Improving Geometric Accuracy in Wire and Arc Additive Manufacturing With Engineering-Informed Machine Learning

Cesar Ruiz, Davoud Jafari, Vignesh Venkata Subramanian, Tom H.J. Vaneker, Wei Ya, Qiang Huang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Wire and arc additive manufacturing (WAAM) is a promising technology for fast and cost-effective fabrication of largescale components made of high-value materials for industries such as petroleum and aerospace. By using robotic arc welding and wire filler materials,WAAM can fabricate complex large near-net shape parts with high deposition rates, short lead times and millimeter resolution. However, due to high temperature gradients and residual stresses, currentWAAM technologies suffer from high surface roughness and poor shape accuracy. This limits the adoption of these technologies in industry and complicates process control and optimization. Since its conception, considerable research efforts have been made on improving the mechanical and microstructural performance of WAAM components while few studies have investigated their geometric accuracy. In this work, we propose an engineering-informed machine learning (ML) framework for predicting and compensating for the geometric deformation of WAAM fabricated products based on a few sample parts. The proposed ML algorithm efficiently separates geometric shape deviation into deformation and surface roughness. Then, the predicted shape deformation of a new product is minimized by applying optimal geometric compensa- tion to the product design. Experimental validation on cylindrical shapes showed that the proposed methodology can effectively reduce product shape deviation, which facilitates the widespread adoption of WAAM.

Original languageEnglish
Title of host publicationASME 2022 17th International Manufacturing Science and Engineering Conference
Subtitle of host publicationJune 27–July 1, 2022 West Lafayette, Indiana, USA
PublisherAmerican Society of Mechanical Engineers
Volume1
ISBN (Electronic)978-0-7918-8580-2
DOIs
Publication statusPublished - 2022
EventASME 2022 17th International Manufacturing Science and Engineering Conference, MSEC 2022 - West Lafayette, United States
Duration: 27 Jun 20221 Jul 2022

Conference

ConferenceASME 2022 17th International Manufacturing Science and Engineering Conference, MSEC 2022
Abbreviated titleMSEC2022
Country/TerritoryUnited States
CityWest Lafayette
Period27/06/221/07/22

Keywords

  • Machine Learning (ML)
  • Shape deviation reduction
  • Wire arc additive manufacturing
  • NLA

Fingerprint

Dive into the research topics of 'Improving Geometric Accuracy in Wire and Arc Additive Manufacturing With Engineering-Informed Machine Learning'. Together they form a unique fingerprint.

Cite this