Using fault detection and classification techniques for machine breakdown reduction of the HGA process caused by the slider loss defect

Fault Detection and Classification (FDC) based on Machine Learning (ML) approach was used to detect classify mount head fault in the slider attachment process which causes machine alarm 71 occur leads 2% of downtime. This paper has focused use classified pixel surface with difference conditions including Healthy, I, II, III diagnose before a vacuum leak. The Artificial Neural Network (ANN) algorithm proposed classification model be evaluated using real processes. Three features pixel, i.e., inner, outer, overall areas were investigated as training data set. experiment result indicates that ANN three performed an accuracy 94.3%. According result, it found reliability production processes FDC technique increased reduction downtime by 1.886%.