The Evolutionary Path of Dynamic Identification Algorithms for Safety Risks in Deep Coal Mines Based on Measurement While Drilling

DOI: https://doi.org/10.62517/jsse.202608206

Author(s)

Biao Fu

Affiliation(s)

College of Energy and Mining Engineering, Shandong University of Science and Technology, Qingdao, China

Abstract

With the increasing depth of coal mining, the high ground stress, high gas pressure, and complex geological conditions faced by deep coal mines significantly increase safety risks such as rockbursts and coal and gas outbursts. Dynamic identification while drilling (DWD) technology has become an important means to achieve real-time perception and early warning of safety risks in coal and rock masses. This paper systematically reviews the evolution path of DWD dynamic identification algorithms for safety risks in deep coal mines. First, it elucidates the disaster-causing mechanism of safety risks in deep coal mines, the data acquisition and signal characteristics during drilling, and the mathematical model of the dynamic identification algorithm. Based on this, it focuses on analyzing the evolution of the algorithm from the traditional threshold algorithm stage to the machine learning algorithm stage, and then to the deep learning fusion algorithm stage. Traditional thresholding algorithms primarily rely on empirical thresholds and statistical properties to identify drilling parameter anomalies, offering advantages such as simple structure and strong real-time performance. Machine learning algorithms, employing methods like Support Vector Machines and Extreme Learning Machines, significantly enhance nonlinear feature extraction capabilities and model adaptability through data-driven modeling. Deep learning fusion algorithms utilize convolutional neural networks, long short-term memory networks, and multi-source data fusion architectures to achieve end-to-end automatic feature extraction and intelligent risk classification and prediction, effectively improving identification accuracy and robustness in complex deep environments. This paper's systematic study of the evolution path of dynamic identification algorithms during drilling provides a theoretical framework and technical support for dynamic identification of safety risks in deep coal mines.

Keywords

Deep Coal Mine; Safety Risks; Dynamic Identification While Drilling; Algorithm Evolution Path; Deep Learning Fusion

References

[1] Shu, LY, Zhu, NN, Chen, J., An, S., Zhang, HJ: Theoretical method and technology of precision identification for coal and gas outburst hazard. Journal of China Coal Society 45(5), 1614–1625 (2020). [2] Zhang, YZ, Li, QX, Li, WN, Zhong, ZC, Chen, L., Yang, DD, Chen, T.: Research and application of intelligent perception while drilling in coal mine. Coal Science and Technology 54(4), 1–13 (2026). [3] Yue, Z., Yue, X., Yang, R., Wang, X., Li, W., Dai, S., Li, Y.: Progress of lithology identification technology while drilling. Journal of Mining Science and Technology 7(4), 389–402 (2022). [4] Si, L., Liu, Y., Wang, Z., Gu, J., Wei, D., Dai, J., Li, X., Zhao, Y.: Coal-rock recognition during drilling of anti-punch drilling robot based on improved 1DCNN-LSTM. Journal of Mining Science and Technology 11(1), 206–217 (2026). [5] Du, JS, Chen, J., Pu, YY, Jiang, DY, Chen, LL, Zhang, YR: Risk assessment of dynamic disasters in deep coal mines based on multi-source, multi-parameter indexes, and engineering application. Process Safety and Environmental Protection 155, 575–586 (2021). [6] Khanal, M., Qin, J., Shen, B., Dlamini, B.: Preliminary investigation into measurement while drilling as a means to characterize the coalmine roof. Resources 9(2), 10 (2020).[7] Zhang, W., Li, C., Jin, J., Qu, [8] Zagré, GE, Gamache, M., Labib, R., Shlenchak, V.: Machine learning algorithms for real-time coal recognition using monitor-while-drilling data. International Journal of Mining, Reclamation and Environment 38(1), 27–52 (2024). [9] Niu, G., Zhang, K., Yu, B., Chen, Y., Wu, Y., Liu, J.: Experimental study on comprehensive real-time methods to determine geological condition of rock mass along the boreholes while drilling in underground coal mines. Shock and Vibration 2019, Article ID 1045929 (2019).