What question did this study set out to answer?

The research aims to evaluate the effectiveness of DSC curves in predicting mechanical properties of aluminum alloys.

May 31, 2026Materials & Design0 citationsOpen Access

DSC curve fingerprints directly encode mechanical properties of aluminum alloys

LPLukas Pichlmann SSSamuel Studer AAAurel R. Arnoldt

Key Points

The research aims to evaluate the effectiveness of DSC curves in predicting mechanical properties of aluminum alloys.
Utilized full thermograms as input for machine learning models.
Compared linear models to Random Forest and Gradient Boosting algorithms.
Analyzed predictive feature importance in the β” precipitation region (230–270°C).
Linear models match or outperform Random Forest and Gradient Boosting in predictive accuracy.
The β” precipitation region significantly influences predictive feature importance.
DSC shows potential as a rapid proxy for tensile testing in screening aluminum alloys.

Abstract

• Full thermogram outperforms hand-crafted DSC features as ML model input. • Linear models match or outperform Random Forest and Gradient Boosting. • β” precipitation region (230–270°C) dominates predictive feature importance. • Cross-alloy transfer achieved with as few as one anchor condition. • DSC established as rapid proxy replacing tensile testing for alloy screening.

Ask AI

Helpful

Bookmark

View Full Paper