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

Abstract

The invention discloses a coal rock classification method based on the asymmetric generalized Gaussian model in the wavelet domain. In the sample training stage, m pieces of known coal sample images and m pieces of known rock sample images with the same size and no background are obtained, and wavelet transform image decomposition is performed on each image, and each wavelet coefficient subband of each image is calculated Under the condition that the parameters obey the asymmetric generalized Gaussian distribution, a training sample feature column vector is constructed with all the parameters of each image; in the stage of coal rock recognition, an unknown coal rock with the same size as the training sample image and without background is collected Image ux, perform wavelet transform image decomposition on ux, calculate the parameters of each wavelet coefficient subband of ux under the condition of obeying the asymmetric generalized Gaussian distribution, construct the feature column vector and judge by comparing the similarity with the training sample feature column vector The coal rock type to which ux belongs. The invention has good reliability, high classification accuracy and convenient maintenance of software and hardware.

Description

technical field [0001] The invention relates to a coal-rock classification method based on a wavelet-domain asymmetric generalized Gaussian model, which is used for distinguishing coal and rock produced in the coal production process, and belongs to the technical field of image pattern recognition. Background technique [0002] Coal and rock classification, also known as coal and rock identification, refers to the automatic identification of coal and rock through various technical means. In the process of coal resource mining and transportation, there are many production links that need to distinguish between coal and rock, such as the adjustment of the height of the shearer drum, the process control of top coal caving 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 on coal...

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