Assessing the implementation of machine learning models for thermal treatments design
Open Access
- 1 November 2021
- journal article
- research article
- Published by SAGE Publications in Materials Science and Technology
- Vol. 37 (16) , 1302-1310
Abstract
The latest progress in machine learning (ML) algorithms enabled to predict some steel physical properties previously modelled by linear regression (LR), such as the Ms temperature. Authors claimed that the performance given by ML models could improve the one of previous LR models, although they did not include fair comparisons. In this work, a large database was used to train different ML algorithms, whose Ms temperature predictions were compared to the ones of previous literature empirical models. ML methods were proved to require longer computational times and wider knowledge, while leading to similar results. Therefore, we recommend that ML methods are not always considered as the first option when trying to solve easy problems that can be modelled by LR techniques.Keywords
Funding Information
- Ministerio de Ciencia e Innovación (PID2019-109334RB-C31)
- Ministerio de Economía y Competitividad (BES-2017-080945)
- Research Fund for Coal and Steel (RFCS-2019-899251)
- Research Fund for Coal and Steel (RFCS-2019- 899268)
This publication has 30 references indexed in Scilit:
- Thermodynamically Based Prediction of the Martensite Start Temperature for Commercial SteelsMetallurgical and Materials Transactions A, 2012
- Neural Networks and Information in Materials ScienceStatistical Analysis and Data Mining: An ASA Data Science Journal, 2009
- Artificial neural network modeling for the prediction of critical transformation temperatures in steelsJournal of Materials Science, 2007
- Critical assessment of models for predicting the Ms temperature of steelsComputational Materials Science, 2005
- A model for predicting the Ms temperatures of steelsComputational Materials Science, 2005
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Kinetics of F.c.c. → b.c.c. heterogeneous martensitic nucleation—II. Thermal activationActa Metallurgica et Materialia, 1994
- Kinetics of F.C.C. → B.C.C. heterogeneous martensitic nucleation—I. The critical driving force for athermal nucleationActa Metallurgica et Materialia, 1994
- Learning representations by back-propagating errorsNature, 1986
- An examination of the validity of existing empirical formulae for the calculation of ms temperatureMetallurgical Transactions A, 1982