PCA-FIG-SVM (Principal Component Analysis-Fuzzy Information Granulation-Support Vector Machine)-based absolute gas emission prediction method

Abstract

The invention discloses a PCA-FIG-SVM (Principal Component Analysis-Fuzzy Information Granulation-Support Vector Machine)-based absolute gas emission prediction method, belonging to an absolute gas emission prediction method for a coal mine stope face. The method comprises the following steps: (1) collecting absolute gas emission monitoring data and influence factors; (2) carrying out principal component modeling on the influence factor data and reconstructing principle components; (3) carrying out FIG on a time sequence composed of the absolute gas emission monitoring data; (4) establishing an SVM regression model of granulation data; (5) predicting the absolute gas emission. According to the method disclosed by the invention, a novel prediction model is provided for an absolute gas emission change trend, the change trend and the change space range are focused and researched, the principle components are extracted by utilizing PCA, the influence of redundant information is effectively reduced, the input dimensionality of the SVM model is reduced, and the design precision is reliable; the prediction method is simple, high in prediction precision and environment-friendly in prediction environment.

Description

technical field [0001] The invention relates to a method for predicting the amount of gas emission in a driving face, in particular to a method for predicting the absolute amount of gas emission based on principal component analysis (PCA)-fuzzy information granulation (FIG)-support vector machine (SVM). Background technique [0002] In the process of coal mining, the gas problem has always been one of the major hidden dangers restricting the safe production of coal mines. Accurate measurement and real-time monitoring of the absolute gas emission in coal mines is an important measure to ensure safe production in coal mines. [0003] At present, many scholars at home and abroad have carried out in-depth and detailed research on the problem of gas prediction, and put forward many effective prediction methods, which can be roughly divided into two categories: one is linear models, such as separate source prediction method, principal component regression analysis method, statisti...

AI Technical Summary

Problems solved by technology

However, these monitoring data are only a record of the current working status, and there is still a lack of development trends for the monitoring data in the future

In the prior art, Wu Zhaofa and others disclosed a gas concentration trend prediction method in the 2014 Volume 40, No. 12 of the Journal of Industrial and Mining Automation. The title of the paper is: Gas concentration trend prediction based on interpolation trapezoidal fuzzy information granulation, However, since the prediction method is only based on the original data of gas concentration, and does not consider the effects of mining conditions, coal seam conditions and other influencing factors, during the mining process, the influencing factors affecting the amount of gas emission are constantly changing, making the gas emission in the working face There is a very large uncertainty in the output, so it is necessary to propose a new prediction model for the change trend of the absolute gas emission, focusing on the study of the change trend and the spatial range of the change

Images