Coal mine water burst predicting method based on long-short-time memory neural network

Abstract

The invention discloses a coal mine water burst predicting method based on a long-short-time memory neural network. The coal mine water burst predicting method introduces the long-short-time memory neural network into coal mine water burst prediction. Firstly, a feature selection method based on a Wrapper evaluation strategy is adopted to preprocess data, extract feature data and eliminate the influence of redundancy features on a follow-up prediction algorithm; by adopting an MSRA initializing method, a weight matrix is initialized into Gaussian distribution with the mean value of 0 and the variance of 2 / (input number), so that the prediction method has more reasonable initializing weight, and the convergence rate of the method is improved; an LSTM method is adopted to learn the change law of dynamic water burst data and the influence of the law on water burst, the method is prevented from overfitting by using a Dropout technology in the learning process. With increase of iteration number, the weight matrix of the prediction method is constantly updated, and accordingly the precision, stability and robustness of the prediction method are improved.

Description

technical field [0001] The invention relates to the technical field of coal mine water inrush prediction, in particular to a coal mine water inrush prediction method based on a long-short-term memory neural network. Background technique [0002] The prediction of water inrush in coal mines mainly studies the mechanism of water inrush and analyzes the previous water inrush accidents, summarizes the risk factors and main links that induce water inrush accidents, analyzes the most likely causes of water inrush, and determines a suitable set of water inrush accidents. The index system to solve the water inrush problem, and adopt a deep learning method to identify, analyze, evaluate, and judge the risk of water inrush accidents, and determine the level of water inrush risk based on the data of historical water inrush accidents. [0003] Existing water inrush prediction methods include backpropagation neural network (BPNN), support vector machine (SVM) and so on. BPNN corrects th...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the traditional water inrush prediction method cannot learn dynamic water inrush data, the present invention proposes a coal mine water inrush prediction method based on long-short-term memory neural network, which introduces long-short-term memory neural network (LSTMs) into water inrush prediction Among them, LSTMs can better process time series data, learn dynamic water inrush features, effectively process variable length data and filter noise data, and are superior to BPNN method and SVM method in terms of prediction accuracy and stability.

Images