Multi-level coal mine water inrush prediction method based on SaE-ELM (self-adaptive evolutionary extreme learning machine)

Abstract

A multi-level coal mine water inrush prediction method based on an SaE-ELM (self-adaptive evolutionary extreme learning machine) includes the steps of 1, researching a coal mine water inrush mechanism and selecting main controlling factors causing coal mine water inrush; 2, searching for a great deal of coal floor water inrush historical data as sample data, with each set of data including main controlling factors and maximum water inrush; 3, dividing the sample data into a training set and a test set, applied to training and testing of a model, respectively; 4, training the sample data with the SaE-ELM to establish a prediction model; 5, testing the prediction model with the data of the test set, comparing obtained prediction results with those obtained by other algorithms; if the prediction precision is high and the speed is high, using the prediction model for predicting whether a coal mine suffers water inrush or not and predicting the degree of water inrush.

Description

technical field [0001] The invention relates to a method for predicting multi-level water inrush in coal mines, in particular to a method for predicting water inrush in mines based on SaE-ELM. Background technique [0002] Coal mine water inrush is one of the five major disasters in coal mines. Rapid and accurate prediction of water inrush is the guarantee of safe production in coal mines. Coal mine water inrush prediction involves many factors such as hydrogeology, rock mechanics, mining conditions, etc. There are complex nonlinear relationships among these factors, so it is difficult to establish a model with traditional mathematical theories. [0003] Experts and scholars have proposed a variety of methods for predicting water inrush in coal mines. Some have used genetic algorithms to train BP neural networks, and established artificial neural network prediction models for coal seam water inrush. Although this method improves the training accuracy, in view of BP neural ne...

AI Technical Summary

Problems solved by technology

Coal mine water inrush prediction involves many factors such as hydrogeology, rock mechanics, mining conditions, etc. There are complex nonlinear relationships among the factors, so it is difficult to establish a model with traditional mathematical theories

[0003] Experts and scholars have proposed a variety of methods for predicting water inrush in coal mines. Some have used genetic algorithms to train BP neural networks, and established artificial neural network prediction models for coal seam water inrush. Although this method improves the training accuracy, in view of BP neural network It takes a lot of time to adjust the parameters; in addition, a coal mine floor water inrush prediction model combining PCA and ELM (Extreme Learning Machine) has been established, and the running speed and prediction accuracy of the model have been improved. , but when the ELM trains the model, all the parameters of the hidden layer of the network are randomly generated, and the training has a certain degree of randomness

In addition, my country divides the types of water inrush according to the maximum value (peak value) of water inrush, and most of the existing methods only predict whether the water inrush will occur, but do not involve the prediction of the degree of water inrush, which is not convenient for different water inrush Conditions are preprocessed

Images