arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18326cs.CVphysics.app-ph
收藏

激光粉末床熔融熔道显微图像的自动分割与分析

Automated Segmentation and Analysis of Microscopy Images of Laser Powder Bed Fusion Melt Tracks

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Massachusetts Institute of Technology(麻省理工学院)

Aagam Shah, Reimar Weissbach, David A. Griggs, A. John Hart, Elif Ertekin, Sameh Tawfick

AI总结:

本文提出基于U-Net的图像分割神经网络,用于自动识别和测量激光粉末床熔融熔道尺寸,在62张跨设备图像上训练后分类准确率超99%,并提取熔池高度、宽度和润湿角。

摘要:

随着金属增材制造(AM)的日益普及,研究人员和从业者正转向数据驱动的方法来优化打印条件。熔道的横截面图像为调整工艺参数、开发参数缩放数据以及识别缺陷提供了有价值的信息。本文提出了一种图像分割神经网络,能够从横截面图像中自动识别并测量熔道尺寸。我们采用U-Net架构,在来自不同实验室、不同机器和不同材料的62张预标注图像组成的数据集上进行训练,并结合了图像增强技术。当批量大小和学习率等神经网络超参数得到适当调优时,学习得到的模型在分类准确率上超过99%,F1分数超过90%。该神经网络在由不同用户拍摄、在不同机器上打印以及使用不同显微镜采集的图像上测试时表现出良好的鲁棒性。后处理模块提取熔池的高度和宽度以及润湿角。我们讨论了提高模型性能的机会以及迁移学习的途径,例如扩展到定向能量沉积等其他增材制造工艺。

英文摘要:

With the increasing adoption of metal additive manufacturing (AM), researchers and practitioners are turning to data-driven approaches to optimise printing conditions. Cross-sectional images of melt tracks provide valuable information for tuning process parameters, developing parameter scaling data, and identifying defects. Here we present an image segmentation neural network that automatically identifies and measures melt track dimensions from a cross-section image. We use a U-Net architecture to train on a data set of 62 pre-labelled images obtained from different labs, machines, and materials coupled with image augmentation. When neural network hyperparameters such as batch size and learning rate are properly tuned, the learned model shows an accuracy for classification of over 99% and an F1 score over 90%. The neural network exhibits robustness when tested on images captured by various users, printed on different machines, and acquired using different microscopes. A post-processing module extracts the height and width of the melt pool, and the wetting angles. We discuss opportunities to improve model performance and avenues for transfer learning, such as extension to other AM processes such as directed energy deposition.

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。

↑