AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (6.5 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Paper | Open Access

Interpretable machine learning integrated with physicochemical feature for developing additively manufactured ultra-high strength and ductility steel

Yating Luo1, Tao Zhu2 , Cunliang Pan1 , Xu Ben1, Xudong An1 , Xiaoming Wang3, Hongmei Zhu1 ( )
Key Laboratory of Hunan Province of Equipment Safety Service Technology under Extreme Environment, University of South China, Hengyang 421001, People’s Republic of China
School of Computer, University of South China, Hengyang 421001, People’s Republic of China
School of Engineering Technology, Purdue University, West Lafayette, IN 47907, United States of America
Show Author Information

Abstract

The multi-component complexity of ultra-high strength and ductility steels (UHSDS) imposes significant challenges for physical metallurgy-guided machine learning (ML) and CALPHAD-combined ML optimization design. Currently, the reported additively manufactured UHSDS necessitate multi-step heat treatments and expensive alloying elements while exhibiting poor corrosion resistance. In this study, a physicochemical feature-integrated, interpretable ML strategy was employed to design multi-component UHSDS fabricated via laser-directed energy deposition (LDED). SHapley additive exPlanation (SHAP) analysis was performed to reveal the critical intrinsic factors and their effects on the tensile mechanical performance, including ultimate tensile strength (UTS), yield strength (YS), and elongation (EL). Accordingly, the candidate alloying elements were identified, and a simple single-step tempering heat treatment was adopted, enabling the synchronous enhancement of strength and ductility. As a consequence, we designed a novel cost-effective and short-process LDEDed Fe-15Cr-3.2Ni-0.8Mn-0.6Cu-0.56Si-0.4Al-0.16C UHSDS, followed by tempering at 480 ℃ for 6 h. The as-tempered specimen mainly consisted of lath martensite, together with some austenite, carbides and nano-precipitates (AlN, NiAl, and ɛ-Cu). Both striking mechanical properties (i.e., UTS: (1713 ± 17) MPa, YS: (1502 ± 33) MPa, EL: (15.5 ± 0.7)%) and excellent corrosion resistance, with a corrosion rate of 0.105 mm·a−1, have been achieved, superior to the reported additively manufactured UHSDS. The ultra-high strength and ductility are attributed to solid–solution strengthening, precipitate strengthening and transformation-induced plasticity (TRIP) effects. This work will be of great significance to provide new insights into the development of low-cost and process-simplified UHSDS, especially for the laser fabrication of high-value-added steel components with excellent comprehensive performance.

References

【1】
【1】
 
 
International Journal of Extreme Manufacturing

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Luo Y, Zhu T, Pan C, et al. Interpretable machine learning integrated with physicochemical feature for developing additively manufactured ultra-high strength and ductility steel. International Journal of Extreme Manufacturing, 2026, 8(4). https://doi.org/10.1088/2631-7990/ae5006

8

Views

0

Downloads

0

Crossref

0

Web of Science

3

Scopus

0

CSCD

Received: 19 September 2025
Revised: 04 December 2025
Accepted: 09 March 2026
Published: 31 March 2026
© 2026 The Author(s).

Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.