Life-cycle Risk Modeling: Alternate Methods Using Bayesian Belief Networks

Abstract

In recent years natural and man-made disasters have highlighted the need for robust supply chain risk management (SCRM) in manufacturing firms from a life-cycle perspective (pre-manufacturing, manufacturing, use, post-use stages). Bayesian Belief Networks (BBN) provide a means to probabilistically represent risk interdependencies and to proactively identify and manage any existing vulnerabilities. In this work, the BBN method is implemented for a product in the aerospace industry. Risk network maps are developed to identify interdependencies and describe the potential risk propagation behavior during each life-cycle phase and from one phase to another. Due to limited number of respondents and lack of certainty with respect to the post-use phase, enhanced methods of risk likelihood assessment are necessary specifically for the post-use phase assessment. In this paper two alternate techniques are compared for risk modeling using BBN in such situations: Boolean nodes and numeric simulation nodes. Results show that numeric nodes provide a more thorough explanation of the interconnections of the risk items modeled. Further enhancement using an approach that combines both BBN and System Dynamics (SD) for SCRM is discussed and possible variations for linking variables between SD and BBN are also presented.