Machine learning in coal and gas outburst prediction

Peng Ji; Shiliang Shi

doi:10.59400/jam.v1i1.74

Machine learning in coal and gas outburst prediction

Peng Ji Hunan University of Science and Technology
Shiliang Shi Hunan University of Science and Technology

Ariticle ID: 74

108 Views, 46 PDF Downloads

DOI: https://doi.org/10.59400/jam.v1i1.74

Keywords: machine learning, coal and gas outburst prediction, deep learning, artificial intelligence, application

Abstract

Artificial intelligence is flourishing, and its research achievements are being extensively applied across various industries. In the field of predicting coal and gas outbursts, methods such as machine learning and deep learning have been widely explored, resulting in accurate prediction accuracy and excellent predictive effects. This has significantly improved the safety of coal mine underground operations.

References

Wu F, Huo Y, Gao J. Coal mine gas emission prediction method based on forest regression. Industry and Mine Automation 2021; 47(8): 102–106. doi: 10.13272/j.issn.1671-251x.2021010024.

Zhang X, Liu F, Li X. Coal mine gas concentration prediction based on wavelet denoising and recurrent neural network. Coal Technology 2020; 39(9): 145–148. doi: 10.13301/j.cnki.ct.2020.09.041.

Zheng X, Lai W, Zhang L, Xue S. Quantitative evaluation of the indexes contribution to coal and gas outburst prediction based on machine learning. Fuel 2023; 338: 127389. doi: 10.1016/j.fuel.2023.127389.

Ji P, Shi S. Hazard prediction of coal and gas outburst based on the hamming distance artificial intelligence algorithm (HDAIA). Journal of Safety Science and Resilience 2023; 4: 151–158. doi: 10.1016/j.jnlssr.2022.12.001.

Xue F, Li X, Xu E. Application of GA-SVM coupling model in prediction coal and gas outburst. Mineral Engineering Research 2022; 37(3): 40–44. doi: 10.13582/j.cnki.1674-5876.2022.03.007.

Ji P, Shi S, Lu Y, Li H. Research on risk identification of coal and gas outburst based on PSO-CSA. Mathematical Problem in Engineering 2023; 2023: e5299986. doi: 10.1155/2023/5299986.

Lin H, Zhou J, Jin H, et al. Cooperative prediction method of coal and gas outburst risk grade based on feature selection and machine learning algorithm. Journal of Mining & Safety Engineering 2023; 40(2): 361–370. doi: 10.13545/j.cnki.jmse.2022.0010.

Fu H, Zhao J, Liu H, et al. Signal identification of fracture in gas bearing coal based on dual strategy coupling optimization. China Safety Science Journal 2022; 32(10): 40–47. doi: 10.16265/j.cnki.issn1003-3033.2022.10.1868.

Li B. Research on early warning method of coal and gas outburst based on deep learning and multi-source information fusion [PhD thesis]. Beijing: China University of Mining and Technology; 2021.

Published

2023-04-27

How to Cite

Ji, P., & Shi, S. (2023). Machine learning in coal and gas outburst prediction. Journal of AppliedMath, 1(1), 74. https://doi.org/10.59400/jam.v1i1.74

Download Citation

Issue

Vol. 1 No. 1 (2023)

Section

Perspective

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The dynamic loads from earthquakes and winds can destroy lives, cause collapsein civil structures, and interrupt basic services provided to the population. In this scenario,structural designs must be developed to decrease the damage induced by these actions. Theobjective of this work is to design a hybrid controller based on the optimization via statefeedback and the magneto-rheological damper (MRD) to mitigate the excessive vibrations ofa three-story steel frame building, represented through the shear building model, subjected tothe simultaneous dynamic action of wind and earthquake. All research is based oncomputational simulation, experimental research and results will not be addressed. In thenumerical analysis, digital computer and MATLAB® software are used, and implementedcodes generate the expected results based on the mathematical modeling. With theapplication of the control technique via state feedback, the displacements were reduced by77%. With MRD this reduction was 79%. With the hybrid controller, this reduction was100%. Thus, the verifications in relation to maximum displacements were met for NBR15421:2006, NBR 8800:2008 and NBR 6118:2014. From the results, it is concluded that thehybrid controller proved to be more efficient and achieved the proposed objective. Theexogenous inputs had zero influence on the behavior of the system output

One of the most widespread interpretations of the mass-energy equivalence establishes that not only can mass be transformed into energy (e.g., through nuclear fission, fusion, or annihilation) but that every type of energy also has mass (via the mass-energy equivalence formula). Here, we show that this is not always the case. With the help a few thought experiments, we show that, for instance, the electric potential energy of a charged capacitor should not contribute to the capacitor’s gravitational rest mass (while still contributing to its linear momentum). That result is in agreement with the fact that light (ultimately, an electromagnetic phenomenon) has momentum but not rest mass