Data-Driven Prediction and Uncertainty Quantification of Process Parameters for Directed Energy Deposition

Author:

Hermann Florian12ORCID,Michalowski Andreas13,Brünnette Tim4,Reimann Peter1ORCID,Vogt Sabrina2,Graf Thomas13ORCID

Affiliation:

1. Graduate School of Excellence Advanced Manufacturing Engineering (GSaME), University of Stuttgart, Nobelstraße 12, 70569 Stuttgart, Germany

2. TRUMPF Laser- und Systemtechnik GmbH, Johann-Maus-Straße 2, 71254 Ditzingen, Germany

3. Institut für Strahlwerkzeuge (IFSW), University of Stuttgart, Pfaffenwaldring 43, 70569 Stuttgart, Germany

4. Institut für Wasser- und Umweltsystemmodellierung (IWS), University of Stuttgart, Pfaffenwaldring 5a, 70569 Stuttgart, Germany

Abstract

Laser-based directed energy deposition using metal powder (DED-LB/M) offers great potential for a flexible production mainly defined by software. To exploit this potential, knowledge of the process parameters required to achieve a specific track geometry is essential. Existing analytical, numerical, and machine-learning approaches, however, are not yet able to predict the process parameters in a satisfactory way. A trial-&-error approach is therefore usually applied to find the best process parameters. This paper presents a novel user-centric decision-making workflow, in which several combinations of process parameters that are most likely to yield the desired track geometry are proposed to the user. For this purpose, a Gaussian Process Regression (GPR) model, which has the advantage of including uncertainty quantification (UQ), was trained with experimental data to predict the geometry of single DED tracks based on the process parameters. The inherent UQ of the GPR together with the expert knowledge of the user can subsequently be leveraged for the inverse question of finding the best sets of process parameters by minimizing the expected squared deviation between target and actual track geometry. The GPR was trained and validated with a total of 379 cross sections of single tracks and the benefit of the workflow is demonstrated by two exemplary use cases.

Funder

Landesministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg

German Federal Ministry of Education and Research

Deutsche Forschungsgemeinschaft

Publisher

MDPI AG

Subject

General Materials Science

Reference53 articles.

1. Schuh, G., Rudolf, S., and Riesener, M. (2016, January 16–19). Design for industrie 4.0. Proceedings of the 14th International Design Conference, Cavtat, Dubrovnik.

2. Production management for mass customization and smart cellular manufacturing system: NSGAII and SMPSO for factory-level planning;Maalouf;Int. J. Adv. Manuf. Technol.,2022

3. Smart mobile apps for supporting product design and decision-making in the era of mass customisation;Mourtzis;Int. J. Comput. Integr. Manuf.,2017

4. Software-defined Cloud Manufacturing for Industry 4.0;Thames;Procedia CIRP,2016

5. Reshaping the Landscape of the Future: Software-Defined Manufacturing;Xu;Computer,2021

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3