Intelligent prediction method of rockburst driven by microseismic temporal features in deep near-vertical coal seams
International Journal of Minerals, Metallurgy and Materials · 2026-07 · 33 (7) · 2403-2418
DOI: 10.1007/s12613-026-3408-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Minerals, Metallurgy and Materials, online erschienen am 17.08.2026. Verfasst von Huicong Xu und 9 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
Rockburst has become a major hazard constraining safe production and high-quality capacity release in China’s coal mines. During deep mining of near-vertical seams within the Tianshan seismic belt, the coupling of nonlinear coal-rock deformation responses with complex geological conditions markedly elevates rockburst risk. To meet the strategic demand for intelligent, safe, and efficient mining in rockburst-prone seams, this study integrates geophysics, spatial statistics, big data mining, and deep learning to investigate a steeply dipping coal mine in Xinjiang, China, and systematically analyze the relationship between microseismic activity parameters and mining-induced disturbances. On this basis, a temporal fusion feature identification method for microseismic indicators is proposed. By embedding temporal constraints into a deep-learning framework, an enhanced temporal fusion transformer (TFT) is developed to predict multiple microseismic indicators. Furthermore, an intelligent rockburst prediction and early-warning approach driven by fused microseismic parameters is established and validated in field applications. Results indicate that hazard risk in the sandwiched rock pillar and the B 6 roof areas increases with working-face advance, and the localized damage in the sandwiched rock pillar is more severe than that in the B 6 roof. To strengthen feature extraction, a WFTBlock is introduced by combining continuous wavelet transform, Fourier transform, and timestamp alignment to reveal the periodic evolution of spectral and phase characteristics in indicator sequences. The final multi-parameter TFT model is trained jointly with fused features and temporal inputs. Compared with the long short-term memory (LSTM) baseline, the proposed model reduces root mean square error (RMSE) by 47.9% and improves coefficient of determination ( R 2 ) by 54.5%, demonstrating substantially enhanced predictive accuracy. Overall, the proposed framework provides technical support for safe and efficient mining of steeply dipping seams and the secure development of key energy bases along the Belt and Road Initiative.
Zitieren
APA
Xu, H., Li, K., Lai, X., Shan, P., Zhang, B., Dai, L., Yang, S., Guo, Q., Xi, X., & Yan, Z. (2026). Intelligent prediction method of rockburst driven by microseismic temporal features in deep near-vertical coal seams. International Journal of Minerals, Metallurgy and Materials, 33(7), 2403-2418. https://doi.org/10.1007/s12613-026-3408-7
Vancouver
Xu H, Li K, Lai X, Shan P, Zhang B, Dai L, et al. Intelligent prediction method of rockburst driven by microseismic temporal features in deep near-vertical coal seams. International Journal of Minerals, Metallurgy and Materials. 2026;33(7):2403-2418. doi:10.1007/s12613-026-3408-7
BibTeX
@article{Xu2026,
author = {Xu, Huicong and Li, Kai and Lai, Xingping and Shan, Pengfei and Zhang, Bo and Dai, Lianpeng and Yang, Shangtong and Guo, Qifeng and Xi, Xun and Yan, Zhongming},
title = {Intelligent prediction method of rockburst driven by microseismic temporal features in deep near-vertical coal seams},
journal = {International Journal of Minerals, Metallurgy and Materials},
year = {2026},
volume = {33},
number = {7},
pages = {2403--2418},
doi = {10.1007/s12613-026-3408-7}
}
EUVIMED