Big data analysis method of outburst risk factors inversion in working face by using local outburst risk prediction data

Abstract

The invention discloses a big data analysis method of outburst risk factors inversion in a working face by using local outburst risk prediction data. The method comprises the following steps: step S1,establishing a feature extraction model of local outburst risk prediction and prediction data; step S2, determining the number N of local outburst risk prediction cycles required for outburst risk factor inversion; 3, establishing an outburst risk factor inversion model in which that prediction cycle number of the local outburst risk is N; S4, processing the collected local outburst risk prediction and prediction data of the latest N cycles of the working face by using the feature extraction model to obtain a set of current local outburst risk prediction and prediction characteristic index values of the working face; S5, obtaining the inversion result of the outburst risk factors at the current position of the working face; 6, issuing alarm information; step S7: repeating steps S4 to S6 to dynamically inverse and alarm the outburst risk factors of the working face.

Description

technical field [0001] The invention belongs to the technical field of coal and gas outburst prevention and control, and relates to a big data analysis method for using local outburst risk prediction and forecast data to invert working face outburst risk factors. Background technique [0002] Coal and gas outburst (hereinafter referred to as "outburst") is extremely destructive, and it is one of the main natural disasters that threaten the safety of coal mines. Outburst prediction and forecasting is an important means of outburst disaster prevention and control. Outburst mines in my country have extensively carried out local outburst risk prediction and forecasting work. However, the existing local outburst risk prediction methods all determine the outburst risk of the working face by simply comparing the forecast index value with the critical value. Otherwise, it is judged as a non-protruding dangerous working face. This judgment method has the following problems: 1) The ...

AI Technical Summary

Problems solved by technology

However, the existing local outburst risk prediction methods all determine the outburst risk of the working face by simply comparing the forecast index value with the critical value. Otherwise, it is determined that there is no prominent dangerous working face

This judgment method has the following problems: 1) The outstanding risk of the working face is determined only according to the size of the forecasting index, and the information mining hidden in the forecasting data is not used enough, resulting in a huge waste of forecasting data resources. The accuracy rate is not high; 2) The judgment results are simply divided into those with outburst risks and those without outburst risks, without considering the potential relationship between prediction indicators and outburst risk factors such as gas occurrence, geological structure, stress concentration, and abnormal coal structure. It has limited guiding role in formulating outburst prevention measures and management of outburst prevention

[0004] Although the gas outburst prediction and early warning method based on the big data platform adopts big data-oriented data processing technology, it is still essentially a method to determine the risk of outburst in the working face by simply comparing the forecast index value with the critical value. , the above problem still exists

Images