THE USE OF ARTIFICIAL INTELLIGENCE METHODS FOR APPROXIMATION OF THE MECHANICAL BEHAVIOR OF RUBBER-LIKE MATERIALS

Abstract

In the XXI century, neural networks are widely used in various fields, including computer simulation and mechanics. This popularity is due to the fact
that they give high precision, work fast and have a very wide range of settings. The purpose of creating a software product using elements of artificial
intelligence, for interpolation and approximation of experimental data. The software should work correctly, and yield results with minimal error. The
disadvantage of using mathematical approaches to calculating and predicting hysteresis loops is that they describe unloading rather poorly, thus, we
obtain incorrect data for calculating the stress-strain state of a structure. The solution tool use of elements of artificial intelligence, but rather neural
networks of direct distribution. The neural network of direct distribution has been built and trained in this work. It has been trained with a teacher (a
teacher using the method of reverse error propagation) based on a learning sample of a pre-experiment. Several networks of different structures were
built for testing, which received the same dataset that was not used during the training, but was known from the experiment, thus finding a network
error in the amount of allocated energy and in the mean square deviation. The article describes in detail the mathematical interpretation of neural
networks, the method for training them, the previously conducted experiment, structure of network that was used and its topology, the training method,
preparation of the training sample, and the test sample. As a result of the robots carried out, the software was tested in which an artificial neural
network was used, several types of neural networks with different input data and internal structures were built and tested, the error of their work was
determined, the positive and negative sides of the networks that were used were formed.