Shuhang Zhang , Xin Jin , Zhijiang Lou , Sen Wang , Shan Lu , Yifan He
{"title":"LSDF-Net: An efficient lightweight defect detection method for ultrasonic welding surfaces","authors":"Shuhang Zhang , Xin Jin , Zhijiang Lou , Sen Wang , Shan Lu , Yifan He","doi":"10.1016/j.jajp.2025.100339","DOIUrl":null,"url":null,"abstract":"<div><div>This paper proposes LSDF-Net, a lightweight and high-speed detection network designed to address the challenges of insufficient accuracy and high computational cost in ultrasonic welding surface defect detection. Built upon the YOLOv8 architecture, LSDF-Net integrates a Dynamic Surface Detail Fusion Module (DSDFM) to enhance multi-scale feature representation and introduces a Lightweight Shared Convolution and Separate Batch Normalization detection head (LSCSBD) to reduce parameters and accelerate inference. In addition, a LAMP-based pruning strategy is applied, which achieves a 67% reduction in model size and a 48% reduction in computational cost with almost no performance degradation. Experimental results on both a self-constructed ultrasonic welding defect dataset and the public NEU-DET dataset demonstrate that LSDF-Net achieves the best overall performance, striking an excellent balance between accuracy and real-time inference. These results highlight its strong potential for real-time industrial defect detection applications.</div></div>","PeriodicalId":34313,"journal":{"name":"Journal of Advanced Joining Processes","volume":"12 ","pages":"Article 100339"},"PeriodicalIF":4.0000,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Advanced Joining Processes","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666330925000603","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
This paper proposes LSDF-Net, a lightweight and high-speed detection network designed to address the challenges of insufficient accuracy and high computational cost in ultrasonic welding surface defect detection. Built upon the YOLOv8 architecture, LSDF-Net integrates a Dynamic Surface Detail Fusion Module (DSDFM) to enhance multi-scale feature representation and introduces a Lightweight Shared Convolution and Separate Batch Normalization detection head (LSCSBD) to reduce parameters and accelerate inference. In addition, a LAMP-based pruning strategy is applied, which achieves a 67% reduction in model size and a 48% reduction in computational cost with almost no performance degradation. Experimental results on both a self-constructed ultrasonic welding defect dataset and the public NEU-DET dataset demonstrate that LSDF-Net achieves the best overall performance, striking an excellent balance between accuracy and real-time inference. These results highlight its strong potential for real-time industrial defect detection applications.