Defect analytics in a high-end server manufacturing environment

Server manufacturing is characterized by extensive test processes to ensure high quality and reliability of the servers. Server components are obtained from different suppliers who may have different specifications. Although outsourcing of components provides many potential benefits to the company, it can also cause quality issues. If quality issues are not addressed effectively at the initial stages, defects can transit through the supply chain. Thus, quality control is one of the major challenges for the high-end server manufacturing industries. Defective parts are either disposed, repaired, or returned to the supplier depending on the type of defects. Product quality is ensured through multiple test processes at the manufacturing and design stages are substantially expensive. The defect-related quality test results are stored in different databases in both structured and unstructured data format. In this study, defect analytics models are used for defect assessment of more than 5,000 different defect instances collected from different databases sources of a high-end server manufacturing environment. Analytics models including cluster analysis, neural networks, and text mining to characterize and predict the defect root causes and solutions. The proposed defect analytics framework replaced the current manual defect analysis method which is based on trial and error.