使用迁移学习方法对3D打印圆柱体对象的缺陷分析
Defect Analysis of 3D Printed Cylinder Object Using Transfer Learning Approaches
AI总结:
本研究利用迁移学习模型(如MobileNetV2)对3D打印圆柱体图像进行缺陷检测,在两个数据集上比较多种模型性能,发现MobileNetV2准确率最高,而ResNet50表现最差,为增材制造自动化缺陷分析提供了优化方向。
摘要:
增材制造(AM)正在医疗保健、航空航天和汽车等多个行业受到越来越多的关注。然而,在增材制造过程中及早识别缺陷可以降低生产成本并提高生产率——这是一个关键挑战。本研究探讨了机器学习(ML)方法,特别是迁移学习(TL)模型,在3D打印圆柱体缺陷检测中的有效性。使用包括VGG16、VGG19、ResNet50、ResNet101、InceptionResNetV2和MobileNetV2在内的模型对圆柱体图像进行了分析。在两个数据集上使用准确率、精确率、召回率和F1分数指标进行了性能比较。在第一项研究中,VGG16、InceptionResNetV2和MobileNetV2取得了满分。相比之下,ResNet50的性能最低,平均F1分数为0.32。同样,在第二项研究中,MobileNetV2正确分类了所有实例,而ResNet50则因更多的假阳性和更少的真阳性而表现不佳,导致F1分数为0.75。总体而言,研究结果表明,某些迁移学习模型(如MobileNetV2)可以在增材制造缺陷分类中提供高准确率,尽管不同算法的性能存在差异。这些结果为在3D打印过程中实现可靠的自动化缺陷分析所需的模型优化和集成提供了见解。通过识别性能最佳的迁移学习技术,本研究旨在通过稳健的基于图像的监测和检查来提高增材制造产品质量。
英文摘要:
Additive manufacturing (AM) is gaining attention across various industries like healthcare, aerospace, and automotive. However, identifying defects early in the AM process can reduce production costs and improve productivity - a key challenge. This study explored the effectiveness of machine learning (ML) approaches, specifically transfer learning (TL) models, for defect detection in 3D-printed cylinders. Images of cylinders were analyzed using models including VGG16, VGG19, ResNet50, ResNet101, InceptionResNetV2, and MobileNetV2. Performance was compared across two datasets using accuracy, precision, recall, and F1-score metrics. In the first study, VGG16, InceptionResNetV2, and MobileNetV2 achieved perfect scores. In contrast, ResNet50 had the lowest performance, with an average F1-score of 0.32. Similarly, in the second study, MobileNetV2 correctly classified all instances, while ResNet50 struggled with more false positives and fewer true positives, resulting in an F1-score of 0.75. Overall, the findings suggest certain TL models like MobileNetV2 can deliver high accuracy for AM defect classification, although performance varies across algorithms. The results provide insights into model optimization and integration needs for reliable automated defect analysis during 3D printing. By identifying the top-performing TL techniques, this study aims to enhance AM product quality through robust image-based monitoring and inspection.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。