Ore automatic identification and coarse sorting system based on deep learning

Abstract

The invention discloses an ore automatic identification and coarse sorting system based on deep learning, and the system comprises: a model construction module which is used for constructing a deep learning model of ore automatic identification and coarse sorting; a model training module which is used for forming a training set and a test set according to the pictures of the selected ore mud blockmixture to train a deep learning model for automatic ore identification and coarse sorting; a recognition module which is used for inputting the shot ore and mud block mixture pictures on the crawlerbelt into a trained ore automatic recognition and rough sorting deep learning model to obtain a real-time recognition result; and a sorting module which is used for controlling the crawler belt to feed the batch of ores into the next procedure according to the recognition result of the recognition module if the mud content after recognition is smaller than a set threshold value, otherwise, controlling the high-pressure water gun to perform fixed-point flushing on the recognized mud blocks, and then feeding the mud blocks into the next procedure. According to the invention, deep learning is creatively introduced into the ore sorting process, and full automation of ore coarse sorting is achieved.

Description

technical field [0001] The present invention relates to ore sorting technology, in particular to an ore automatic identification and rough sorting system based on deep learning. Background technique [0002] After the ore is mined, the first process is to crush the ore and mud. After the crushing, several times of ore washing are required. The first two to three times of ore washing are roughed, and the loose mud is washed away with a high-pressure water gun. During the roughing process, it is necessary Manually sort out the mud with strong cohesiveness, otherwise the excessive mud content will not only greatly increase the difficulty of the subsequent process, but even block the mining machine in severe cases, causing property loss and threatening the safety of the staff. Not only that, in the process of ore roughing, there are still problems such as excessive water consumption and low automation and intelligence caused by more manual participation. How to utilize present ...

AI Technical Summary

Problems solved by technology

[0002] After the ore is mined, the first process is to crush the ore and mud. After the crushing, several times of ore washing are required. The first two to three times of ore washing are roughed, and the loose mud is washed away with a high-pressure water gun. During the roughing process, it is necessary Manually sort out the mud with strong cohesiveness, otherwise the mud content will be too much, which will not only greatly increase the difficulty of the subsequent process, but even block the mining machine in serious cases, causing property loss and threatening the safety of the staff

Not only that, but in the process of ore roughing, there are still problems such as excessive consumption of water resources and low degree of automation and intelligence caused by more manual participation.

Images