of analysis in FMECA-based risk assessment. We propose to consider a new parameter with respect to those traditionally used for the Risk Priority Number (RPN) calculation, namely the human factor, something that existing approaches scarcely consider in the current practice. The contributions to the risk function calculation of the identified factors are determined using a Multi-criteria Decision-Making (MCDM) perspective. We present and develop a real-world application in the alimentary industry on supply chain risk (SCR) management, a fundamental business topic where risk and supply chain management processes merge.