Increase the operational reliability of the electric drive of the weaving machine

Abstract

The main purpose of this research work is to analyze malfunctions, power consumption, engine overheating and vibrations based on the loadings of electrical circuits through artificial neural networks. The reliability of artificial intelligence systems was proven on the basis of a model-based system depending on the task, and the obtained values were experimentally compared in the electrical operation of existing equipment in general industrial enterprises. An imitation model of the real object was developed. A concept of increasing productivity was set up to identify malfunctions, in contrast to the existing annular method. The article developed an algorithm for increasing the operational reliability of the electrical operation of the weaving machine on the basis of integrated indicators of excitation to determine the probability of failure of electrical operation. The article proposes the possibility of directly processing the diagnostic energy parameters through artificial neural networks. An experimental combination of signals resulted in a model based on input power and torque, and was based on an asynchronous motorized electrical circuit. It has been proven that intellectual reliability can be increased by 3-5% compared to operational reliability in traditional methods.