RBF neural network-based coal and gas outburst prediction method

Abstract

The invention discloses an RBF (Radial Basis Function) neural network-based coal and gas outburst prediction method. The method comprises the steps of 1, performing dimensionality reduction on feature data of coal and gas outburst, and performing normalization processing on the feature data subjected to the dimensionality reduction to obtain normalized feature data; 2, clustering the normalized feature data by using a K-mean algorithm and calculating the center of an RBF; 3, training an RBF neural network on the normalized feature data, and introducing an optimal expansion factor and an optimal weight when the number of neurons in a hidden layer is determined by an adaptive differential evolution algorithm; 4, increasing the number of the neurons in the hidden layer, and repeating the steps 2-3 to obtain global optimal parameters of the RBF neural network, thereby determining a prediction model of the RBF neural network; and 5, predicting test data by using the prediction model of the RBF neural network. According to the method, the optimal parameter adaptive problem of the RBF neural network can be solved, so that the coal and gas outburst can be quickly and accurately predicted.

Description

technical field [0001] The invention relates to the field of coal mine safety production, in particular to a coal and gas outburst prediction method based on an RBF neural network. Background technique [0002] Coal is the main energy source and important raw material in the development of my country's national economy. However, the safety situation of my country's coal production is still very severe. Mine gas, coal dust, fire, flood and roof accidents are the five natural disasters in coal mines, among which gas is the number one "killer" of coal mines, and coal and gas outburst are the most frequently occurring gas disaster accidents and the number of people injured is large One of the typical dynamic disasters. Therefore, it is of great practical significance to quickly and accurately predict coal and gas outburst, which can not only improve the safety of coal mine production, but also generate huge economic and social benefits. [0003] Traditional coal and gas outbur...

AI Technical Summary

Problems solved by technology

For example, the BP neural network model is used to predict coal and gas outbursts. However, the disadvantages of the BP neural network are that the convergence speed is slow, the training time is long, and it is easy to fall into a local minimum.

There have been some works using RBF neural network to predict coal and gas outburst problems, but because the optimal parameters of RBF neural network are difficult to determine, and the data of coal and gas outburst in different mines in different regions are different, the optimal parameters will also vary. different

[0006] Therefore, it is difficult to determine the optimal parameters of the RBF neural network, and the differences in the coal and gas outburst data of different mines in different regions lead to different optimal parameters. An adaptive RBF neural network model with optimal parameters is needed to quickly and Accurately predict coal and gas outburst

Images