Detection of micro contamination in hard disk drives using maximum likelihood estimation and angle detection

Abstract

Micro contamination is one of the critical defects that occur on the head gimbal assembly (HGA). The HGA is a key component of the read/write assembly of a hard disk drive. This paper presents an image-based automatic inspection method for micro-contamination detection. Maximum likelihood estimation combined with angle measurements are proposed for identifying defects. The performance of the proposed maximum likelihood estimation and angle measurement method is compared to previous angle measurement and intensity thresholding methods. The experimental results show that the fusion of maximum likelihood estimation and angle measurements outperforms the angle measurement and intensity thresholding method with an accuracy of 87.9 % compared the accuracy of 80.1% reported in previous work.