Neural network rock burst prediction method based on time sequence data

Abstract

The invention relates to a neural network rock burst prediction method based on time sequence data, and the method comprises the steps: collecting rock burst data through mine data collection equipment, and carrying out the quantitative processing of main influence factors; standardizing the quantized data and then adding random noise; intercepting a quantitative time window through a sliding window method to construct sample data; dividing the time window data into a training set and a verification set through a random sampling method; training the established neural network by using the training set data, and adjusting network parameters by using the verification set test network performance; and predicting the rock burst of the mine by using the trained neural network model to obtain danger early warning information. The method is high in reliability, the neural network is trained through time sequence data, the problem that rock burst prediction is limited by short-time data is solved, rock burst long-term dynamic prediction is achieved, and rock burst disaster early warning can be effectively conducted.

Description

technical field [0001] The invention relates to a method for predicting mine rock burst, in particular to a method for predicting rock burst based on a neural network of time series data. Background technique [0002] When the mine is mined to a certain depth, the rock burst due to the underground stress, environmental disturbance, mining stress and structural stress is a special form of mine pressure. During the occurrence of rock burst, the ore body of the mine is violently crushed and thrown into the roadway to cause damage to the mine support and working face, and casualties often occur. At present, most mines in my country are threatened by rock burst in varying degrees. [0003] The research on rock burst mainly focuses on analyzing its formation mechanism and researching its prediction method. And various prediction methods need to be aimed at specific geological conditions, and combine theory with practice to predict rock burst. At present, in addition to the empi...

AI Technical Summary

Problems solved by technology

[0006] The technology of the invention solves the problem: it overcomes the inability to make full use of the existing complex nonlinear mine pressure data in the current rock burst prediction process, and provides a neural network dynamic prediction method for rock burst based on time series data, which has high reliability and realizes rock burst Medium- and long-term dynamic prediction of ground pressure

Images