The Use of Neural Networks for the Technological Objects Recognition Tasks in Computer-Integrated Manufacturing

Abstract

This work is devoted to the actual topic of neural networks using for the technological objects recognition tasks in computer-integrated manufacturing. In the work, a study for the transport technological objects recognition using a neural network was carried out. This study contains a neural network without and with the convolutional layers usage in architecture, as well as experiments on neural networks training depends on the number of iterations. The practical implementation of this work is the possibility of the developed software usage on portable mobile devices, as well as training on remote servers, which makes it possible to use this software even on devices with minimal technical requirements.