Expert knowledge and data fusion driven rock burst prediction model construction method

Abstract

The invention discloses a rock burst prediction model construction method driven by expert knowledge and data fusion, which comprises the following steps: collecting mine earthquake data, processing the mine earthquake data, extracting display features and implicit features and constructing a prediction model, if the probability of a large-energy mine earthquake event is greater than the probability of a large-energy mine earthquake event, outputting 1, otherwise, outputting 0, and if the probability of a large-energy mine earthquake event is greater than the probability of a small-energy mine earthquake event, outputting 1; therefore, prediction of the rock burst macro-energy event is realized. The method can comprehensively and accurately predict the occurrence probability of the rock burst.

Description

technical field [0001] The invention relates to a rock burst prediction model, in particular to a construction method of a rock burst prediction model driven by the fusion of expert knowledge and data, and belongs to the technical field of monitoring and early warning. Background technique [0002] Coal is my country's basic energy and an important raw material, and the coal industry is an important basic industry related to the country's economic lifeline and energy security. Rockburst is a coal rock dynamic disaster that seriously threatens the safety of mine production. With its sudden, sharp and violent destruction characteristics, rock burst has a serious impact on the normal production of coal mines, metal mines, tunnels, etc., and even causes huge economic losses and casualties. [0003] As the mining depth of the mine increases, the danger of rock burst is also gradually increasing, and mines where rock burst did not occur before also began to occur; mines that had ...

AI Technical Summary

Problems solved by technology

However, these artificially designed features may not be able to make full use of the information contained in the mine-seismic sequence;

[0006] 2) Using the deep learning method to extract the implicit features of the mine earthquake data to establish a corresponding model for prediction, although the information contained in the mine earthquake sequence can be fully utilized, but from the perspective of the theoretical system, its interpretation ability is weak

[0007] Neither of the above two methods can fully and accurately predict the occurrence probability of rock burst. Therefore, how to comprehensively and accurately predict the occurrence probability of rock burst has become a technical problem that needs to be solved urgently.

Images