计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230700086-8.doi: 10.11896/jsjkx.230700086
焦若丹, 高东辉, 黄艳华, 刘硕, 段宣翡, 王蕊, 刘伟东
JIAO Ruodan, GAO Donghui, HUANG Yanhua, LIU Shuo, DUAN Xuanfei, WANG Rui, LIU Weidong
摘要： 随着工业4.0时代的到来,制造业与人工智能的深度融合已成为了业界的重要发展趋势,工业质检是其中的重要突破口,但目前业界缺乏对工业质检产品进行评估的标准方法,各质检产品的性能往往不透明,不利于优化迭代及规模推广。针对上述问题,提出了一种面向工业界产线应用需求的AI工业质检算法评测方法,可在工业领域样本数量少且不均衡的情况下,面向产线落地应用需求,对AI工业质检产品及其竞品进行对标评估。该评测方法通过交叉验证法构建数据集,从而避免数据集规模小且不均衡导致的评测结果波动较大的问题,通过灰盒测试法避免数据集来源单一导致的评测结果不客观问题,并根据产线实际生产需求制定相关评估指标,可真实反映产线应用场景下质检产品检测性能。将上述方法应用于光伏电池片EL检测产品的对标评测中进行验证,结果表明该评测方法具备可行性,且能客观反映各产品的真实性能。最后,基于对评测结果的分析对比,为AI工业质检产品的优化提供了一些建议。
中图分类号:
| [1]国家工业信息安全发展研究中心.AI工业质检应用发展白皮书.[R/OL].https://www.zhangqiaokeyan.com/academic-journal-cn_ceocio-china_thesis/02012102861837.html. [2]LUO D L,CAI Y X,YANG Z H,et al.Survey on industrial defect detection with deep learning[J].Sci SinInform,2022,52:1002-1039. [3]DENG Y S,LUO A C,DAI M J.Building an automatic defect verification system using deep neural network for PCB defect classification[C]//Proceedings of the 4th International Conference on Frontiers of Signal Processing(ICFSP).2018:145-149. [4]DEITSCH S,CHRISTLEIN V,BERGER S,et al.Automaticclassification of defective photovoltaic module cells in electrolu-minescence images[J].Sol Energy,2019,185:455-468. [5]ZHANG Z,WEN G,CHEN S.Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding[J].J Manuf Processes,2019,45:208-216. [6]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of Advances in Neural Information Processing Systems.2015:91-99. [7]HE Y,SONG K,MENG Q,et al.An end-to-end steel surfacedefect detection approach via fusing multiple hierarchical features[J].IEEE Trans Instrum Meas,2020,69:1493-1504. [8]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:4700-4708. [9]REDMON J,FARHADI A.Yolov3:an incremental improve-ment[J].arXiv:1804.02767101255,2018. [10]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Visionand Pattern Recognition.2016:779-788. [11]REDMON J,FARHADI A.Yolo9000:better,faster,stronger[C]//CVPR.2017. [12]LI J,SU Z,GENG J,et al.Real-time detection of steel strip surface defects based on improved YOLO detection network[J].IFAC-Papers OnLine,2018,51:76-81. [13]CHEN S H,TSAI C C.SMD LED chips defect detection using a YOLOv3-dense model[J].Adv Eng Inf,2021,47:101255. [14]CHA Y J,CHOI W,SUH G,et al.Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types[J].Comput-Aided Civil Infrastruct Eng,2018,33:731-747. [15]TAO X,ZHANG D,WANG Z,et al.Detection of power line insulator defects using aerial images analyzed with convo-lutional neural networks[J].IEEE Trans Syst Man Cybern Syst,2020,50:1486-1498. [16]ZHANG C,CHANG C,JAMSHIDI M.Concrete bridge surface damage detection using a single-stage detector[J].Comput-Aided Civil Infrastruct Eng,2020,35:389-409. [17]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440. [18]RONNEBERGER O,FISCHER P,BROX T.U-Net:convolu-tional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-assisted Intervention.Cham:Springer,2015:234-241. [19]QIU L,WU X,YU Z.A high-efficiency fully convolutional networks for pixel-wise surface defect detection[J].IEEE Access,2019,7:15884-15893. [20]HUANG Y,QIU C,YUAN K.Surface defect saliency of magnetic tile[J].Vis Comput,2020,36:85-96. [21]XIE Y,ZHU F,FU Y.Main-secondary network for defect segmentation of textured surface images[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2020:3531-3540. |
|
||
首页