A Bayesian Network Based Approach to Defect Prediction in New Product Development

Abstract

The development of new product with low cost and reliable quality is one of important means to improve customer satisfaction and increase manufactures’ profits. It is necessary to identify the key factors affecting product defects and control them early in the new product development (NPD) process with defect prediction methods, because defect prediction can effectively avoid or lower testing and unnecessary rework costs. The author proposes a new product defect prediction approach on the basis of Bayesian Network theory for decision-making in the NPD process. The proposed approach makes use of Bayesian Network to simulate defects’ formation process, and it has a strong learning ability without requiring much data at the beginning of defect prediction. Product developers can easily predict the probability of defect occurrence of new products with this practical approach. The proposed product defect prediction approach can also help to focus on key factors influencing defects most. An example of turbine valve development is used to illustrate the proposed defect prediction approach. Also, recommendations for future research have been suggested.