Coal gangue identification method of particle swarm optimization XGBoost algorithm

Abstract

The invention provides a coal gangue identification method based on a particle swarm optimization XGBoost algorithm, and belongs to the field of coal gangue identification; the method comprises the steps: collecting the multispectral image information of coal and gangue, and carrying out the preprocessing; performing sample division on the collected coal and gangue multispectral images, randomly dividing the preprocessed coal and gangue multispectral images into an independent training set and a test set according to a ratio of 7: 3, and setting labels for samples; performing feature extraction on the coal and gangue multispectral images in the training set and the test set; building a coal gangue recognition model based on an XGBoost algorithm by using the extracted multispectral image features, training the coal gangue recognition model on a training set, and performing parameter optimization of the XGBoost algorithm through a particle swarm optimization algorithm; and verifying the classification accuracy of the coal and gangue identification model on the coal and gangue through the test set, and verifying the model performance. The XGBoost model adopted in the method is high in recognition accuracy and interpretability, overfitting is not prone to being generated, and a good classification effect can be obtained.

Description

technical field [0001] The invention belongs to the technical field of gangue identification, and in particular relates to a gangue identification method based on particle swarm optimization XGBoost algorithm. Background technique [0002] Coal has long been my country's primary energy source. In the process of coal mining and excavation, coal that has not undergone any treatment is called raw coal. Raw coal contains a large amount of gangue, which has a high sulfur content and a large amount of heavy metals, and gangue has a low calorific value. , After mixing with coal, it will affect the calorific value of coal, affect the quality of coal, and cause pollution to the environment during the combustion process. China has been vigorously developing clean coal technology, and coal gangue sorting is an important step. [0003] The separation methods of coal and gangue mainly include artificial gangue discharge, jigging coal preparation, flotation coal preparation, selective cru...

AI Technical Summary

Problems solved by technology

Wet coal selection needs to consume a lot of water resources, and the coal slime pollution produced at the same time is difficult to deal with, which is inconsistent with the concept of producing clean coal; radiation selection such as gamma ray and X-ray selection has certain radiation, which will cause harm to human health. Certain damage, while the ordinary image recognition selection is greatly disturbed by factors such as light, and the recognition accuracy is not high

Images