Hybrid Machine Learning Optimization Approach to Predict Hot Deformation Behavior of Medium Carbon Steel Material

Abstract

The isothermal tensile test of medium carbon steel material was conducted at deformation temperatures varying from 650 to 950 ∘ C with an interval of 100 ∘ C and strain rates ranging from 0.05 to 1.0 s − 1 . In addition, the scanning electron microscopy (SEM) procedures were exploited to study about the surface morphology of medium carbon steel material. Using the experimental data, the artificial neural network (ANN) model with a back-propagation (BP) algorithm was proposed to predict the hot deformation behavior of medium carbon steel material. For model training and testing purpose, the variables such as deformation temperature, strain rate, and strain data were considered as inputs and the flow stress data were used as targets. Before running the neural network, the test data were normalized to effectively run the problem and after solving the problem, the obtained results were again converted in order to achieve the actual data. According to the predicted results, the coefficient of determination ( R 2 ) and the average absolute relative error between the predicted flow stress and the experimental data were determined as 0.999 and 1.335%, respectively. For improving the model predictability, the constrained nonlinear function based optimization procedures was adopted to obtain the best candidate selections of weights and biases. By evaluating each test conditions, it was found that the average absolute relative error based on the optimized ANN-BP model varied from 0.728% to 1.775%. Overall, the trained ANN-BP models proved to be much more efficient and accurate by means of flow stress prediction against the experimental data for all the tested conditions. These optimized results displayed that an ANN-BP model is more accurate for flow stress prediction than that of the conventional flow stress models.

Formability and Failure Evaluation of AA3003-H18 Sheets in Single-Point Incremental Forming Process through the Design of Experiments

“…Mathematical assessments such as the coefficient of determination ( ), adjusted , root mean square error (RMSE), and average absolute relative error (AARE) are widely used for verifying the adequacy of the proposed regression model [ 44 , 45 , 46 , 47 ].…”

“…The most common parameter used to determine a regression model’s adequacy is , which is the square of the correlation coefficient between the actual and the predicted data. This parameter indicates the association between any two quantitative variables by explaining the amount of variation appearing in the data; the greater the value, the higher the quality of fit [ 44 , 45 , 46 , 47 ]. where = and = ; and are the error sum of squares and the total corrected sum of squares, respectively.…”

“…Adjusted is the altered form of , which has been modified based on the number of independent variables in the regression model. This quantity is always smaller than because it improves only when a new regressor variable is included in the regression model [ 44 , 45 , 46 , 47 ]. …”

“…RMSE reveals how the residuals are presented in the designed space. It is often used to estimate the difference between the actual and the predicted data; e.g., if RMSE is near to 0, the calculated data are scattered adjacent to the regression line, and vice versa [ 44 , 45 , 46 , 47 ]. …”

Prediction and Analysis of Tensile Properties of Austenitic Stainless Steel Using Artificial Neural Network

“…Nowadays, machine learning prompts data science and analytics to become a significant tool to find the desired causal relations in the material research [11], and results in developing a new field termed as "Materials Informatics" [12,13] in recent years. Machine learning has been rapidly used in the fields of metals [14][15][16][17][18], as well as polymers [19], semiconductors [20,21], which fully demonstrates its powerful universality.…”