2010 | OriginalPaper | Buchkapitel
Data Mining for CNC Machine Adjustment Decision in Hard Disk Drive Arm Manufacturing: Empirical Study
verfasst von : Pongsak Holimchayachotikul, Wimalin Laosiritaworn
Erschienen in: Proceedings of the 6th CIRP-Sponsored International Conference on Digital Enterprise Technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The numbers of hard disk drive heads manufactured in Thailand have increased rapidly in the past few years, and one of the most important components of the hard disk drive head is the hard disk drive arm. This component has been produced in large amounts and has been a major income source for a case study company. The manufacturing process of the hard disk drive arm, especially the machining process, is highly complicated and also a main factor of defining the usability of the final product. However, during dimension inspections, many defected parts were detected, resulting in an overall decrease in productivity, sales and profit. Normally, parts are randomly chosen from each CNC machine to be inspected. If there is a defective product, that machine would be shut down and the tool settings will be reset. If the machine that has been producing defective products is inspected late into the inspection shifts, it would result in a considerable amount of defective parts produced before any corrective actions can be made. Therefore, this study presents an application of the integration between Multiple Attribute Decision Making (MADM) and Data Mining (DM) to define the inspection order for tooling adjustment of which the machines with higher risk of producing defective parts can be inspected and corrected before those with lower risk. The methodology is as follows. First, raw measurement data from each machine was collected and noise elimination was performed using the anomaly clustering method. Secondly, K-means clustering, after a machine performance hypothesis test to confirm that the performance of each machine is not equal, was opted for dividing the raw data into three clusters, consisting of good, normal, and bad machines. Finally, a daily CNC machine priority assessment model (CNC-MPAM) is developed based on the Simple Additive Weight (SAW) technique, resulting in a machine performance score for optimal ordering of machine tooling adjustment. Experimental results suggested that this proposed method is capable of machine adjustment ordering so that defective prone machines can be serviced sooner, reducing defective parts produced and improving overall productivity.