Challenges for Predictive Quality in Multi-stage Manufacturing: Insights from Literature Review

This paper investigates data quality challenges in applying predictive quality solutions for multi stage discrete manufacturing. Through an analysis of existing research via systematic literature search, we highlight key obstacles that affect the implementation of machine learning approaches for quality control, such as the quantity and quality of available datasets for model training and testing and available quality labels for supervised training. Our findings underscore the necessity of addressing these challenges to enhance the accuracy and scalability of predictive quality models.