Open AccessGas Data Prediction Based on LSTM Neural Network
Author(s) -
Danhui Li,
Yingjun Zhang,
Gong Da-li,
Lei Pan,
Yajuan Zhao
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/750/1/012175
Subject(s) - artificial neural network , computer science , coal mining , fuzzy logic , coal , artificial intelligence , content (measure theory) , data mining , machine learning , petroleum engineering , mathematics , engineering , mathematical analysis , waste management
To improve the prediction accuracy of the coal seam gas content in the unmined areas, based on the analysis and study of the main geological factors affecting coal seam gas content, fuzzy mathematics is used as a means of expressing and processing inaccurate data and fuzzy information and neural network as a way to solve the problem to combine fuzzy mathematics with neural network organically and establish a coal seam gas content prediction model based on LSTM neural network. The results of this study show that the LSTM neural network model can not only solve the problems of difficulty to express fuzzy information quantitatively and determine the learning samples, etc., but also extract the non-linear relationship between the coal seam gas content and its various influencing factors accurately. According to the instance operation verification, the prediction accuracy is improved by 4.84% ∼ 25.79% compared with that of the neural network model. The effect of application to the prediction of coal seam gas content is more ideal. It has a good application prospect and can provide a theoretical basis for implementing scientific mine gas management and preventing various gas accidents.