LET'S CONNECT
Published · 2026 · Materials

Machine learning and physics based empirical equations for fatigue life prediction of AM Ti‑6Al‑4 V

Authors: Muhammad Muteeb Butt, Mehmood ul Haq, Varma KVVSSN, Hossein Laieghi, Hakan Yavas, Metin U Salamci, Hüseyin Kızıl

Overview

Fatigue life decides whether an additively manufactured Ti-6Al-4 V part can be qualified, yet fatigue data are scarce and depend on stress, defects and build orientation all at once. Synthetic data can fill the gap, but whether generated data still behave like the real material is rarely checked.

The study benchmarks several data-augmentation strategies under strict fidelity checks, so the stress–defect–life relationships survive augmentation before any model is trained. On the most reliable strategy, four regression models are compared and the best one is interpreted with SHAP to show which factors drive fatigue life.

Two practical results come out of it: an interactive tool that estimates fatigue life from stress, orientation and defect inputs, and orientation-specific, physics-guided Basquin-type equations that can be used on their own.

Key findings

This is our summary of the paper. The full text, with its abstract, figures and data, is on the publisher's site.

Details

Journal
Progress in Additive Manufacturing
Published
13 Mar 2026
Volume
11, issue 5
Pages
4731–4749
DOI
10.1007/s40964-026-01615-w

Topics

Additive manufacturing
Fatigue life
Defects
Data augmentation
Machine learning
SHAP analysis

Cite

Muhammad Muteeb Butt, Mehmood ul Haq, Varma KVVSSN, Hossein Laieghi, Hakan Yavas, Metin U Salamci, Hüseyin Kızıl (2026). Machine learning and physics based empirical equations for fatigue life prediction of AM Ti-6Al-4 V. Progress in Additive Manufacturing, 11(5), 4731–4749. https://doi.org/10.1007/s40964-026-01615-w

More research

Collaborate with us on research or production AI

Whether you're a company with a problem to solve or a university looking for a research partner, we'd like to hear from you.

Start a conversation