Fault Detection and Classification for Slider Attachment Process using Convolution Neural Network

Hard Disk Drive (HDD) utilizes automation machines for the assembly processes used in the industry to achieve higher production rates and lower costs. The Head Gimbal Assembly (HGA) production process has two main parts: glue dispensing and slider attaching by an Auto Core Adhesion mounting Machine (ACAM). The slider attaching process produces a mounted head to the suspension utilizing vacuum pressure to hold and position a slider. The errors from a vacuum leak from any step trigger system alarms resulting in machine downtime and slider loss defective (SLD). This paper proposes a classification algorithm derived from 250x250 micron images of mounted heads are 4 different categories: Good, Fault I, Fault II and Fault III using Convolution Neural Networks (CNN). CNN is a performance model for predictive maintenance before failure. The method has achieved a 95 % accuracy for detection and classification

The Effect of Laser Energy and Nitrogen Flow in Solder Joints Properties of Head Gimbal Assembly

The objective of this research is to study the effect of laser energy and Nitrogen flow on the solder joints of the Head Gimbal Assembly (HGA). The soldering of the HGA components isn't the same as general semiconductors. Since the soldering figure perpendicular to each other so that, it was used the laser solder jet bonding system. The solder jet bonding system uses a solder ball consisting of Sn-2.0Ag-0.7Cu (SAC207) is used for connection of the HGA pad made from a Cu trace coated with Au. The growth of intermetallic compounds (IMCs) and shear strength will be analyzed to investigate the effects of laser energy and Nitrogen flow on solder joint reliability. In this research, laser energy levels since 2, 2.5, 3, 3.5, 4, and 4.5 mJ and keep the Nitrogen flow value at 90 mbar. As for the Nitrogen flow effect analysis, the Nitrogen flow level was used at 80, 100, 120, and 140 mbar and keep the laser energy value 3.5 mJ. The results of the study show that the increased levels of laser energy can inhibit the growth of intermetallic compounds as well as the AuSn4 phase that can present benefit to solder joints with results showing within the shear strength to increase significantly. The increase in Nitrogen flow levels has the same effect as the increase in laser energy levels, which can decreases the growth of intermetallic compounds and AuSn4 phase also including increased shear strength. The difference between laser energy and Nitrogen flow increasing shows the level of laser energy can clearly distinct the effect on each level. But the increase in Nitrogen flow level is statistically insignificant from each level.

Neurofuzzy c-Means Network-Based SCARA Robot for Head Gimbal Assembly (HGA) Circuit Inspection

Decision and control of SCARA robot in HGA (head gimbal assembly) inspection line is a very challenge issue in hard disk drive (HDD) manufacturing. The HGA circuit called slider FOS is a part of HDD which is used for reading and writing data inside the disk with a very small dimension, i.e., 45 × 64 µm. Accuracy plays an important role in this inspection, and classification of defects is very crucial to assign the action of the SCARA robot. The robot can move the inspected parts into the corresponding boxes, which are divided into 5 groups and those are “Good,” “Bridging,” “Missing,” “Burn,” and “No connection.” A general image processing technique, blob analysis, in conjunction with neurofuzzy c-means (NFC) clustering with branch and bound (BNB) technique to find the best structure in all possible candidates was proposed to increase the performance of the entire robotics system. The results from two clustering techniques which are K-means, Kohonen network, and neurofuzzy c-means were investigated to show the effectiveness of the proposed algorithm. Training results from the 30x microscope inspection with 300 samples show that the best accuracy for clustering is 99.67% achieved from the NFC clustering with the following features: area, moment of inertia, and perimeter, and the testing results show 92.21% accuracy for the conventional Kohonen network. The results exhibit the improvement on the clustering when the neural network was applied. This application is one of the progresses in neurorobotics in industrial applications. This system has been implemented successfully in the HDD production line at Seagate Technology (Thailand) Co. Ltd.

The Effect of Track-Seeking Motion on Off-Track Vibrations of the Head Gimbal Assembly in HDDs

The effect of track-seeking on off-track residual vibrations of the head-gimbal assembly (HGA) is investigated for air and helium environments using the so-called “fluid dynamic mesh” method and the “fluid-structure interaction” method. Three different angular acceleration profiles (square wave, triangular wave and sinusoidal wave) are investigated as a function of seek time (10 ms and 5 ms). Results show that smoothening of sharp transitions of the seek profile improves the performance of off-track residual vibrations during track-following and shortens the track-following time of the head positioning servo system. In addition, the effect of lateral flow (windage) on off-track residual vibrations during track-following must be considered for a square wave angular acceleration profile. Simulation results show that helium improves the track-following accuracy compared to air due to the lower windage forces acting on the HGA. We observe that the sinusoidal wave angular acceleration performs best among the three angular acceleration profiles investigated. Furthermore, seek time is found to have only a small effect on off-track residual vibrations during track-following.