Abstract
The designs of screw conveyors contain safety clutches that ensure the avoidance of breakdowns in emergencies (e.g., when the auger is jammed). Therefore, the choice of these clutches is a relevant scientific problem, which is related to the calculation of the maximum torque of the auger. The purpose of this study was to develop a method for calculating the maximum torque when the auger of a screw conveyor is jammed. The method developed in this paper article is based on the use of an artificial neural network trained using the “learning with a teacher” technology. The training and test data set for the artificial neural network was obtained by conducting machine experiments, each of which consisted in the numerical integration of a nonlinear differential equation and the determination of the value of the maximum moment in the elastic connection of the dynamic system based on the obtained solution. The specified differential equation is obtained based on the equation of motion of the non-jammed part of the conveyor (drive, gears, clutch) and the Kloss equation, which corresponds to the model of the mechanical characteristics of the conveyor asynchronous motor. The statistical significance of the results of an artificial neural network was proved by analysing the values of approximation quality indicators. A brief analysis of the influence of the stiffness of the elastic connection of the dynamic conveyor system and the drive gear ratio, as well as the overloading capacity of the engine on the maximum moment that occurs when the screw is jammed, was performed. The practical significance of the results obtained is related to the software implementation of the method, which allows engineers to effectively select safety clutches upon designing screw conveyors.