Author(s)

JiaQi Wu^1*, YunMin Tian², TianLe  Xiong¹, JunYao Hou³, YunFeng Luo³, Hao Chen³

Affiliation(s)

¹Reading Academy, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China.

²School of Atmosphere Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China.

³Waterford Institute, Nanjing University of Information Science and Technology, Nanjing 210044, Jaingsu, China.

Corresponding Author

JiaQi Wu

ABSTRACT

As the main energy and important industrial raw materials, coal plays a vital role. With the deep development of coal mining, the risk of underground coal and rock dynamic disasters is rising, which seriously threatens the safety of coal mining. In this paper, the interference signals and precursory characteristic signals in acoustic emission (AE) and electromagnetic radiation (EMR) signals are analyzed. A multi classification model based on the fine KNN model is established to classify the jamming signal data in three different intervals. ARIMA model is used to summarize and analyze the trend characteristics of precursory characteristic signals. The method of random forest classification model is used to classify and identify the time interval of the precursor signal. And calculate the probability of precursory characteristic data at a specific time.

KEYWORDS

ARIMA model; Refined k-nearest neighbor algorithm; Random forest classification model; Non-linear classification

CITE THIS PAPER

JiaQi Wu, YunMin Tian, TianLe  Xiong, JunYao Hou, YunFeng Luo, Hao Chen. Optimization of coal mine rockburst early warning system. World Journal of Engineering Research. 2025, 3(2): 15-20. DOI: https://doi.org/10.61784/wjer3024.

REFERENCES

[1] Song C H, Lu C P, Liu J R. Moment Tensor and Stress Field Inversions of Mining-Induced Seismicity in A Thick-Hard Roof Zone. Rock Mechanics and Rock Engineering, 2024, 57(3): 2267-2287.

[2] Watson J, Canbulat I, Zhang C, et al. Energies Within Rock Mass and the Associated Dynamic Rock Failures. Rock Mechanics and Rock Engineering, 2025, 58(5): 4935-4958.

[3] Wojtecki U, Krawiec K, Wikaa M, et al. An attempt to determine the cause of the strong tremor responsible for a rockburst in a hard coal mine based on numerical modeling and spectral parameters. Geology, Geophysics & Environment, 2024, 50(4).

[4] Wang K, Xie T, Mei L I, et al. A surrogate model for the rapid prediction of rockburst risk based on numerical samples and random forest classifier. Journal of Tsinghua University (Science and Technology), 2024, 64(7): 1203-1214.

[5] Kuzniar K, Tatara T, Zajac M. Experimental and numerical assessment of soil-structure interaction effects in the case of mine-induced vibrations. IOP Publishing Ltd, 2024.

[6] Eremin M O, Chirkov A O, Pazhin A, et al. Finite-Difference Analysis of Influence of Borehole Diameter and Spacing on Reduction in Rockburst Potential of Burst-Prone Coal Seams. Mining, 2024, 4(4).

[7] Jiahao S, Wenjie W, Lianku X. Predicting Short-Term Rockburst Using RF–CRITIC and Improved Cloud Model. Natural resources research, 2024, 33(1): 471-494.

[8] Dai J, Gong F, Huang D, et al. Quantitative evaluation method of rockburst prevention effect for anchoring rock masses around deep-buried tunnels. Tunnelling and Underground Space Technology incorporating Trenchless Technology Research, 2025, 156.

[9] Wojtecki U, Iwaszenko S, Apel D B, et al. Use of machine learning algorithms to assess the state of rockburst hazard in underground coal mine openings. 2022.

[10] Wang Q, Ma T, Yang S, et al. Intelligent rockburst level prediction model based on swarm intelligence optimization and multi-strategy learner soft voting hybrid ensemble. Geomechanics & Geophysics for Geo-Energy & Geo-Resources, 2025, 11(1).