A gas emission amount prediction method based on an improved GA-BP network model

Abstract

The invention discloses an improved GA-based (genetic algorithm-based) method. The invention discloses a gas emission amount prediction method of a BP network model, and relates to the technical fieldof coal mine underground stope face gas prevention and control. GA-BP network model is combined with a genetic algorithm and a BP algorithm, and on the basis of keeping the original adaptivity and fault tolerance, the optimal initial weight value and threshold value are selected through global search. Therefore, the learning speed of the network is accelerated, and the global optimization capability is improved to a certain extent. GA-BP network model is combined with a main factor analysis method, main factors are extracted through main factor analysis to replace original input variables, the network structure is simplified, and variable redundancy information is eliminated. Meanwhile, a genetic algorithm (GA) is adopted to optimize the initial weight value and the threshold value of thenetwork, and a momentum factor is added to optimize the updating mode of the weight value, so that the search is prevented from falling into a local minimum value, and the prediction accuracy is improved. And finally, selecting actual gas emission monitoring data as label data and input data, and carrying out simulation and analysis on different network models.

Description

technical field [0001] The invention relates to the technical field of gas prevention and control in underground mining working faces of coal mines, in particular to a gas emission prediction method based on an improved GA-BP network model. Background technique [0002] With the increasing intensity and depth of coal mine mining, gas control has gradually become one of the important factors restricting the safe and efficient production of mines. Accurate prediction of gas emission is a necessary prerequisite for the implementation of the gas control system. However, gas gushing is an extremely complex dynamic system, and there is a high degree of nonlinear correlation between the various influencing factors. Traditional linear prediction methods such as the separate source prediction method cannot achieve the expected accuracy. For example, Lu Fu et al. applied the principal component regression analysis method to the prediction of gas emission; Li Guozhen et al. used gray t...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the defects of the existing coal temperature programming experiment device, the present invention provides an oil bath type coal temperature programming experiment device based on a dynamic oxygen environment, which is reasonable in design and easy to operate, and can provide coal samples with different oxygen concentrations through a dynamic gas distribution system. Heating the coal sample in the oil bath can make each part of the coal sample heated evenly, improve the accuracy of the experiment and the accuracy of the data results, and the automatic quantitative gas sample collection system can realize the gas product in the process of coal oxidation and heating. Automatic sampling can accurately control the sampling time and gas sample volume, and realize the automatic intelligent testing and analysis of gas samples, which makes up for the defects of artificial uneven sampling and low measurement accuracy, simplifies the operation process, and shortens the experiment time

Images