Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Prediction and Analysis of Mechanical Properties of Low Carbon Steels Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-5153-4449
The mechanical properties such as yield strength and elongation of steels directly depended on the compositions and thermodynamic properties. Generally, experimental approaches are used to understand the mechanical properties of any alloys. Hence there is a need for an automated prediction model, which could be helpful evaluate the same without experimental processes. In recent trends, mathematical modeling is gaining popularity in materials science. In this paper, a machine intelligence-based model has been proposed to predict the mechanical properties such as yield strength and elongation for selected steels produced by various thermomechanical processes. A wide range of data is used, which has been generated by hot rolled, cold drawn, annealed, and spheroidized annealed processes are used to develop the proposed model. The outcomes of the proposed model are examined by evaluating the root-mean-square error, and the goodness of the model is discussed with the help of the coefficient of determination, i.e., R2 and the 99.95% and 99.05% R2 values has been achieved for yield strength and elongation prediction, respectively, for 129 various data samples.
Prediction and Analysis of Mechanical Properties of Low Carbon Steels Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-5153-4449
The mechanical properties such as yield strength and elongation of steels directly depended on the compositions and thermodynamic properties. Generally, experimental approaches are used to understand the mechanical properties of any alloys. Hence there is a need for an automated prediction model, which could be helpful evaluate the same without experimental processes. In recent trends, mathematical modeling is gaining popularity in materials science. In this paper, a machine intelligence-based model has been proposed to predict the mechanical properties such as yield strength and elongation for selected steels produced by various thermomechanical processes. A wide range of data is used, which has been generated by hot rolled, cold drawn, annealed, and spheroidized annealed processes are used to develop the proposed model. The outcomes of the proposed model are examined by evaluating the root-mean-square error, and the goodness of the model is discussed with the help of the coefficient of determination, i.e., R2 and the 99.95% and 99.05% R2 values has been achieved for yield strength and elongation prediction, respectively, for 129 various data samples.
Prediction and Analysis of Mechanical Properties of Low Carbon Steels Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-5153-4449
The mechanical properties such as yield strength and elongation of steels directly depended on the compositions and thermodynamic properties. Generally, experimental approaches are used to understand the mechanical properties of any alloys. Hence there is a need for an automated prediction model, which could be helpful evaluate the same without experimental processes. In recent trends, mathematical modeling is gaining popularity in materials science. In this paper, a machine intelligence-based model has been proposed to predict the mechanical properties such as yield strength and elongation for selected steels produced by various thermomechanical processes. A wide range of data is used, which has been generated by hot rolled, cold drawn, annealed, and spheroidized annealed processes are used to develop the proposed model. The outcomes of the proposed model are examined by evaluating the root-mean-square error, and the goodness of the model is discussed with the help of the coefficient of determination, i.e., R2 and the 99.95% and 99.05% R2 values has been achieved for yield strength and elongation prediction, respectively, for 129 various data samples.
Prediction and Analysis of Mechanical Properties of Low Carbon Steels Using Machine Learning
J. Inst. Eng. India Ser. D
Choudhury, Amitava (Autor:in)
Journal of The Institution of Engineers (India): Series D ; 103 ; 303-310
01.06.2022
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
| British Library Online Contents | 2019
Prediction of mechanical properties of carbon fiber based on cross-scale FEM and machine learning
| British Library Online Contents | 2019
Prediction of mechanical properties of carbon fiber based on cross-scale FEM and machine learning
| British Library Online Contents | 2019
Mechanical properties of two ultrahigh carbon-boron tool steels
| British Library Online Contents | 1995