Low Cost and Highly Sensitive Automated Surface Defects Identification Method of Precision Castings Using Deep Learning

IF 2.6 3区 材料科学 Q2 MATERIALS SCIENCE, CHARACTERIZATION & TESTING
Huipeng Yu, Maodong Kang, Chenyang Ding, Yahui Liu, Haiyan Gao, Jun Wang
{"title":"Low Cost and Highly Sensitive Automated Surface Defects Identification Method of Precision Castings Using Deep Learning","authors":"Huipeng Yu,&nbsp;Maodong Kang,&nbsp;Chenyang Ding,&nbsp;Yahui Liu,&nbsp;Haiyan Gao,&nbsp;Jun Wang","doi":"10.1007/s10921-024-01121-5","DOIUrl":null,"url":null,"abstract":"<div><p>The surface of superalloy precision castings might exhibit defects after forming, posing a significant risk to their service life, necessitating inspection during post-process. Radiographic inspection, with its extensive research in automation, can achieve efficient and accurate detection of defects. However, it is limited in surface defects detection due to limited sensitivity to non-volumetric defects and high cost. In contrast, fluorescent penetrant inspection (FPI) is highly efficient for surface defect inspection due to its low cost, high sensitivity, and speed. However, manual examination introduces variability in the results, impacting the consistency and reliability of the inspection process. Automation is needed to ensure consistency and reliability of inspection. The implementation of an automated defect identification system based on FPI using convolutional neural networks (CNNs) was systematically investigated. Among the CNN models tested, MobileNetV2 exhibited exceptional performance, achieving a remarkable recall rate of 0.992 and an accuracy of 0.992. Additionally, the effect of class imbalance on model performance was carefully examined. Furthermore, the features extracted by the model were visualized using Grad-CAM to reveal the attention of the CNN model to the fluorescent display features of defects. This study underscores the strong capability of deep learning architectures in identifying defects of precision casting components, paving the way for the automation of the entire FPI process.</p></div>","PeriodicalId":655,"journal":{"name":"Journal of Nondestructive Evaluation","volume":"43 4","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nondestructive Evaluation","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s10921-024-01121-5","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, CHARACTERIZATION & TESTING","Score":null,"Total":0}
引用次数: 0

Abstract

The surface of superalloy precision castings might exhibit defects after forming, posing a significant risk to their service life, necessitating inspection during post-process. Radiographic inspection, with its extensive research in automation, can achieve efficient and accurate detection of defects. However, it is limited in surface defects detection due to limited sensitivity to non-volumetric defects and high cost. In contrast, fluorescent penetrant inspection (FPI) is highly efficient for surface defect inspection due to its low cost, high sensitivity, and speed. However, manual examination introduces variability in the results, impacting the consistency and reliability of the inspection process. Automation is needed to ensure consistency and reliability of inspection. The implementation of an automated defect identification system based on FPI using convolutional neural networks (CNNs) was systematically investigated. Among the CNN models tested, MobileNetV2 exhibited exceptional performance, achieving a remarkable recall rate of 0.992 and an accuracy of 0.992. Additionally, the effect of class imbalance on model performance was carefully examined. Furthermore, the features extracted by the model were visualized using Grad-CAM to reveal the attention of the CNN model to the fluorescent display features of defects. This study underscores the strong capability of deep learning architectures in identifying defects of precision casting components, paving the way for the automation of the entire FPI process.

利用深度学习实现低成本、高灵敏度的精密铸件表面缺陷自动识别方法
超合金精密铸件在成型后表面可能会出现缺陷,对其使用寿命构成重大威胁,因此有必要在后加工过程中进行检测。射线检测在自动化方面有广泛的研究,可以实现高效、准确的缺陷检测。然而,由于对非体积缺陷的灵敏度有限和成本高昂,它在表面缺陷检测方面受到限制。相比之下,荧光渗透检测(FPI)因其成本低、灵敏度高和速度快而在表面缺陷检测方面具有很高的效率。然而,人工检测会导致检测结果多变,影响检测过程的一致性和可靠性。为确保检测的一致性和可靠性,需要实现自动化。我们利用卷积神经网络(CNN)系统地研究了基于 FPI 的自动缺陷识别系统的实施情况。在测试的 CNN 模型中,MobileNetV2 表现优异,召回率达到 0.992,准确率达到 0.992。此外,还仔细研究了类不平衡对模型性能的影响。此外,还使用 Grad-CAM 对模型提取的特征进行了可视化,以揭示 CNN 模型对缺陷荧光显示特征的关注。这项研究强调了深度学习架构在识别精密铸造部件缺陷方面的强大能力,为整个 FPI 过程的自动化铺平了道路。
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
Journal of Nondestructive Evaluation
Journal of Nondestructive Evaluation 工程技术-材料科学:表征与测试
CiteScore
4.90
自引率
7.10%
发文量
67
审稿时长
9 months
期刊介绍: Journal of Nondestructive Evaluation provides a forum for the broad range of scientific and engineering activities involved in developing a quantitative nondestructive evaluation (NDE) capability. This interdisciplinary journal publishes papers on the development of new equipment, analyses, and approaches to nondestructive measurements.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信