Application of Polynomial Regression to stress-strain curve interpolation to determine the tenacity modulus
This paper presents an analytical solution for calculating the modulus of toughness from the stress-strain curve of materials. This curve is obtained through tests performed with specific testing machines for analyzing the deformation of materials. The modulus of toughness is determined by calculating the area under the stress-strain curve. The analytical method used to fit the curve was polynomial regression, highlighting the use of machine learning techniques to improve the accuracy and efficiency of data processing.
The machine learning model developed in this work was trained using polynomial regression strategies, with a focus on the least squares method. This method is used to determine a polynomial approximation that best fits a data set, seeking to minimize the sum of the squares of the differences between the observed values (real data) and the values predicted by the model.
The data used to train the model were obtained from test conducted on polymers, following the ASTM D638 standard.