Deep Learning for Distortion Prediction in Laser-Based Additive Manufacturing using Big Data
Deep Learning for Distortion Prediction in Laser-Based Additive Manufacturing using Big Data
复制标题
DOI：
10.1016/j.mfglet.2019.02.001
复制
发表时间：
2019-04-01
影响因子：
3.9
通讯作者：
Bian, Linkan
中科院分区：
文献类型：
--
作者：
Francis, Jack;Bian, Linkan
基于激光的增材制造（LBAM）是一种制造工艺，是工业4.0的一个关键方面，其目标是采用许多传感器进行连续过程控制。LBAM中的一个当前挑战是制造部件的几何不准确性。为了提高精度，需要对失真进行准确的预测。在这里，我们开发了一种新的深度学习方法，通过考虑逐点失真预测的局部热传递，在LBAM公差范围内准确预测失真。我们的深度学习方法不仅可以提供高度准确的预测，而且还适合使用许多传感器分析大数据的工业4.0框架。(C)2019年制造工程师协会（SME）。由爱思唯尔有限公司出版。保留所有权利。
Laser-Based Additive Manufacturing (LBAM) is a fabrication process that is a key aspect of Industry 4.0, which aims to employ many sensors for continuous process control. One current challenge in LBAM is the geometric inaccuracy of fabricated parts. To increase accuracy, accurate predictions of distortion are needed. Here we develop a novel Deep Learning approach that accurately predicts distortion well within LBAM tolerance limits by considering the local heat transfer for pointwise distortion prediction. Our Deep Learning approach not only gives highly accurate predictions but also fits into the Industry 4.0 framework of analyzing big data with many sensors. (C) 2019 Society of Manufacturing Engineers (SME). Published by Elsevier Ltd. All rights reserved.