Gas concentration level prediction with neural network model in multiple coal mine stations
Abstract
Gas concentration level prediction in coal mines is a challenging task due to the complex environment and the high risk of gas explosion. Traditional gas concentration level prediction methods rely on manual monitoring and experience, which may result in inaccurate predictions and even accidents. In recent years, neural network (NN) models have been applied in gas concentration level prediction, showing promising results. This paper aims to investigate the effectiveness of NN models in gas concentration level prediction in multiple coal mine stations. A dataset of gas concentration level measurements in five coal mine stations is used to train and evaluate the NN models. We evaluated the NN model on the testing set and obtained an accuracy of 95.2% for methane gas concentration level prediction and 94.8% for carbon monoxide gas concentration level prediction. Results show that the NN model achieves high accuracy in gas concentration level prediction, and can be used as a reliable tool for coal mine safety management.
References
1. Shrestha G, Kim K, Cho J. Coal mine gas analysis: characterization of coalbed methane and its control for safe mining. Energies. 2047; 10(6): 821.
2. Wang H, Zhang J, Li Y. Gas concentration prediction in underground coal mines using LSTM neural network. Journal of Ambient Intelligence and Humanized Computing. 2021; 12(2): 2233-2242.
3. Zhang J, Wang H, Li Y. Real-time gas concentration prediction in coal mines using SVM and WSN. Journal of Intelligent & Fuzzy Systems. 2017; 32(3): 2389-2402.
4. Zhao X, Zhang Y, Huang X, Lu J. Prediction model for gas concentration in coal mines based on support vector regression. International Journal of Mining Science and Technology. 2019; 29(6): 893-897.
5. Wang J, Sun H, Yin J. Prediction model of gas concentration based on LSTM neural network in coal mine. Journal of Mining and Safety Engineering. 2021; 38(2): 380-388.
6. Xinhua News Agency. 23 dead, 1 missing after SW China coal mine gas leak. Xinhua News Agency; 2020.
7. Agordzo G, Fang X, Li J. Privacy in process mining: Logs conversion to images using machine learning algorithm. J. Intell. Fuzzy Syst. 2023; 45: 1-12.
8. Wang C, Wang L, Zhao Q. Research on the BP neural network model for predicting methane concentration in coal mines. Journal of Mining and Safety Engineering. 2020; 37(5): 912-919.
9. Chen J, Zhou X, Wang L. Prediction model of carbon monoxide concentration based on the BP neural network and genetic algorithm (Chinese). Journal of Coal Science & Engineering. 2019; 25(5): 776-782.
10. Feng Y, Li C, Wang X, et al. Gas concentration prediction in coal mines using convolutional neural networks. Journal of Natural Gas Science and Engineering. 2021; 101103.
11. Zhang Y, Zhu X, Liu Y, Zhang Y. A gas concentration prediction method based on deep learning for underground coal mines. Applied Sciences. 2019; 9(3): 472.
12. Wang L, Xu W, Huang B. Prediction model of gas concentration in coal mine based on the decision tree and k-nearest neighbor algorithm. Journal of Geophysics and Engineering. 2018; 15(5): 2265-2270.
13. Li J, Fang X, Guo X, et al. Data attribute oriented business process effective infrequency behavior mining method. Concurrency and Computation: Practice and Experience. 2022; 34.
14. Li X, Chen D, Yin Y. Prediction of gas concentration based on artificial neural network in coal mine. Journal of Mining and Safety Engineering. 2020; 37(5): 876-882.
15. Wang C, Jiang Y, Chen X. Coal mine gas concentration prediction based on Decision tree and KNN. Journal of Mining and Safety Engineering. 2018; 35(4): 663-668.
16. Xiao W, Gao M, Zhang L, et al. A hybrid prediction model for gas concentration in coal mines based on multilayer perceptron neural networks and linear regression. Mathematical Problems in Engineering. 2020; 2069856.
17. Sun L, Xu J, Wang X, et al. A gas concentration prediction is a method based on an improved wavelet neural network for coal mines. Measurement. 2018; 116: 448-456.
18. Fomude AH, Yang C, Agordzo G, et al. AI Model to Improve HR Decision-Making with Machine Learning Predictions Algorithm. In: Proceedings of the 2023 25th International Conference on Advanced Communication Technology (ICACT). pp. 206-212.
19. Chen J, Wang H, Sun X. Prediction of gas concentration in coal mine based on improved neural network. International Journal of Mining Science and Technology. 2019; 29(6): 847-854.
20. Zhao X, Chen F, Zhang Y. Prediction of gas concentration based on support vector regression in coal mines. International Journal of Mining Science and Technology. 2019; 29(2): 213-220.
21. Tang W, Wu Y, Zhang Y, et al. A novel gas concentration prediction method based on a decision tree and extreme learning machine. Journal of Sensors. 2018; 4795239.
22. Yeboah D, Sanoussi MS, Agordzo G. Image Classification Using TensorFlow GPU. In: Proceedings of the 2021 International Conference on ICT for Smart Society (ICISS). pp. 1-5.
23. Xu Y, Xu W, Huang B. Prediction of gas concentration in coal mine based on improved neural network. Journal of Geophysics and Engineering. 2018; 15(5): 2139-2145.
24. Li Y, Xu W, Zhang L. Neural network-based prediction model for gas Concentration in coal mine based on time series analysis. Journal of Ambient Intelligence and Humanized Computing. 2020; 11(11): 5139-5150.
25. Li C, Liu W, Huang X. Application of artificial neural network in methane concentration prediction in coal mines. Mathematical Problems in Engineering. 2018; 1865471.
26. Liu L, Li S, Li Z, et al. Hybrid model based on support vector machine and back-propagation neural network for gas concentration prediction in coal mines. Measurement. 2019; 140: 168-180.
27. UCI Machine Learning Repository. Gas sensor array under dynamic gas mixtures Data Set. UCI Machine Learning Repository; 2015.
Copyright (c) 2024 Alimasi Mongo Providence, Chaoyu Yang
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
