Coal gangue identification method based on X-ray image

Abstract

The invention relates to the technical field of coal gangue recognition, in particular to a coal gangue recognition method based on an X-ray image. The method comprises an on-line identification process and a model learning process, and the on-line identification process comprises the steps of (1) obtaining an X-ray image of coal gangue; (2) carrying out preprocessing and target extraction on theimage; (3) extracting gray feature quantity; (4) calculating a gray level co-occurrence matrix, and extracting a texture characteristic quantity; (5) taking the calculated coal gangue characteristic quantity as an input characteristic quantity of a classification model; (6) obtaining recognition accuracy; the model learning process comprises the following steps: (1) accumulating a large number ofcoal gangue X-ray image databases; (2) manually calibrating the type of the coal gangue; (3) preprocessing and feature extraction are carried out on the images in the database; (4) constructing an NP-FSVM model to perform supervised learning; (5) further optimizing main parameters of the model by utilizing PSO; and (6) obtaining a final classification model. The method can effectively improve on-line identification accuracy of the coal gangue.

Description

technical field [0001] The invention belongs to the technical field of gangue identification, and in particular relates to an X-ray image-based identification method for gangue. Background technique [0002] Coal is one of the main energy sources in my country. With the increasing environmental pollution in recent years, the state attaches great importance to and actively advocates the clean use of coal resources. The sorting of coal gangue is an important link in the production and processing of coal mines, and it is also an effective way to make full use of coal resources to improve coal quality and reduce environmental pollution. At present, the separation methods of coal and gangue mainly include artificial gangue discharge, jigging coal preparation, flotation coal preparation, selective crushing, dense medium coal preparation, and ray detection and identification coal preparation, etc., but these methods generally have low recognition accuracy, Large space occupation, ...

AI Technical Summary

Problems solved by technology

In the actual coal preparation process, the size of lump coal and gangue is different. Due to the influence of thickness, the gray value of X-ray image may be partially equal or crossed, which makes the correct recognition rate of coal gangue lower. Therefore, it is not possible to only Consider the gray feature information of coal gangue; the traditional fuzzy support vector machine (FSVM) membership function only measures the membership degree from the center distance of the sample, and cannot effectively eliminate isolated samples, resulting in a decrease in the correct recognition rate

Images