The use of artificial neural networks for determining the parameters of laser processing of fused quartz

Abstract

This paper provides the simulation of the laser splitting process of fused quartz using artificial neural networks. The calculations of temperatures and thermoelastic stresses were performed by the finite element method in the ANSYS program to create a training data array and an array data for testing neural networks. The paper studies the influence of neural network architecture, the size of the training data array, and the training time on the accuracy of determining thermoelastic stresses and temperatures in the zone of laser processing of quartz sol-gel glass.