A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures

A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures
复制标题

使用热特征进行金属粉末床熔融分层孔隙率预测的深度学习框架

DOI:
10.1007/s10845-022-02039-3
复制
发表时间:
2022
影响因子:
8.3
通讯作者:
Liao, Wei-keng
Liao, Wei-keng
中科院分区:
工程技术1区
文献类型:
--
作者:
Mao, Yuwei;Lin, Hui;Yu, Christina Xuan;Frye, Roger;Beckett, Darren;Anderson, Kevin;Jacquemetton, Lars;Carter, Fred;Gao, Zhangyuan;Liao, Wei-keng

文献摘要

参考文献

被引文献

相似文献

通过激光粉末床熔融工艺制造的零件质量受到孔隙率的显著影响。现有的孔隙度预测的过程-性质关系的工作需要许多实验或计算昂贵的模拟,而不考虑环境变化。而采用实时监测传感器的努力只能在孔隙发生后才能检测到它,而不是提前预测它。在这项研究中,提出了一种基于深度学习的新型孔隙度检测-预测框架,该框架根据前一层的热特征预测下一层的孔隙度。所提出的框架进行了验证,其能力,准确地预测缺乏融合的孔隙度,使用计算机断层扫描(CT)扫描,达到F1分数为0.75。本文提出的框架可以有效地应用于增材制造中的质量控制。根据预测的孔隙位置,可以调整下一层中的激光工艺参数以避免将来出现更多的部件孔隙,或者可以填充现有的孔隙。如果预测的零件孔隙率无论激光参数如何都不可接受,则可以停止构建过程以最小化损失。
Part quality manufactured by the laser powder bed fusion process is significantly affected by porosity. Existing works of process–property relationships for porosity prediction require many experiments or computationally expensive simulations without considering environmental variations. While efforts that adopt real-time monitoring sensors can only detect porosity after its occurrence rather than predicting it ahead of time. In this study, a novel porosity detection-prediction framework is proposed based on deep learning that predicts porosity in the next layer based on thermal signatures of the previous layers. The proposed framework is validated in terms of its ability to accurately predict lack of fusion porosity using computerized tomography (CT) scans, which achieves a F1-score of 0.75. The framework presented in this work can be effectively applied to quality control in additive manufacturing. As a function of the predicted porosity positions, laser process parameters in the next layer can be adjusted to avoid more part porosity in the future or the existing porosity could be filled. If the predicted part porosity is not acceptable regardless of laser parameters, the building process can be stopped to minimize the loss.
DOI: 10.1038/s41598-022-15816-0
发表时间: 2022-07-13
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Jha, Dipendra;Gupta, Vishu;Liao, Wei-keng;Choudhary, Alok;Agrawal, Ankit
通讯作者: Agrawal, Ankit
基于CMS的网页设计管理中多层感知器人工神经网络与遗传算法的新型混合模型
DOI: --
发表时间: 2018
期刊:
影响因子: --
作者:
M. Aghazadeh;F. S. Gharehchopogh
通讯作者: F. S. Gharehchopogh
激光粉末床熔合孔隙率的概率预测控制
DOI: 10.1007/s10845-021-01836-6
发表时间: 2021
影响因子: 8.3
作者:
Paromita Nath;S. Mahadevan
通讯作者: S. Mahadevan
DOI: 10.3390/s22020494
发表时间: 2022-01-10
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
McGowan E;Gawade V;Guo WG
通讯作者: Guo WG
采矿业电子健康记录预处理的系统方法:心脏病案例研究
DOI: --
发表时间: 2020
影响因子: 0.3
作者:
Leila Baradaran Sorkhabi;F. S. Gharehchopogh;J. Shahamfar
通讯作者: J. Shahamfar