Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties
The as-rolled mechanical properties of microalloyed steels result from their chemical composition and thermomechanical processing history. Accurate predictions of the mechanical properties would reduce the need for expensive and time-consuming testing. At the same time, understanding the interplay b...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827024000070 |
| _version_ | 1797311497990307840 |
|---|---|
| author | Sushant Sinha Denzel Guye Xiaoping Ma Kashif Rehman Stephen Yue Narges Armanfard |
| author_facet | Sushant Sinha Denzel Guye Xiaoping Ma Kashif Rehman Stephen Yue Narges Armanfard |
| author_sort | Sushant Sinha |
| collection | DOAJ |
| description | The as-rolled mechanical properties of microalloyed steels result from their chemical composition and thermomechanical processing history. Accurate predictions of the mechanical properties would reduce the need for expensive and time-consuming testing. At the same time, understanding the interplay between process variables and alloy composition will help reduce product variability and facilitate future alloy design. This paper provides an artificial neural network methodology to predict lower yield strength (LYS) and ultimate tensile strength (UTS). The proposed method uses feature engineering to transform raw data into features typically used in physical metallurgy to better utilize the artificial neural network model in understanding the process. SHAP values are used to reveal the effect of thermomechanical controlled processing, which can be rationalized by physical metallurgy theory. |
| first_indexed | 2024-03-08T02:00:36Z |
| format | Article |
| id | doaj.art-2ff2fe94ef6a4bd58b9ed5bdeefcb077 |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-03-08T02:00:36Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-2ff2fe94ef6a4bd58b9ed5bdeefcb0772024-02-14T05:19:09ZengElsevierMachine Learning with Applications2666-82702024-03-0115100531Neural network prediction of the effect of thermomechanical controlled processing on mechanical propertiesSushant Sinha0Denzel Guye1Xiaoping Ma2Kashif Rehman3Stephen Yue4Narges Armanfard5Department of Mining and Materials Engineering, McGill University, 3610 Rue University, Montréal, H3A 0C5, Quebec, Canada; Corresponding author.Department of Mining and Materials Engineering, McGill University, 3610 Rue University, Montréal, H3A 0C5, Quebec, CanadaAlgoma Steel Inc., 105 West Street, Sault Ste. Marie, P6A 7B4, Ontario, CanadaAlgoma Steel Inc., 105 West Street, Sault Ste. Marie, P6A 7B4, Ontario, CanadaDepartment of Mining and Materials Engineering, McGill University, 3610 Rue University, Montréal, H3A 0C5, Quebec, CanadaDepartment of Electrical and Computer Engineering, McGill University, 3480 rue University, Montréal, H3A 0E9, Quebec, Canada; Mila - Quebec AI Institute, 6666 St Urbain St, Montréal, H2S 3H1, Quebec, CanadaThe as-rolled mechanical properties of microalloyed steels result from their chemical composition and thermomechanical processing history. Accurate predictions of the mechanical properties would reduce the need for expensive and time-consuming testing. At the same time, understanding the interplay between process variables and alloy composition will help reduce product variability and facilitate future alloy design. This paper provides an artificial neural network methodology to predict lower yield strength (LYS) and ultimate tensile strength (UTS). The proposed method uses feature engineering to transform raw data into features typically used in physical metallurgy to better utilize the artificial neural network model in understanding the process. SHAP values are used to reveal the effect of thermomechanical controlled processing, which can be rationalized by physical metallurgy theory.http://www.sciencedirect.com/science/article/pii/S2666827024000070Machine learningMechanical propertiesMicroalloyed steelThermomechanical controlled processing |
| spellingShingle | Sushant Sinha Denzel Guye Xiaoping Ma Kashif Rehman Stephen Yue Narges Armanfard Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties Machine Learning with Applications Machine learning Mechanical properties Microalloyed steel Thermomechanical controlled processing |
| title | Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| title_full | Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| title_fullStr | Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| title_full_unstemmed | Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| title_short | Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| title_sort | neural network prediction of the effect of thermomechanical controlled processing on mechanical properties |
| topic | Machine learning Mechanical properties Microalloyed steel Thermomechanical controlled processing |
| url | http://www.sciencedirect.com/science/article/pii/S2666827024000070 |
| work_keys_str_mv | AT sushantsinha neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties AT denzelguye neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties AT xiaopingma neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties AT kashifrehman neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties AT stephenyue neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties AT nargesarmanfard neuralnetworkpredictionoftheeffectofthermomechanicalcontrolledprocessingonmechanicalproperties |