DEVELOPMENT OF AN AUTOMATED SYSTEM FOR INPUT TESTING AND DIAGNOSTICS OF CU/TI RODS

Abstract

The article presents the results of the development and testing of an automatic installation designed to diagnose (classify) defects of Cu/Ti rods (electrodes) widely used as current conductors in electroplating and chemical production. It is shown that the introduction of such an installation using one of the methods of non-destructive testing allows, on average, to reduce the diagnostic time by an order of magnitude compared to the option if the necessary actions were performed manually. To create an automated system based on the installation, modern electromechanical, electronic and computing tools have been used, which allow almost completely automating the diagnostic process from taking the necessary measurements, filtering data, displaying them in the form of graphs and tables, as well as classifying defects at the last stage using a neural network. According to the tests carried out, it was shown that the classification accuracy was at least 93 %.