A big data-driven root cause analysis system: Application of Machine Learning in quality problem solving

Abstract

Root cause analysis for quality problem solving is critical to improve product quality performance and reduce the quality risk for manufacturers. Subjective conventional methods have been applied frequently in past decades. However, due to increasingly complex product and supply chain structures, diverse working conditions, and massive amounts of components, accuracy and efficiency of root cause analysis are progressively challenged in practice. Therefore, data-driven root cause analysis methods have attracted attention lately. In this paper, taking advantage of the availability of big operations data and the rapid development of data science, we design a big data-driven root cause analysis system utilizing Machine Learning techniques to improve the performance of root cause analysis. More specifically, we first propose a conceptual framework of the big data-driven root cause analysis system including three modules of Problem Identification, Root Cause Identification, and Permanent Corrective Action. Furthermore, in the Problem Identification Module, we construct a unified feature-based approach to describe multiple and different types of quality problems by applying a data mining method. In the Root Cause Identification Module, we use supervised Machine Learning (classification) methods to automatically predict the root causes of multiple quality problems. Finally, we illustrate the accuracy and efficiency of the proposed system and algorithms based on actual quality data from a case company. This study contributes to the literature from the following aspects: (i) the integrated system and algorithms can be used directly to develop a computer application to manage and solve quality problems with high concurrences and complexities in any manufacturing process; (ii) a general procedure and method are provided to formulate and describe a large quantity and different types of quality problems; (iii) compared with traditional methods, it is demonstrated using real case data that manufacturing companies can save significant time and cost with our proposed data-driven root cause analysis system; (iv) this study not only aims at improving the quality problem solving practices for a complex manufacturing process but also bridges a gap between the theoretical development of Machining Learning methods and their application in the operations management domain.