[1]张鹏飞,王淑青,王年涛,等. 基于改进MobileNetV3的PCB裸板缺陷检测[J].湖北工业大学学报,2023,(1):27-32.
　ZHANG Pengfei,WANG Shuqing,WANG Niantao,et al. PCB Bare Board Defect Detection Based on Improved MobileNetV3[J].,2023,(1):27-32.
点击复制

 基于改进MobileNetV3的PCB裸板缺陷检测()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2023年第1期
页码:
27-32
栏目:
湖北工业大学学报
出版日期:
2023-03-13

文章信息/Info

Title:
 PCB Bare Board Defect Detection Based on Improved MobileNetV3
文章编号:
1003-4684(2023)01-0027-06
作者:
 张鹏飞;  王淑青;  王年涛;  顿伟超;  黄剑锋
 湖北工业大学电气与电子工程学院，湖北 武汉 430068
Author(s):
 ZHANG Pengfei;  WANG Shuqing;  WANG Niantao;  DUN Weichao;  HUANG Jianfeng
 School of Electrical and Electronic Engineering，Hubei Univ. of Tech.，Wuhan 430068，China
关键词:
 ; PCB裸板;  缺陷检测;  MobileNetV3;  软池化;  深度学习
Keywords:
 ; Bare PCB board;  Defect detection;  MobileNetV3;  Soft pool;  Deep learning
分类号:
TP391.4
文献标志码:
A
摘要:
 为解决传统PCB裸板缺陷检测效率低、误检率高、通用性差等问题，提出一种基于改进MobileNetV3的PCB表面缺陷检测模型。首先对PCB数据集进行预处理，然后采用多方向协调注意力代替原网络中的挤压和激励注意力模块，提升特征定位精度从而增强感受野；最后利用软池化优化MobileNetV3的末端结构，以在简化后的激活映射中保留更多的特征信息。实验结果证明，提出的模型对PCB裸板缺陷检测的平均准确率可达96.1%，图片平均检测速度为25.1 ms，能够高效识别PCB裸板的多种缺陷类型，对工业生产中PCB裸板的质量检测有实际应用价值。
Abstract:
 To solve the problems of low efficiency, high error detection rate and poor universality of traditional PCB bare board defect detection, a PCB surface defect detection method based on improved MobileNetV3 was proposed. Firstly, PCB data set was preprocessed. Then, multi-directional coordinated attention was used to replace the squeezing and motivating attention modules in the original network to improve the accuracy of feature localization and enhance the receptive field. Finally, the Soft Pool was used to optimize the terminal structure of MobileNetV3 to retain more feature information in the simplified activation map. Experimental results show that the average accuracy of the proposed model is 96.1%, and the average image detection speed is 25.1ms. The proposed model can efficiently identify various defect types of PCB bare board, and has practical application value for PCB bare board quality detection in industrial production.

参考文献/References:

[1] 李磊, 秦伟鹏, 江庭富. 印制电路板钻孔毛刺的产生原因与改善探讨[J].印制电路信息, 2021, 29(11): 10-13.
[2] IKIRI  Y, FUMIYA SAKO, MASAKI HASHIZUME, et al. Open defect detection in assembled circuit boards with built-in relaxation oscillators[J]. In IEEE Transactions on Components, Packaging and Manufacturing Technology, 2021, 11(06): 931-943.
[3] 魏嘉莉,王瑞丰,冀运景, 等.基于机器视觉的PCB板电解电容极性自动定位[J].电子测量技术,2021,44(16):148-155.
[4] 陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J].自动化学报, 2021, 47(05): 1017-1034.
[5] ADIBHATLA V A, SHIEH J, ABBOD M F, et al. Detecting defects in PCB using deep learning via convolution neural networks[C]. 2018 13th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT), 2018: 202-205.
[6] 瞿栋, 汪鹏宇, 黄允, 等. 基于卷积神经网络的PCB缺陷图像识别[J].计量与测试技术, 2021, 48(08): 21-23.
[7] 耿朝晖, 龚涛. 基于改进Faster R-CNN的PCB板表面缺陷检测[J].现代计算机,2021(19):89-93.
[8] 谢黎, 袁小芳, 尹柏鑫. 基于改进YOLOv4网络的电路板元器件缺陷检测[J]. 测控技术, 2022, 41(04):9.
[9] HOWARD A, MARK SANDLER, BO CHEN, et al. Searching for MobileNetV3[C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019: 1314-1324.
[10] JIE H , LI S , GANG S. Squeeze and excitation networks[C].∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018：7132-7141.
[11] PALA T, GVEN U, KAHRAMAN H T, et al. Comparison of pooling methods for handwritten digit recognition problem[C]. 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 2018: 1-5.
[12] RAO Q, YU B, HE K, et al. Regularization and iterative initialization of softmax for fast training of convolutional neural networks[C]. 2019 International Joint Conference on Neural Networks (IJCNN), 2019: 1-8.
[13] DING R, DAI L, LI G, et al. TDD-net: a tiny defect detection network for printed circuit boards[J]. In CAAI Transactions on Intelligence Technology, 2019, 4(02): 110-116.
[14] HAO G, YINGKUN Y, YI Q. General target detection method based on improved SSD[C]. 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2019:1787-1791.
[15] FENG H, JIANG Y. Recognition of insulator based on yolov5 algorithm[C]. 2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2021: 505-509.

相似文献/References:

[1]熊韧,曹海印,王焱清,等.非牛顿润滑静压轴承的节流器流量方程修正[J].湖北工业大学学报,2019,34(5):6.
　XIONG Ren,CAO Haiyin,WANG Yanqing,et al.Modified restrictor flow equations of hydrostatic bearings ubricated by non-Newtonian fluids[J].,2019,34(1):6.
[2]王照远,曹 民,王 毅,等. 场景与数据双驱动的隧道图像拼接方法[J].湖北工业大学学报,2020,(4):11.
　WANG Zhaoyuan,CAO Min,WANG Yi,et al. Tunnel Image Stitching Method based on Scene and Data[J].,2020,(1):11.
[3]潘 健,梁佳成,陈凤娇,等. 单电流闭环多重PR控制的LCL型逆变器[J].湖北工业大学学报,2020,(4):16.
　PAN Jian,LIANG Jiacheng,CHEN Fengjiao,et al. Design of LCL Grid Connected Inverter based on Single Closed Loop Control and Multiple PR Controllers[J].,2020,(1):16.
[4]王晓光,赵 萌,文益雪,等. 定子闭口槽结构对永磁电机齿槽转矩影响分析[J].湖北工业大学学报,2020,(4):25.
　WANG Xiaoguang,ZHAO Meng,WEN Yixue,et al. Study on Cogging Torque and Vibration Noise of Permanent Magnet Motor with Segmental Stator and Closed-Slot[J].,2020,(1):25.
[5]宇 卫,凃玲英,陈 健. 风电场集中接入对集电线电流保护的影响[J].湖北工业大学学报,2020,(4):29.
　YU Wei,TU Lingying,CHEN Jian. Effect of the Collective Line Current Protection when Wind Farms are Centralized Accessed to the Power System[J].,2020,(1):29.
[6]廖政斌,王泽飞,祝 珊. 二惯量系统谐振在线抑制及相位补偿[J].湖北工业大学学报,2020,(4):34.
　LIAO Zhengbin,WANG Zefei,ZHU Shan. Online Resonance Suppression and Phase Compensation for Double Inertia System[J].,2020,(1):34.
[7]王 欣,游 颖,姜天翔,等. 面向3D打印过程的产品工艺设计和优化[J].湖北工业大学学报,2020,(4):39.
　WANG Xin,YOU Ying,JIANG Tianxiang,et al. Product Process Design and Optimization for 3D Printing Processes[J].,2020,(1):39.
[8]冉晶晶,文 红,罗雅梅,等. 全自动样品前处理平台及其控制系统[J].湖北工业大学学报,2020,(4):43.
　RAN Jingjing,WEN Hong,LUO Yamei,et al. Research on Automatic Sample Preprocessing Platform and its Control System[J].,2020,(1):43.
[9]杨 磊,马志艳,石 敏,等. 基于模糊PID的小型冷库过热度控制方法[J].湖北工业大学学报,2020,(4):43.
　YANG Lei,MA Zhiyan,SHI Min,et al. Research on Superheat Control Method of Small Cold Storage based on Fuzzy PID[J].,2020,(1):43.
[10]黄 晶,周细枝,周业望. 动态注塑成型模具的设计与实验研究[J].湖北工业大学学报,2020,(4):52.
　HUANG Jing,ZHOU Xizhi,ZHOU Yewang. Design and Experimental Study of Dynamic Injection Molding[J].,2020,(1):52.

备注/Memo

备注/Memo:
［收稿日期］ 2021-12-19
［第一作者］ 张鹏飞（1995-），男，内蒙古呼和浩特人，湖北工业大学硕士研究生，研究方向为目标检测与智能控制系统
［通信作者］ 王淑青（1969-），女，河北衡水人，湖北工业大学教授，研究方向为人工智能，目标检测及智能控制
更新日期/Last Update: 2023-03-14