Anomaly Detection Model Based Visual Inspection Method for PCB Board Manufacturing Process

被引：0
|
作者：
Lee, Sang-Jeong [1 ]
Seo, Sung-Bal [2 ]
Bae, You-Suk [2 ]
机构：
[1] Vision AI Business Team, LG CNS, Korea, Republic of
[2] Dept. of Computer Engineering, Tech University of Korea, Korea, Republic of
来源：
Transactions of the Korean Institute of Electrical Engineers | 2024年 / 73卷 / 11期
关键词：
Contrastive Learning - Deep learning - Smart manufacturing;
D O I：
10.5370/KIEE.2024.73.11.2024
中图分类号：
学科分类号：
摘要：
We developed a visual inspection method for PCB board using an anomaly detection model. To improve feature extraction performance, we developed and optimized the feature extractor by comparing three types of backbone models. Then we compared two anomaly detection models with developed feature extractor as a backbone for visual inspection. Finally, we found the optimized loss function named mean-shifted contrastive loss which showed the highest accuracy in our experiment. Copyright © The Korean Institute of Electrical Engineers.
引用
收藏
页码：2024 / 2029
相关论文
共 50 条
  • [1] Design and development of automatic visual inspection system for PCB manufacturing
    Mar, N. S. S.
    Yarlagadda, P. K. D. V.
    Fookes, C.
    ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2011, 27 (05) : 949 - 962
  • [2] Glue Level Estimation through Automatic Visual Inspection in PCB Manufacturing
    Iglesias, Bruno P.
    Otani, Mario
    Oliveira, Felipe G.
    PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS (ICINCO), 2021, : 731 - 738
  • [3] AUTOMATIC VISUAL INSPECTION SYSTEM FOR PCB-FABRICATION PROCESS
    PIIRONEN, T
    ELSILA, M
    SILVEN, O
    VIRTANEN, I
    ACTA POLYTECHNICA SCANDINAVICA-APPLIED PHYSICS SERIES, 1985, (150): : 37 - 40
  • [4] New Anomaly Detection in Semiconductor Manufacturing Process using Oversampling Method
    Song, Seunghwan
    Baek, Jun-Geol
    ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 2, 2020, : 926 - 932
  • [5] AN ANOMALY DETECTION METHOD BASED ON SELF-SUPERVISED LEARNING WITH SOFT LABEL ASSIGNMENT FOR DEFECT VISUAL INSPECTION
    Hu, Chuanfei
    Wang, Yongxiong
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3468 - 3472
  • [6] Automatic Industry PCB Board DIP Process Defect Detection with Deep Ensemble Method
    Yu-Ting, Li
    Kuo, Paul
    Jiun-In, Guo
    2020 IEEE 29TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2020, : 453 - 459
  • [7] Energy consumption of the brushing process for PCB manufacturing based on a friction model
    Hae-Sung Yoon
    Eun-Seob Kim
    Min-Soo Kim
    Gyu-Bong Lee
    Sung-Hoon Ahn
    International Journal of Precision Engineering and Manufacturing, 2014, 15 : 2265 - 2272
  • [8] Energy Consumption of the Brushing Process for PCB Manufacturing Based on a Friction Model
    Yoon, Hae-Sung
    Kim, Eun-Seob
    Kim, Min-Soo
    Lee, Gyu-Bong
    Ahn, Sung-Hoon
    INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING, 2014, 15 (11) : 2265 - 2272
  • [9] Dynamic Bayesian Network-Based Anomaly Detection for In-Process Visual Inspection of Laser Surface Heat Treatment
    Ogbechie, Alberto
    Diaz-Rozo, Javier
    Larranaga, Pedro
    Bielza, Concha
    MACHINE LEARNING FOR CYBER PHYSICAL SYSTEMS, 2017, 3 : 17 - 24
  • [10] A Novel Method of Digital Twin-Based Manufacturing Process State Modeling and Incremental Anomaly Detection
    Zhang, Qinglei
    Liu, Zhen
    Duan, Jianguo
    Qin, Jiyun
    MACHINES, 2023, 11 (02)
12345