Machine Learning Perspective of Predictive Modelling for Additive Manufacturing

Read full text Summarise with VIRAT
Authors: Jasvinder Singh, Sameer Dev Sharma, Rahul Dev Gupta
Cited by: 0
References: 33

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Additive Manufacturing (AM) has proven to be a revolutionary technique of fabrication in numerous fields because of its salient features of complexity in geometries and customization of components.However, there are many challenges to printing the part with good quality and reliability, which are linked to the phenomenon of component warping and poor surface finish.The growth of digital manufacturing technologies has led to pathways to the utilization of data-driven machine learning (ML) in AM to get the benefits of quality assurance, process enhancement, and intricate system modelling techniques.The present paper discusses about the employment of ML to support AM operations.In this paper, the predictive modelling for AM via ML has been examined in terms of its potential to enhance product quality.The present work has successively underlined the manners of the ML integration as data-driven ML approach for product enhancements.A comprehensive review on predictive modelling techniques has revealed the critical role of ML in highlighting the importance of understanding material characteristics, working conditions and process parameters.Various ML algorithms, including regression models and deep learning frameworks, are evaluated for their efficacy in predicting geometric deviations, mechanical properties like fatigue life, temperature profile, melt pool characteristics, optimization of process parameters, and real-time monitoring to minimize defects.It has been concluded that ML algorithm can be effective for the prediction of AM processes in the metal part fabrication.It has also been summated that modern machine learning algorithms can optimize process parameters and facilitate the analysis of in-process defect detection.In AM processes, machine learning supports professionals in process planning, production planning, assessment, and product quality management.

Fields of Study & Subjects

Additive Manufacturing Materials and Processes Additive Manufacturing and 3D Printing Technologies Machine Learning in Materials Science

Publication details

Journal / source
Advances in engineering research/Advances in Engineering Research
Pages
193–209
Publication date
30 March 2026
Language
EN
Document type
Book chapter