Decision Support Systems in Product Development: A Bayesian Network Approach for Injection-molded Products

Every day decisions are made that affect the success or failure of a product. This work provides insight for any manufacturer looking to examine how constraints, objectives and decisions in the product development process affect the outcome of nonconformities. Specifically, an expert system in the form of a Bayesian belief network was designed and built to determine the probability of an injection-molded defect, called shear splay. This work provides a thorough justification about the variables in the network, as well as operational guidance for the construction of a Bayesian network to be used in prevention. Included is an explanation about the history, theory and applications of Bayesian networks. A description of the shortcomings for other defect prevention techniques used in manufacturing is provided. This work also summarizes the benefits and limitations of this expert system to be used as a decision support system in product development.