An ore sorting method based on a convolutional neural network

A convolutional neural network and ore technology, applied in the field of sorting, can solve problems such as low accuracy and low efficiency, and achieve the effects of improving accuracy, improving economic benefits, and improving accuracy

CN109740656AInactive Publication Date: 2019-05-10HUAQIAO UNIVERSITY
7 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2019-05-10
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides an ore sorting method based on a convolutional neural network. The method comprises the following steps: making a training set and a test set of ore pictures; building VGG-SE model for inputting the ore pictures in the training set into the VGG-SE model and using VGG-SE model to carry out feature extraction on the ore picture to obtain a group of feature vectors; inputting agroup of obtained feature vectors into a softmax classifier, and classifying the ore pictures through the softmax classifier to obtain a trained VGG-SE model; inputting ore pictures in a test set toa trained VGG-SE modle to perform prediction to obtain a prediction result. The method has the advantages that compared with existing manual classification, machine classification is used for replacing manual classification, the classification accuracy is greatly improved, and meanwhile economic benefits are improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a sorting method, in particular to an ore sorting method based on a convolutional neural network. Background technique

[0002] Mineral resources are non-renewable resources. With the massive development of mineral resources, mineral resources are gradually decreasing. This makes the mining industry begin to pay attention to the sorting of ores, which can ensure the utilization of high-quality mineral resources as much as possible in the limited mineral resources. But for now, the sorting of ores mainly relies on manual sorting. Due to the influence of human subjective factors, human eyes are prone to fatigue and other reasons, the sorting rate of ores has always been relatively low, which also directly affects economic benefits.

[0003] With the continuous advancement of science and technology, the use of artificial intelligence to solve practical industrial problems has begun to appear widely in recent years. As a branch o...

Examples

Embodiment Construction

[0048] Please refer to Figure 1 to Figure 3 Shown, a kind of preferred embodiment of the ore sorting method based on convolution neural network of the present invention, described method comprises the steps:

[0049] Step S1, making a training set and a test set of ore pictures;

[0050] In a specific embodiment of the present invention, the step S1 specifically includes:

[0051] Step S11. Under the same environment, use the same shooting instrument to shoot the collected ores of different qualities to obtain various ore pictures; in actual implementation, it is necessary to collect as many ore pictures as possible to ensure sufficient data sources. The purpose of shooting in the same environment and with the same shooting equipment is to reduce the interference of the surrounding environment on the ore pictures taken. The shooting instrument can be selected as a gray point color camera of FL3-GE-03S1M-C for shooting, and the pixel size is 1024×1280. Of course, the present...