Intelligent detection methods for miniature defects in metallic materials

IF 4.5 Q2 COMPUTER SCIENCE, THEORY & METHODS

Array Pub Date : 2025-06-27 DOI:10.1016/j.array.2025.100430

Chuan-Hao Liu , Wei-Lun Lin , Fan-Shuo Tseng

{"title":"Intelligent detection methods for miniature defects in metallic materials","authors":"Chuan-Hao Liu , Wei-Lun Lin , Fan-Shuo Tseng","doi":"10.1016/j.array.2025.100430","DOIUrl":null,"url":null,"abstract":"<div><div>Powder metallurgy (PM) technology is extensively used in high-value industries for its energy efficiency, precision, and cost-effectiveness. However, detecting mini-defects in PM production remains challenging, particularly in highly customized and small-batch productions. This study evaluated defect detection in PM parts, PMPDv1 and PMPDv2 datasets comprising 457 and 1521 images, respectively. Automated optical inspection (AOI) and image augmentation techniques were applied to enhance image quality and model learning. The YOLO series models were employed for automated defect detection.</div><div>Results demonstrated that YOLOv4 achieved a mean average precision (mAP) of 93.94% at a resolution of 1600 but required 31 GB of GPU memory and 881,443 GFLOPs. YOLOv5s, under the same conditions, achieved an mAP of 92.7% with just 12.1 GB of GPU memory and 15.8 GFLOPs, making it suitable for resource-constrained environments. This study confirms the efficacy of YOLO models for PM defect detection and suggests further exploration of transfer learning and generative AI techniques to enhance detection efficiency and accuracy in other products.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100430"},"PeriodicalIF":4.5000,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Array","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590005625000578","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}

引用次数: 0

Abstract

Powder metallurgy (PM) technology is extensively used in high-value industries for its energy efficiency, precision, and cost-effectiveness. However, detecting mini-defects in PM production remains challenging, particularly in highly customized and small-batch productions. This study evaluated defect detection in PM parts, PMPDv1 and PMPDv2 datasets comprising 457 and 1521 images, respectively. Automated optical inspection (AOI) and image augmentation techniques were applied to enhance image quality and model learning. The YOLO series models were employed for automated defect detection.

Results demonstrated that YOLOv4 achieved a mean average precision (mAP) of 93.94% at a resolution of 1600 but required 31 GB of GPU memory and 881,443 GFLOPs. YOLOv5s, under the same conditions, achieved an mAP of 92.7% with just 12.1 GB of GPU memory and 15.8 GFLOPs, making it suitable for resource-constrained environments. This study confirms the efficacy of YOLO models for PM defect detection and suggests further exploration of transfer learning and generative AI techniques to enhance detection efficiency and accuracy in other products.

查看原文本刊更多论文

金属材料微小缺陷的智能检测方法

粉末冶金（PM）技术因其高能效、精度和成本效益而广泛应用于高价值行业。然而，在PM生产中检测微小缺陷仍然具有挑战性，特别是在高度定制和小批量生产中。本研究评估了PM部件的缺陷检测，PMPDv1和PMPDv2数据集分别包含457和1521张图像。应用自动光学检测（AOI）和图像增强技术来提高图像质量和模型学习。采用YOLO系列模型进行自动缺陷检测。结果表明，YOLOv4在1600分辨率下实现了93.94%的平均精度（mAP），但需要31 GB的GPU内存和881,443 GFLOPs。在相同的条件下，YOLOv5s仅使用12.1 GB的GPU内存和15.8 GFLOPs就实现了92.7%的mAP，使其适合资源受限的环境。本研究证实了YOLO模型在PM缺陷检测中的有效性，并建议进一步探索迁移学习和生成式AI技术，以提高其他产品的检测效率和准确性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊