Coal and rock classification method based on wavelet domain asymmetric generalized Gaussian model

Abstract

The invention discloses a coal and rock classification method based on a wavelet domain asymmetric generalized Gaussian model. The method comprises the steps of obtaining m known coal sample images and m known rock sample images which are of the same size and do not contain backgrounds in the sample training stage, conducting wavelet transform image decomposition on each image, calculating parameters of each wavelet coefficient sub-band meeting the asymmetric generalized Gaussian distribution condition of each image, and using all the parameters of each image for constructing a training sample characteristic column vector; in the coal and rock recognition stage, collecting and obtaining unknown type coal and rock images ux which are of the same size of the training sample image and do not contain the background, conducting wavelet transform image decomposition on the ux, calculating parameters of each wavelet coefficient sub-band meeting the asymmetric generalized Gaussian distribution condition of the ux to form a characteristic column vector Vux, and judging the type of coal and rock of the ux by comparing the similarities between the Vux and the training sample characteristic column vector. The coal and rock classification method is good in reliability and high in classification accuracy, and software and hardware are convenient to maintain.

Description

technical field [0001] The invention relates to a coal and rock classification method based on an asymmetric generalized Gaussian model in the wavelet domain, which is used for distinguishing coal and rocks produced in the coal production process, and belongs to the technical field of image pattern recognition. Background technique [0002] Coal rock classification, also known as coal rock identification, refers to the automatic identification of coal and rock through various technical means. In the process of mining and transportation of coal resources, there are many production links that need to distinguish between coal and rock, such as the height adjustment of the shearer drum, the control of the top coal caving process in fully mechanized mining, and the selection of raw coal in coal preparation plants. South Africa, Australia, Germany, the United States, China and other major coal-producing countries in the world have always attached great importance to the research o...

AI Technical Summary

Problems solved by technology

However, these methods have the following common problems: (1) Various sensors need to be installed and deployed on existing equipment, resulting in complex structure and high manufacturing cost; The force is complex, the vibration is severe, the wear is serious, the deployment of the sensor is relatively difficult, the electronic circuit is also easily damaged, and the reliability of the device is poor; (3) For different types of mechanical carrier equipment, the selection of the sensor and the selection of the installation position are difficult. There is a big difference, which requires personalized customization, so its universality is not good

The existing coal and rock classification methods based on image processing still have a lot of room for improvement in terms of stability and recognition rate.

Images