Determining the Rheological Parameters of Polymers Using Machine Learning Techniques

Abstract

Introduction. The paper investigates the methodology for determining the rheological parameters of materials based on the nonlinear Maxwell-Gurevich rheological model using the stress relaxation curves. The review of the main directions of the metaheuristic approaches (local search, evolutionary algorithms) to solving the combinatorial optimization problems is presented. The metaheuristic algorithms for solving some important combinatorial optimization problems with the special emphasis on building decision trees are described. The comparative analysis of the algorithms for solving the regression problem in CatBoost Regressor is carried out. The aim of the work is to determine the rheological properties of polymers using machine learning techniques.Materials and Methods. The objects of the study are the generated data sets obtained on the basis of the theoretical stress relaxation curves. The source data tables for model training across all samples are presented, and the statistical analysis of the source data sets characteristics is carried out. The total number of numerical experiments across all samples amounted to 346020 variations. To develop the models, the CatBoost artificial intelligence techniques were used; the regularization techniques (Weight Decay, Decoupled Weight Decay Regulation, Augmentation) were used to increase the model accuracy; and Z–Score technique was used for data normalization.Results. As a result of the research, the intelligent models for determining the rheological parameters of polymers (initial relaxation viscosity, velocity modulus) have been developed based on the generated data sets on the example of the epoxy binder EDT-10. Based on the testing results of the models with the best parameters, the quality assessments were carried out: for the parameter 𝜂∗0 the range of values MAPE 0.46 — 2.72, MSE 0.15 — 1.09, RMSE 0.19 —  0.44, MAPE 0.46 — 1.27; for the parameter 𝑚∗ — MAPE 0.07 — 0.32, MSE 0.01 —  0.13, RMSE 0.10 — 0.41, MAPE 0.58 — 2.72. The resulting metric values are permissible. The training graphs demonstrate the stability of the process.Discussion and Conclusion. The developed intelligent models are scalable and cross-platform, have practical applied significance that ensures their implementation in a wide range of the scientific and engineering apps.