Identification method for laser-induced fluorescence spectral image of water inrush in coal mine

Abstract

The invention discloses an identification method for a laser-induced fluorescence spectral image of water inrush in a coal mine. The method comprises the following steps of (1) acquiring an original fluorescence spectral image of a water sample by use of a laser-induced fluorescence spectroscopy; (2) performing zooming, cropping and graying preprocessing on the original fluorescence spectral imageof the water sample; (3) performing characteristic extraction on the preprocessed gray image by use of a PCANet (Principal component analysis Network) to obtain PCANet image characteristics; (4) partitioning a water sample specimen consisting of the PCANet image characteristics into an independent training set and an independent test set by use of a SPXY (sample set partitioning based on joint x-y distance) method; and (5) establishing a water inrush source identification model on the training set, and performing test on a model identification result through the test set. According to the identification method for the laser-induced fluorescence spectral image of the water inrush in the coal mine, the identification model for the fluorescence spectral image of the water inrush source in the coal mine by use of the PCANet is simply constructed, is simple for parameter optimization, meanwhile has high identification rate and identification speed and is suitable for online and real-time monitoring of the water inrush source in the coal mine.

Description

technical field [0001] The invention relates to the field of mine water inrush water source identification, in particular to a mine water inrush laser-induced fluorescence spectrum image recognition method. Background technique [0002] Water inrush disaster is the second largest disaster among the five major disasters in coal mines. It is necessary to carry out early warning of water inrush on site and accurately grasp the type of water inrush. For the identification of the type of water inrush in coal mines, most of the traditional methods are based on water chemistry to obtain parameters such as pH value, ion concentration, and conductivity of the water sample to be tested, and establish a water source type identification model based on these parameters. However, the determination of water chemical parameters, especially the ion concentration, takes 1-2 hours to complete, which takes a long time and cannot meet the real-time requirements of coal mine water inrush disaster...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a mine water inrush laser-induced fluorescence spectrum image recognition method to solve the deficiencies in the existing mine water inrush water source identification method, and to carry out early warning of coal mine water inrush disasters

Images