As military aircraft continue to remain in service and age, cannibalization of parts is increasing. Proactive identification of parts that are at high risk for cannibalization will inform engineering processes such as reverse engineering, thus allowing potentially reducing lead time to develop new parts. The research objective was to develop a causal structure that can be used for prediction of when cannibalization actions may occur. Bayesian networks allow encoding of causality between various descriptive features given a data set. The method utilized a tabu search algorithm, identified the underlying causal structure and the associated node probabilities. The method is then applied to an aircraft case study. The analysis resulted in a predictive algorithm with a true positive rate of 73 – 96 percent depending on the target feature. The results indicate high precision and recall for all target features. Additional research is needed in order to validate the causal structure with military personal, incorporate domain expertise, and reduce the high false alarm rate.
Scholarly Commons Citation
Banghart, M. (2017). Identification of Reverse Engineering Candidates utilizing Machine Learning and Aircraft Cannibalization Data. International Journal of Aviation, Aeronautics, and Aerospace, 4(4). https://doi.org/10.15394/ijaaa.2017.1183
Industrial Engineering Commons, Management Sciences and Quantitative Methods Commons, Operational Research Commons, Operations and Supply Chain Management Commons, Other Operations Research, Systems Engineering and Industrial Engineering Commons, Risk Analysis Commons, Systems Engineering Commons