The Input Material Flow Model of the Transport Conveyor

Abstract

This paper discusses the problem of forming a data set for training a neural network used to build a model of a multi-section conveyor. The analysis of the models, which are used by designing the flow parameters control system of the transport system, is given. The conditions of applying a neural network in the transport conveyer model are justified and determined. Methods for generating a data set for training a neural network are discussed. As the main approach, the use of production data obtained from functioning transport conveyors is considered. Statistically processed data can be used to build generators of stochastic processes that model the incoming material flow for the transport system. The development of these generators to form the input flow of the material of the transport system opens up the possibility of analyzing and monitoring conveyor models in various modes of its configuration. A statistical analysis of the incoming material flow of the transport system was carried out and its number characteristics were determined. The correlation function characterizing the input flow of material for the transport system is considered. The introduction of dimensionless parameters to describe the input material flow made it possible to scale the results of work for a wide class of conveyor-type transport systems.