Predicting defects in disk drive manufacturing. A case study in high-dimensional classification

Abstract

We consider the application of several computer-intensive classification techniques to disk drive manufacturing quality control. This application is characterized by very high dimensions, with hundreds of features, and tens of thousands of cases. Two principal issues are addressed; (a) can a very expensive testing process be eliminated while still maintaining high quality throughput in disk drive manufacturing, and (b) can the manufacturing process be made more efficient by identifying bad disk drives prior to the expensive testing. Preliminary results indicate that although the expensive testing cannot be completely eliminated, a fraction of the disk drives can be determined to be faulty prior to further testing. This detection may improve the throughput of the manufacturing line.