Design and Development of Chip Quality Inspection System Based on PaddlePaddle EasyDL Platform
(Suzhou College of Information Technology, Suzhou 215200, China)
Abstract
Aiming at the problems of low chip inspection efficiency, high labor cost, and poor product consistency in current industrial production, this paper designs and develops an automated chip quality inspection system based on artificial intelligence technology. The system takes the PaddlePaddle EasyDL platform as the core, collects chip images through industrial cameras, and uses the Deep Learning algorithm to realize the intelligent recognition of defects such as chip pin missing and surface scratches. The experimental results show that the system can effectively replace the traditional manual inspection method, significantly improve the inspection accuracy and efficiency, reduce production costs, and provide strong support for enhancing the core competitiveness of the industry and promoting key technological innovations. The successful application of this system not only promotes the improvement of industrial independent innovation ability, but also provides a new technical path for the realization of high-quality development of manufacturing industry.
Keywords
PaddlePaddle; EasyDL; chip inspection; quality inspection; Deep Learning; intelligent manufacturing
References
- [1] Chen Weixun. Design of chip software and hardware quality inspection device based on YOLOv3 [J]. Transportation Technology and Management, 2023, 4 (18): 4-6
- [2] Wu Kai. A Flexible Intelligent Appearance Quality Inspection Algorithm Platform Based on Deep Learning [J]. Communication World, 2024, 31 (12): 163-165
- [3] Guo Zaoqiang, Lin Shuying, Zhang Zhenyu, et al. Research and Application Practice of AI Intelligent Quality Inspection System in Automotive Automation Coating Quality Monitoring [J]. Times Automotive, 2024 (21): 121-123
- [4] Liang Zhi, Wu Tao, Xue Yansong. Research on Human Object Detection Algorithm Based on Improved YOLOv3 [J]. Computer and Digital Engineering, 2024, 52 (12): 3503-3508+3554
- [5] Cheng Zhenzhen, Cheng Yifan, Miao Bailing, et al. Apple object detection method based on YOLOv3 in different scenarios [J]. Northern Horticulture, 2024 (22): 137-146
- [6] Tian Zhihui, Yang Qiwen, Wei Haitao. Research on Improved YOLOv3 Multi Objective Small Scale Vehicle Detection Algorithm [J]. Computer Applications and Software, 2023, 40 (12): 169-175
- [7] Li Zhenjie, Zang Chunhua, Su Baoyu, et al. Design of OpenCV Image Processing Software [J]. Internet of Things Technology, 2024, 14 (6): 47-49
- [8] Xia Qing, Wang Guixia. Research on Laser Spot Position Detection Based on Digital Image Processing Technology [J]. Laser Journal, 2024, 45 (9): 208-212
- [9] Zhou Xiaotian, Sun Shang, Zhang Haixia, et al. Real time task scheduling strategy for AI quality inspection system enabled by multi access edge computing [J]. Journal of Electronics and Information Technology, 2024, 46 (2): 662-670
- [10] Shen Zhaoyu, Lin Zhongchen, Xue Chaoyang, et al. Research on Chip Surface Defect Detection Method Based on EasyDL [J]. Science and Technology Vision, 2023 (6): 115-118
Funding
Key Project of Provincial Education Science Planning for 2024 (Bb/2024/02/124); Horizontal project for 2023 (H2023-008); Excellent Teaching Team Project of Jiangsu Qinglan Project; Computer Basic Education Teaching Research Project of the National Higher Education Computer Basic Education Research Association in 2023 (2024-AFCEC-553); General Project of Philosophy and Social Sciences Research in Jiangsu Universities in 2024 (2024SJYB1148); 2024 National Computer Basic Education Research Association Computer Basic Education Teaching Research Project (2024-AFCEC-552)
About the authors
Sun Cuigai (February 1982-), female, Han ethnicity, from Suzhou, Jiangsu, associate professor, PhD, research direction: mobile development, artificial intelligence.