A Deep Learning-Based Method and Apparatus for Parameter Prediction in Natural Graphite Spherical Production Line

Abstract

This application provides a method and apparatus for predicting parameters of a natural graphite spherical production line based on deep learning, relating to the field of deep processing of natural graphite. The method includes: inputting acquired spherical graphite production indicators, the structure of the natural graphite spherical production line, the characteristics of the raw materials used, and corresponding product indicators into a pre-trained spherical production line parameter prediction model to obtain equipment parameters; wherein, the equipment parameters include the set frequencies of each piece of equipment in the material crushing, shaping, grading, and conveying stages of the natural graphite spherical production line; and determining the corresponding equipment rotation speed and equipment flow rate based on the set frequencies. This application can construct an end-to-end neural network model by collecting historical operating parameters and corresponding product indicator data of the production line, transforming the "black box" process of natural graphite spheroidization into a modelable and optimizable regression prediction problem, achieving intelligent recommendation and prediction of key operating parameters, and providing accurate and reliable parameter solutions for the production process.

Images