Machine learning of mechanical properties of steels

Jie Xiong, Tong Yi Zhang, San Qiang Shi

Research output: Journal article publicationJournal articleAcademic researchpeer-review

72 Citations (Scopus)


Knowledge of the mechanical properties of structural materials is essential for their practical applications. In the present work, three-hundred and sixty data samples on four mechanical properties of steels—fatigue strength, tensile strength, fracture strength and hardness—were selected from the Japan National Institute of Material Science database, comprising data on carbon steels and low-alloy steels. Five machine learning algorithms were used to predict the mechanical properties of the materials represented by the three-hundred and sixty data samples, and random forest regression showed the best predictive performance. Feature selection conducted by random forest and symbolic regressions revealed the four most important features that most influence the mechanical properties of steels: the tempering temperature of steel, and the alloying elements of carbon, chromium and molybdenum. Mathematical expressions were generated via symbolic regression, and the expressions explicitly predicted how each of the four mechanical properties varied quantitatively with the four most important features. This study demonstrates the great potential of symbolic regression in the discovery of novel advanced materials.

Original languageEnglish
Pages (from-to)1247-1255
Number of pages9
JournalScience China Technological Sciences
Issue number7
Early online date27 May 2020
Publication statusPublished - 1 Jul 2020


  • fatigue strength
  • materials informatics
  • steel
  • symbolic regression

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)


Dive into the research topics of 'Machine learning of mechanical properties of steels'. Together they form a unique fingerprint.

Cite this