Current Applications of Machine Learning in Additive Manufacturing: A Review on Challenges and Future Trends

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27230%2F24%3A10256517" target="_blank" >RIV/61989100:27230/24:10256517 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s11831-024-10215-2#citeas" target="_blank" >https://link.springer.com/article/10.1007/s11831-024-10215-2#citeas</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11831-024-10215-2" target="_blank" >10.1007/s11831-024-10215-2</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Current Applications of Machine Learning in Additive Manufacturing: A Review on Challenges and Future Trends

Popis výsledku v původním jazyce

The article provides a detailed review of the utilisation of machine learning (ML) in various domains of additive manufacturing (AM) and highlights its potential to address key challenges in the industry. The article acknowledges the hurdles to widespread adoption of AM, including barriers in design for AM (DfAM), limited materials selection, processing defects, and inconsistent product quality. ML is increasingly being integrated into AM workflows, offering significant potential for classification, regression, and clustering to address the AM challenges. It can be used to generate new high-performance metamaterials and optimize topological designs, improving the efficacy and usefulness of the design process. It also optimizes process parameters, monitors powder spreading, and detects in-process defects, enhancing the overall quality and reliability of the manufacturing process. ML aids in streamlining the production processes and ensuring consistent product quality. There&apos;s recognition of the importance of data security in AM, with ML techniques potentially posing risks of data breaches if not properly managed. Therefore, a synergistic approach where ML assists in identifying critical conditions and human operators take action is likely the most effective way to ensure both efficiency and accuracy in AM processes. The paper summarises the key results from the literature and discusses some significant applications of machine learning in AM. It emphasizes the potential of ML to drive innovation and address critical challenges in the AM industry. Overall, the article underscores the significance of ML in advancing AM technology and its potential to overcome existing barriers to adoption, making way for broader implementation of AM in various industries. (C) The Author(s) under exclusive licence to International Center for Numerical Methods in Engineering (CIMNE) 2024.

Název v anglickém jazyce

Current Applications of Machine Learning in Additive Manufacturing: A Review on Challenges and Future Trends

Popis výsledku anglicky

The article provides a detailed review of the utilisation of machine learning (ML) in various domains of additive manufacturing (AM) and highlights its potential to address key challenges in the industry. The article acknowledges the hurdles to widespread adoption of AM, including barriers in design for AM (DfAM), limited materials selection, processing defects, and inconsistent product quality. ML is increasingly being integrated into AM workflows, offering significant potential for classification, regression, and clustering to address the AM challenges. It can be used to generate new high-performance metamaterials and optimize topological designs, improving the efficacy and usefulness of the design process. It also optimizes process parameters, monitors powder spreading, and detects in-process defects, enhancing the overall quality and reliability of the manufacturing process. ML aids in streamlining the production processes and ensuring consistent product quality. There&apos;s recognition of the importance of data security in AM, with ML techniques potentially posing risks of data breaches if not properly managed. Therefore, a synergistic approach where ML assists in identifying critical conditions and human operators take action is likely the most effective way to ensure both efficiency and accuracy in AM processes. The paper summarises the key results from the literature and discusses some significant applications of machine learning in AM. It emphasizes the potential of ML to drive innovation and address critical challenges in the AM industry. Overall, the article underscores the significance of ML in advancing AM technology and its potential to overcome existing barriers to adoption, making way for broader implementation of AM in various industries. (C) The Author(s) under exclusive licence to International Center for Numerical Methods in Engineering (CIMNE) 2024.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

—

Návaznosti

O - Projekt operacniho programu

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Archives of Computational Methods in Engineering

ISSN

1134-3060

e-ISSN

—

Svazek periodika

2024

Číslo periodika v rámci svazku

December

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

34

Strana od-do

—

Kód UT WoS článku

001383454000001

EID výsledku v databázi Scopus

2-s2.0-85213342730