太原理工大学学报2025，Vol.56Issue(3)：419-426,8.DOI:10.16355/j.tyut.1007-9432.20230217
基于多尺度目标检测的蓄电池外观缺陷检测
Detection of Battery Appearance Defects Based on Multi-Scale Object Detection
摘要
Abstract
[Purposes]Based on YOLO v4 framework,a new feature extraction network VoVNet-A algorithm was designed,which can effectively identify image fine-grained features.[Methods]With the proposed algorthm,acts of improved attention module CSAM on aggregated fea-tures,distinguishes of the importance of different channels and regions of aggregated features,and effi-cient filterings of the redundant features brought by feature aggregation were realized.The selection of pre-selected boxes was also optimized and a variety of data enhancements were used to expand the de-fect data,which finally improved the detection of battery defects.[Results]The ablation experiments show that the above enhancements can improve the detection accuracy to different degrees.The com-parison experiments show that compared with the commonly used target detection algorithms Fast RCNN,SSD-VGG16,and YOLO v4,the mAP values of the method for battery defects are im-proved by 11.5%,21.5%,and 3.3%,respectively,and the FPS quantities are increased by 16,12,and 4 frames,respectively.关键词
蓄电池故障/缺陷检测/深度学习/YOLO v4/VovNetKey words
battery faults/defects detection/deep learning/YOLO v4/VovNet分类
信息技术与安全科学引用本文复制引用
李洋,张建亮,赵敏,巫健,韩超,党小燕,王慧芳..基于多尺度目标检测的蓄电池外观缺陷检测[J].太原理工大学学报,2025,56(3):419-426,8.基金项目
国网山西省电力公司科技项目资助(52051C220003) （52051C220003）
