Rock burst danger level prediction method based on local weighting C4.5 algorithm

Abstract

The invention provides a rock bust danger level prediction method based on a local weighting C4.5 algorithm and relates to the technical field of rock burst prediction. The method includes the steps of firstly, adopting an MDLP method for conducting discretization on continuous attribute data in sample data, then adopting a local weighting method for selecting a training set and calculating the weight of samples, utilizing the weight of the samples to calculate an information gain ratio of each attribute, and selecting sample attributes as root nodes of a C4.5 decision tree and splitting attributes of other branch nodes according to the information gain ratios; finally, adopting the weight of the samples to substitute the sample number to conduct pessimistic pruning on the created decisiontree, and correspondingly achieving prediction of rock burst dangers and the like in a predicted area. According to the provided rock bust danger level prediction method based on the local weightingC4.5 algorithm, the defect is overcome that the preference selection values have too many attributes when information gain is adopted for selecting node splitting attributes in an ID3 algorithm; an over-fitting problem is avoided, and the prediction accuracy of a model is high.

Description

technical field [0001] The invention relates to the technical field of rock burst prediction, in particular to a method for predicting a rock burst hazard level based on a local weighted C4.5 algorithm. Background technique [0002] Rock burst is a dynamic phenomenon characterized by sudden, sharp and violent damage caused by the release of deformation energy of the coal and rock mass around mine shafts and stopes. It is one of the major disasters that affect the safety of coal mine production. All countries are threatened by rock burst to varying degrees. In recent years, developed countries have shut down rock burst mines due to energy structure adjustment and safety considerations. my country has become the main victim of rock burst and the main country for rock burst prevention nation. [0003] Prediction and evaluation of rock burst is a key step in the prevention and control of rock burst based on the study of the mechanism of rock burst, but because the mechanism of ro...

AI Technical Summary

Problems solved by technology

[0003] Prediction and evaluation of rock burst is a key step in the prevention and control of rock burst based on the study of the mechanism of rock burst, but because the mechanism of rock burst is not fully understood, especially for deep rock burst The research on the mechanism of rock burst is still in its infancy, which increases the difficulty of rock burst prediction

At present, the methods for predicting rock burst mainly include rock mechanics methods and geophysical methods, among which rock mechanics methods include drilling cuttings method, mining stress detection method, etc., and geophysical methods include geoacoustic monitoring, microseismic monitoring, electromagnetic radiation monitoring, etc. method; in addition, with the development of artificial intelligence, there have been some methods for predicting rock burst using intelligent algorithms, such as: neural network method, Bayes discriminant analysis method, support vector machine, etc. A large number of research results have been obtained in this method, but there are still some problems, such as the neural network generally requires more samples, but the sample size used for rock burst prediction is less, the Bayes method requires high independence between data, and In reality, it is difficult for the sampling data of rock burst to meet the independence requirements, and the above method does not consider the overfitting problem of the model, etc.

Images