Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning

Ramalho, André; Assad, Anis; Bevans, Benjamin; Deschamps, Fernando; Santos, Telmo G.; Oliveira, J. P.; Rao, Prahalada

http://hdl.handle.net/10362/187499

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
Ramalho_A._et_al._2025_..pdf		15.31 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Resumo(s)

This work concerns the wire arc directed energy deposition (WA-DED) additive manufacturing process. The objectives were two-fold: (1) observe and understand, through in-operando high-speed meltpool imaging, the causal dynamics of two common WA-DED process instabilities, namely, humping and humping-induced porosity; and (2) leverage the high-speed meltpool imaging data within machine learning algorithms for real-time detection of process instabilities. Humping and humping-induced porosity are leading stochastic causes of poor WA-DED part quality that occur despite extensive optimization of processing conditions. It is therefore essential to understand, detect and control the causal meltpool phenomena linked to these instabilities. Accordingly, we used a high-speed camera to capture the meltpool dynamics of multi-layer depositions of ER90S-G steel parts and meltpool flow behavior related to process instabilities were demarcated and quantified. Next, physically intuitive meltpool morphology signatures were extracted from the imaging data. These signatures were used in a machine learning model trained to autonomously detect process instabilities. This novel process-aware machine learning approach classified onset of instabilities with ∼85 % accuracy (F1-score), outperforming black-box deep learning models (F1-score <66 %). These results pave the way for a physically intuitive process-aware machine learning strategy for monitoring and control of the WA-DED process.

Descrição

Funding Information: AR, TGS and JPO acknowledge the Portuguese Fundação para a Ciência e a Tecnologia (FCT - MCTES) for its financial support via the project UIDB/00667/2020 and UIDP/00667/2020 (UNIDEMI). JPO acknowledges the funding by national funds from FCT - Fundação para a Ciência e a Tecnologia, I.P., in the scope of the projects LA/P/0037/2020, UIDP/50025/2020 and UIDB/50025/2020 of the Associate Laboratory Institute of Nanostructures, Nanomodelling and Nanofabrication – i3N. AR acknowledges FCT - MCTES for funding the PhD grant UI/BD/151018/2021. This activity has received funding from the European Institute of Innovation and Technology (EIT) RawMaterials through the project Smart WAAM: Microstructural Engineering and Integrated Non-Destructive Testing. This body of the European Union receives support from the European Union's Horizon 2020 research and innovation program. Prahalada Rao gratefully acknowledges funding from the following US federal government agencies for nurturing his scholastic research in metal additive manufacturing and smart manufacturing over the last decade through the following awards. National Science Foundation (NSF) via Grant Nos. CMMI-2428305, CMMI-2336449, CMMI-2309483/1752069, OIA-1929172, PFI-TT 2322322/2044710, CMMI-1920245, ECCS-2020246, CMMI-1739696, CMMI-2336449, and CMMI-2428305; US Department of Navy, Naval Surface Warfare Center (NAVAIR, N6833524C0215) and Office of Naval Research (ONR, N00014-21-1-2781); and the National Institute of Standards and Technology (NIST, 70NANB23H029T). Understanding the causal influence of process parameters on part quality and detection of defect formation using in-situ sensing was the major aspect of CMMI-2309483/1752069 (Program Officer: Pranav Soman). The use of machine learning and analytics for process diagnosis in additive manufacturing was funded via ECCS-2020246 (program officer: Richard Nash). Benjamin Bevans was funded through CMMI-2309483/1752069 and PFI-TT 2322322/2044710. Anis Assad and Fernando Deschamps were funded by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001. The foregoing also funded a visiting student scholarship for Anis Assad to work at Virginia Tech under the supervision of Prahalada Rao. Publisher Copyright: © 2025 The Authors

Palavras-chave

Humping Meltpool imaging Porosity Process-aware machine learning Wire arc additive manufacturing (WAAM) Wire arc directed energy deposition General Materials Science Mechanics of Materials Mechanical Engineering