Proceedings of the International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)

International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)

📍Gorakhpur, IndiađŸ—“ïž 12-13 March 2026
<Previous Article In Volume
Next Article In Volume>

A Variational Autoencoder Framework for the Inverse Design of High-Temperature Alloys

Authors
Shruti Sivakumar1, Shreya Sriram1, S. Vida Nadheera1, Kritesh Kumar Gupta1, *
1Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, India
*Corresponding author. Email: g_kriteshkumar@cb.amrita.edu
Corresponding Author
Kritesh Kumar Gupta
Available Online 31 August 2026.
DOI
10.2991/978-94-6239-750-7_59How to use a DOI?
Keywords
High-entropy alloys; conditional VAE; inverse design; machine learning; materials informatics; yield strength
Abstract

This study proposes a deep learning approach based on a conditional variational autoencoder (CVAE) for inverse design of Refractory High Entropy Alloys (RHEAs). The recommended model helps investigate a wide composition space by generating alloy compositions to obtain a desired yield strength at a certain operating temperature. The model has a coefficient of determination (R2) of 0.99 and a mean absolute error (MAE) of 19 MPa when trained on experimental data for 122 different alloys and 340 composition-temperature combinations from room temperature (RT, 25 ℃) to 1600 ℃. The examination of the latent space uncovers gradual yield-strength gradients and systematic compositional arrangement. Explainability study identifies tantalum, aluminum, chromium, Young’s modulus, and testing methods as significant factors in predicting yield strength. The produced alloy candidates maintain statistically significant composition–property correlations while adhering to established performance criteria, illustrating the appropriateness of the suggested methodology for transparent and temperature-sensitive inverse alloy design.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)
Series
Atlantis Highlights in Engineering
Publication Date
31 August 2026
ISBN
978-94-6239-750-7
ISSN
2589-4943
DOI
10.2991/978-94-6239-750-7_59How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Shruti Sivakumar
AU  - Shreya Sriram
AU  - S. Vida Nadheera
AU  - Kritesh Kumar Gupta
PY  - 2026
DA  - 2026/08/31
TI  - A Variational Autoencoder Framework for the Inverse Design of High-Temperature Alloys
BT  - Proceedings of the International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)
PB  - Atlantis Press
SP  - 821
EP  - 833
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-750-7_59
DO  - 10.2991/978-94-6239-750-7_59
ID  - Sivakumar2026
ER  -