A Bayesian Networks Approach to Estimate Engineering Change Propagation Risk and Duration Open Access
Downloadable ContentDownload PDF
An engineering change (EC) is an alteration made to a system that has beenreleased following a system design process. EC propagation is a series of ECs occurringdue to dependencies among components of a product. ECs can consume up to 50% of theoverall engineering efforts during development of a complex system. Therefore, ECpropagation prediction received considerable attention in past decades as the productdevelopment industries started to suffer from the negative impacts of change propagation.This research evaluates the current approaches to EC propagation prediction and presentsa dynamic Bayesian networks (DBNs) approach to estimate change propagation risk(CPR) as well as a novel approach to estimate EC durations. Literature research showsthat although some studies have used design structure matrices (DSMs) to estimate CPRand the total redesign duration (TRD) due to change propagation, an approach that allowsiteration while accounting for the conjunction of all impacts has not been explored. Thisresearch aims to fill the gaps for calculating CPR using DBN and evaluating changepropagation paths (CPPs) from an AND-Split task outcome logic, which accounts for theconjunction of all component relationships. This research compares the proposed methodresults with the existing CPR and engineering change duration estimation methods usinga real-world dataset from a U.S. Navy shipbuilding program. The results indicate that theCPR can be calculated using the proposed method without the shortcomings of theexisting method and the accuracy for estimating engineering change durations isincreased.