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

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-i...

Full description

Saved in:
Bibliographic Details
Main Authors: André Ramalho, Anis Assad, Benjamin Bevans, Fernando Deschamps, Telmo G. Santos, J.P. Oliveira, Prahalada Rao
Format: Article
Language:English
Published: Elsevier 2025-10-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127525010184
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226994335612928
author André Ramalho
Anis Assad
Benjamin Bevans
Fernando Deschamps
Telmo G. Santos
J.P. Oliveira
Prahalada Rao
author_facet André Ramalho
Anis Assad
Benjamin Bevans
Fernando Deschamps
Telmo G. Santos
J.P. Oliveira
Prahalada Rao
author_sort André Ramalho
collection DOAJ
description 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.
format Article
id doaj-art-31873e2e7ec149fe87c63feebdd239c7
institution Kabale University
issn 0264-1275
language English
publishDate 2025-10-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj-art-31873e2e7ec149fe87c63feebdd239c72025-08-24T05:11:21ZengElsevierMaterials & Design0264-12752025-10-0125811459810.1016/j.matdes.2025.114598Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learningAndré Ramalho0Anis Assad1Benjamin Bevans2Fernando Deschamps3Telmo G. Santos4J.P. Oliveira5Prahalada Rao6UNIDEMI, Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Universidade NOVA de Lisboa, Caparica 2829-516, Portugal; Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USA; Corresponding author at: UNIDEMI, Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Universidade NOVA de Lisboa, Caparica 2829-516, Portugal.Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USA; University of Southern Denmark, Department of Technology and Innovation, Sønderborg, DenmarkGrado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USA; Sooner Advanced Manufacturing Laboratory, University of Oklahoma, Norman, OK, USAPontifícia Universidade Católica do Paraná, Imaculada Conceição 1155, 80215-901 Curitiba, BrazilUNIDEMI, Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Universidade NOVA de Lisboa, Caparica 2829-516, Portugal; Laboratório Associado de Sistemas Inteligentes, LASI, 4800-058 Guimarães, PortugalCENIMAT/I3N, Department of Materials Science, NOVA School of Science and Technology, Universidade NOVA de Lisboa, Caparica 2829-516, PortugalGrado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USAThis 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.http://www.sciencedirect.com/science/article/pii/S0264127525010184Wire arc directed energy depositionWire arc additive manufacturing (WAAM)PorosityHumpingMeltpool imagingProcess-aware machine learning
spellingShingle André Ramalho
Anis Assad
Benjamin Bevans
Fernando Deschamps
Telmo G. Santos
J.P. Oliveira
Prahalada Rao
Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
Materials & Design
Wire arc directed energy deposition
Wire arc additive manufacturing (WAAM)
Porosity
Humping
Meltpool imaging
Process-aware machine learning
title Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
title_full Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
title_fullStr Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
title_full_unstemmed Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
title_short Understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
title_sort understanding and detection of process instabilities in wire arc directed energy deposition additive manufacturing using meltpool imaging and machine learning
topic Wire arc directed energy deposition
Wire arc additive manufacturing (WAAM)
Porosity
Humping
Meltpool imaging
Process-aware machine learning
url http://www.sciencedirect.com/science/article/pii/S0264127525010184
work_keys_str_mv AT andreramalho understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT anisassad understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT benjaminbevans understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT fernandodeschamps understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT telmogsantos understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT jpoliveira understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning
AT prahaladarao understandinganddetectionofprocessinstabilitiesinwirearcdirectedenergydepositionadditivemanufacturingusingmeltpoolimagingandmachinelearning