Authors: Muhammad Muteeb Butt, Sidra Rashid, Mehmood ul Haq, Ayyaz Mustafa, Arshad Iqbal, Hossein Laieghi, Varma KVVSSN, Metin U. Salamci, Enrico Salvati, Hüseyin Kızıl
Overview
Selective laser melting (SLM) can produce high-performance Ti6Al4V parts, but finding the process parameters that deliver the required mechanical properties usually takes costly trial and error.
The study assembles 201 results from published literature, linking six SLM process parameters to three tensile properties: yield strength, ultimate tensile strength and elongation. Six machine learning models are compared with artificial neural networks (ANN), and the best ANN is interpreted with SHAP to connect its predictions to the underlying process physics.
By reverse-training the ANN models, the authors build a graphical user interface that suggests process parameters for a required set of mechanical properties: a practical tool for pre-production evaluation in aerospace and biomedical applications.
Key findings
- Six conventional models (support vector regression, random forest, k-nearest neighbours, gradient boosting, Gaussian process regression and decision tree) reached only moderate accuracy.
- Artificial neural networks captured the relationships best, with R² scores of up to 0.84 across all three properties.
- SHAP analysis shows the relative importance and physical influence of each process parameter.
- A GUI built by reverse-training the ANNs recommends process parameters for target mechanical properties.
This is our summary of the paper. The full text, with its abstract, figures and data, is on the publisher's site.
Details
- Journal
- International Journal of Precision Engineering and Manufacturing
- Published
- 17 Oct 2025
- Volume
- 27, issue 1
- Pages
- 329–348
- DOI
- 10.1007/s12541-025-01360-0
Topics
Cite
Muhammad Muteeb Butt, Sidra Rashid, Mehmood ul Haq, Ayyaz Mustafa, Arshad Iqbal, Hossein Laieghi, Varma KVVSSN, Metin U. Salamci, Enrico Salvati, Hüseyin Kızıl (2025). Machine Learning Driven Prediction and GUI Based Optimization of Quasi-Static Mechanical Properties in SLM Fabricated Ti6Al4V Alloy. International Journal of Precision Engineering and Manufacturing, 27(1), 329–348. https://doi.org/10.1007/s12541-025-01360-0










