Research on Identification Method of Magnetite Ore Based on Convolutional Neural Network

Abstract

Aiming at the low effect and intelligence of traditional pre-concentration methods for screening low-grade magnetite ore, a method based on convolutional neural network (CNN) is proposed. According to the simulation result of COMSOL Multiphysics for magnetite ore, the magnetic induction signals acquisition system is built and the signal acquisition method is designed. The magnetic induction signals of 1200 magnetite ores are collected and converted into two-dimensional signals that CNN is good at processing through sample preparation. The network model is constructed, and the parameters of the model is optimized by orthogonal experiment design. The optimized model is trained and tested based on the experimental data. The results show that the CNN model can effectively extract the magnetic induction signal characteristics of magnetite ore, and the recognition accuracy rate is as high as 87.5 %.