University of Leicester
Browse
Nenchev2022_Article_EvaluatingData-drivenAlgorithm.pdf (1.87 MB)

Evaluating data-driven algorithms for predicting mechanical properties with small datasets: A case study on gear steel hardenability

Download (1.87 MB)
journal contribution
posted on 2022-08-26, 11:16 authored by B. Nenchev, Q. Tao, Z. Dong, C. Panwisawas, H. Li, B. Tao, H. Dong
Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability. The limitations of current data-driven algorithms and empirical models are identified. Challenges in analysing small datasets are discussed, and solution is proposed to handle small datasets with multiple variables. Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity. The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability. Metallurgical-property relationships between chemistry, sample size, and hardness are predicted via two optimized machine learning algorithms: neural networks (NNs) and extreme gradient boosting (XGboost). A comparison is drawn between all algorithms, evaluating their performance based on small data sets. The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.

History

Citation

International Journal of Minerals, Metallurgy and Materials, Volume 29, Number 4, April 2022, Page 836

Author affiliation

School of Engineering

Version

  • VoR (Version of Record)

Published in

International Journal of Minerals, Metallurgy and Materials

Volume

29

Issue

4

Pagination

836 - 847

Publisher

Springer

issn

1674-4799

eissn

1869-103X

Acceptance date

2022-02-11

Copyright date

2022

Available date

2022-04-06

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC