Coal mine gas early warning method based on class label weighted extreme learning machine

Abstract

The invention discloses a coal mine gas early warning method based on a class label weighted extreme learning machine, which comprises the steps of acquiring historical gas concentration monitoring data, preprocessing the data and filling missing data, generating a sample set, setting a gas concentration early warning threshold value, and determining a sample imbalance ratio by adopting the early warning threshold value mu; and performing weighting operation on the class label matrix of the sample according to the feedback value of the imbalance ratio, determining the optimal hidden layer node number of the extreme learning machine by utilizing five-fold cross validation, and training and generating an extreme learning machine model by taking a Sigmoid function as an activation function and taking the weighted class label matrix as an expected output matrix of the model. Whether the gas concentration of a certain single monitoring point exceeds the warning line or not in the next three hours is predicted, the potential production safety risk is early warned, the influence of class imbalance is considered, and the method is easy to implement, high in detection rate and low in false alarm rate.

Description

technical field [0001] The invention relates to a coal mine gas early warning method, which belongs to the technical field of gas concentration prediction. Background technique [0002] In my country's energy industry, coal accounts for about 70% of my country's primary energy production and consumption structure. For a long period of time in the future, coal will still be the main energy source in my country, but at present, the safety situation of coal mine production is very serious. Severe, safety accidents still occur from time to time, and the monitoring systems of many coal mines in my country lack the function of disaster prediction. Mine gas is one of the main factors affecting the safety of coal mines. If the gas concentration is too high, it may cause a series of safety accidents. Therefore, it is of great significance to the safe production of coal mines to accurately predict whether the gas concentration in the next few hours will exceed the warning line, and to...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a coal mine gas early warning method based on class-marked weighted extreme learning machine. This method can effectively solve the problem of category imbalance and accurately predict gas according to the historical data of gas Whether the concentration will exceed the warning line in the next few hours is mainly used in coal mine safety warning, which can improve the coal mine's ability to prevent and control gas explosion accidents

Images