Enhancing Quality Control: A Study on AI And Human Performance in Flip Chip Defect Detection
Issued Date
2024-01-01
Resource Type
eISSN
21693536
Scopus ID
2-s2.0-85213223385
Journal Title
IEEE Access
Rights Holder(s)
SCOPUS
Bibliographic Citation
IEEE Access (2024)
Suggested Citation
Cheamsiri W., Jitpattanakul A., Muneesawang P., Wongpatikaseree K., Hnoohom N. Enhancing Quality Control: A Study on AI And Human Performance in Flip Chip Defect Detection. IEEE Access (2024). doi:10.1109/ACCESS.2024.3521459 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/102604
Title
Enhancing Quality Control: A Study on AI And Human Performance in Flip Chip Defect Detection
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
This research presents an intelligent defect inspection model that uses object detection to identify defects in Flip Chip cross-section images, aiding failure analysis (FA) engineers working with Chip-on-Wafer (CoW) products. The model aims to enhance accuracy, save time and costs, reduce human error, and ensure reliability. The dataset was sourced from an electronics service manufacturer in Thailand and categorized into four classes: good bump, head-in-pillow (HIP) defect, non-wetting defect, and solder void defect. High-resolution images were captured using an Olympus BX53M microscope at 1000× magnification, focusing on a 50-micrometer copper pillar (CP) bump diameter. To address dataset imbalances, we established seven experimental conditions using various augmentation techniques and generative artificial intelligence (AI) to synthesize underrepresented image classes. We evaluated YOLOv5, YOLOv6, YOLOv7, and YOLOv8 across 26 trained models. The training durations for YOLOv5 and YOLOv8 were 0.86 hours, demonstrating a significant time advantage over other versions. F1-score evaluations indicated that YOLOv5 achieved scores between 0.948 and 0.981, outperforming other versions and even inspectors with over 20 years of experience.