scholarly journals High-throughput Map Design of Creep Life in Low-Alloy Steels by Integrating Machine Learning with a Genetic Algorithm

2021 ◽  
pp. 110326
Author(s):  
Chenchong Wang ◽  
Xiaolu Wei ◽  
Da Ren ◽  
Xu Wang ◽  
Wei Xu
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
High Throughput ◽  
Low Alloy Steels ◽  
Creep Life ◽  
Map Design ◽  
Alloy Steels

scholarly journals Application of Machine Learning Algorithms and SHAP for Prediction and Feature Analysis of Tempered Martensite Hardness in Low-Alloy Steels

Metals ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1159
Author(s):  
Junhyub Jeon ◽  
Namhyuk Seo ◽  
Seung Bae Son ◽  
Seok-Jae Lee ◽  
Minsu Jung
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Relevant Literature ◽  
Machine Learning Algorithms ◽  
Holding Time ◽  
Low Alloy Steels ◽  
Tempered Martensite ◽  
Tempering Temperature ◽  
Target Values ◽  
Alloy Steels

The tempering of low-alloy steels is important for controlling the mechanical properties required for industrial fields. Several studies have investigated the relationships between the input and target values of materials using machine learning algorithms. The limitation of machine learning algorithms is that the mechanism of how the input values affect the output has yet to be confirmed despite numerous case studies. To address this issue, we trained four machine learning algorithms to control the hardness of low-alloy steels under various tempering conditions. The models were trained using the tempering temperature, holding time, and composition of the alloy as the inputs. The input data were drawn from a database of more than 1900 experimental datasets for low-alloy steels created from the relevant literature. We selected the random forest regression (RFR) model to analyze its mechanism and the importance of the input values using Shapley additive explanations (SHAP). The prediction accuracy of the RFR for the tempered martensite hardness was better than that of the empirical equation. The tempering temperature is the most important feature for controlling the hardness, followed by the C content, the holding time, and the Cr, Si, Mn, Mo, and Ni contents.

Effects of cooling rate on the mechanical properties of dual phase treated vanadium steels

1983 ◽  
Vol 41 ◽  
pp. 220-221
Author(s):  
L.J. Chen ◽  
H.C. Cheng ◽  
J.R. Gong ◽  
J.G. Yang
Keyword(s):  
Mechanical Properties ◽  
Cooling Rate ◽  
Automobile Industry ◽  
High Strength ◽  
Weight Percent ◽  
Low Alloy Steels ◽  
Dual Phase ◽  
Resource Requirement ◽  
Alloy Steels ◽  
Potential Weight

For fuel savings as well as energy and resource requirement, high strength low alloy steels (HSLA) are of particular interest to automobile industry because of the potential weight reduction which can be achieved by using thinner section of these steels to carry the same load and thus to improve the fuel mileage. Dual phase treatment has been utilized to obtain superior strength and ductility combinations compared to the HSLA of identical composition. Recently, cooling rate following heat treatment was found to be important to the tensile properties of the dual phase steels. In this paper, we report the results of the investigation of cooling rate on the microstructures and mechanical properties of several vanadium HSLA steels.The steels with composition (in weight percent) listed below were supplied by China Steel Corporation: 1. low V steel (0.11C, 0.65Si, 1.63Mn, 0.015P, 0.008S, 0.084Aℓ, 0.004V), 2. 0.059V steel (0.13C, 0.62S1, 1.59Mn, 0.012P, 0.008S, 0.065Aℓ, 0.059V), 3. 0.10V steel (0.11C, 0.58Si, 1.58Mn, 0.017P, 0.008S, 0.068Aℓ, 0.10V).

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

Sign in / Sign up

Export Citation Format

Share Document