Belt conveyor coal flow binocular vision measurement method based on deep transfer learning

Abstract

The invention discloses a belt conveyor coal flow binocular vision measurement method based on deep transfer learning, and the method comprises the steps: carrying out the preprocessing of a coal material image according to a Bouguet image correction algorithm, a histogram equalization image enhancement algorithm and a Hough transform image segmentation algorithm; carrying out transfer learning onthe pre-trained PSM-Net model according to the coal three-dimensional matching data set, establishing a deep learning model for a coal three-dimensional matching task, and carrying out coal three-dimensional information calculation by applying a binocular vision measurement principle; and calculating the volume of the load adhesive tape by adopting triangular prism gridding differential traversalsummation, and obtaining the coal carrying flow through differential calculation of the no-load adhesive tape and the load adhesive tape. According to the method, non-contact measurement is achievedby adopting binocular vision to collect data, stable, accurate and rapid calculation of the coal flow carried by the belt conveyor is achieved through deep transfer learning stereo matching model PSM-Net, GPU acceleration calculation and differential calculation, and meanwhile the use simplicity and practicability of the method are improved.

Description

technical field [0001] The invention relates to an intelligent visual measurement method for coal flow of a belt conveyor, in particular to a binocular visual measurement method for coal flow of a belt conveyor based on deep transfer learning. Background technique [0002] Belt conveyor is one of the important equipment in coal mine production. It is a kind of equipment for transportation by means of friction. It has the characteristics of strong transportation capacity, long transportation distance and continuous transportation. [0003] The coal in the underground fully mechanized mining face is transported to the ground through the trough belt conveyor, the main belt conveyor, the main shaft belt conveyor and the upper warehouse belt conveyor, and the length of the mining belt conveyor can be from Hundreds of meters to nearly a thousand meters. As an important energy-consuming equipment in coal mining enterprises, mining belt conveyors can account for 30% of the total lo...

AI Technical Summary

Problems solved by technology

However, when using binocular cameras for measurement, the influence of complex and changeable underground lighting in coal mining enterprises, dark coal images, and external interference factors are ignored; at the same time, the traditional image stereo matching algorithm has poor adaptability in coal stereo matching tasks.

The color and texture of the coal material image are repetitive and single, and the traditional image stereo matching algorithm needs to perform sliding window matching based on the image pixel information, resulting in the failure of the coal material image stereo matching, which in turn causes the calculation error of binocular vision to measure the coal flow; and the need to carry the coal material Image segmentation with tape, this process is computationally complex and affects system operating efficiency

Images