Multi-Factor Prediction of Water Inflow from the Working Face Based on an Improved SSA-RG-MHA Model DOI Open Access
Yingying Ding, Shangxian Yin, Zhenxue Dai

et al.

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3390 - 3390

Published: Nov. 25, 2024

The accurate prediction of mine water inflow is very important for design and safe production. existing forecasting methods based on single factors are often less stable. Multi-factor data-driven models play a key role in predicting without taking physical changes into account. Therefore, multi-factor method an improved SSA-RG-MHA model introduced this study. uses two sets data related to as the input improve accuracy stability. first applies residual network (ResNet) mitigate problems disappearing gradients explosions. Gated Recurrent Units (GRUs) then used learn characteristics long-term sequence data. combines ResNet GRU new architecture incorporates multiple attention (MHA) mechanism focus information at different time scales. Finally, optimized sparrow search algorithm (SSA) optimize parameters global ability avoid local optimization. affected by many factors, among which level microseismic energy particularly important. these types selected variables prediction. experimental results show that significantly reduces error: mean absolute error (MAE), root square (RMSE), percentage (MAPE) were reduced 4.42 m3/h, 7.17 5%, respectively. more stable reliable than single-factor it comprehensively considers affecting working face. Compared with other models, exhibits higher robustness, providing basis hazard monitoring early warning.

Language: Английский

Construction and application of optimized model for mine water inflow prediction based on neural network and ARIMA model DOI Creative Commons
Xiaoyu Gong, Bo Li, Yang Yu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 15, 2025

Mine water influx is a significant geological hazard during mine development, influenced by various factors such as conditions, hydrology, climate, and mining techniques. This phenomenon characterized non-linearity high complexity, leading to frequent accidents in coal mines. These not only impact production quality but also jeopardize the safety of staff. In order better predict amount surging mines provide an important basis for damage prevention work, based on time series data from January 2020 February 2023 Northern Guizhou Province Longfeng Coal Mine, BP-ARIMA prediction model was established combining BP neural network ARIMA autoregressive sliding average model, It predicted total 6 months July 2022 2023, compared results with four models, namely, traditional method Large well method, GM(1,1) grey used absolute relative error calculation accuracy. The show that BP-ARIMA(3,1,1) much closer actual value, 1.02% maximum 3.036%, goodness fit R² 0.93, which than other single substantially improves accuracy influx. Furthermore, utilizing future predictions were made, offering scientific foundation effective control measures.

Language: Английский

Citations

2
Deformation properties of rock strata based on angular displacement and its hydrogeological significance DOI Creative Commons
Cunjin Lu,

Hui Zhao,

Jinpeng Xu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 25, 2025

The deformation behavior of the roof and floor strata during coal seam mining plays a critical role in development mining–induced fractures is an intrinsic factor prevention control rock dynamic disasters, such as mine water hazards. This study investigates values failure angle displacement based on performance through both laboratory field experiments. A method for assessing condition using differences proposed. results indicated that when angular was greater than value, layer destroyed, value related to lithology, thickness cross–sectional area. with high strength larger, sandstone 0.0552 ° average, limestone 0.0818 °. small under unit load resulting deformation. 5.45 × 10− 6 / N, 4.41 °/ N. larger area smaller. 50 mm were 0.0516 0.0774 °, respectively, less 30 150 0.0483 0.0720 which 120 40 difference between (θi) (θ0) stress leads time sequence horizontal vertical 'anisotropic seepage' law groundwater. It more convenient use criterion judging traditional mechanical criterion. research have important practical significance strata, analyzing movement groundwater, calculating depth water–conducting fracture zone zone.

Language: Английский

Citations

1
Evolution of Overlying Strata Bed Separation and Water Inrush Hazard Assessment in Fully Mechanized Longwall Top-Coal Caving of an Ultra-Thick Coal Seam DOI Open Access
Shun Liang, Xuepeng Zhang, Fang Ke

et al.

Water, Journal Year: 2025, Volume and Issue: 17(6), P. 850 - 850

Published: March 16, 2025

Bed-separation water hazards are a common and very harmful mining disaster in the areas of western China recent years, which seriously threatens safe rich thick coal seam resources West. The Yonglong area has become high-risk for bed-separation due to its particularly seams strong water-rich overlying strata. In view this, this paper investigates development height water-flowing fractured zone fully mechanized caving an ultra-thick area, evolution law bed separation strata, process inrush from separation. Based on measured data several surrounding mines, prediction formula suitable geological conditions was fitted. By using discrete element numerical simulation laboratory similarity simulation, strata under study analyzed, space summarized into “four zones, three arches, five zones”. Through stress-seepage coupling roof seam, migration, accumulation, sudden aquifer influence were variation pore pressure during summarized. showed trend first decreasing, then increasing, and, finally, stabilizing. Combined with height, volume, zoning characteristics 1012007 working face Yuanzigou Coal Mine, danger evaluated. It is believed that it formation accumulation separation, risk high. Prevention control measures need be taken site ensure safety. research results have important guiding significance assessment prevention longwall top-coal similar worldwide.

Language: Английский

Citations

1
Quantitative correlation between fracture fractal and overburden deformation due to the multiple layers backfill mining DOI
Jiawei Liu, Wanghua Sui,

Zhongwen Duan

et al.

Bulletin of Engineering Geology and the Environment, Journal Year: 2025, Volume and Issue: 84(2)

Published: Jan. 18, 2025

Language: Английский

Citations

0
Stability Analysis and Failure Control of Composite Roof in Mining Roadway Considering Plastic Zone Expansion DOI Creative Commons
Kun Pan,

Biao Hou,

Zhen Zhang

et al.

Energy Science & Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 19, 2025

ABSTRACT To address the problems of large deformation surrounding rock, failure support, and even roof fall under influence severe mining in return airway panel I0116 3 06 Mindong No.1 Coal Mine, fracture evolution characteristics law roadway composite were investigated through numerical simulation, theoretical analysis, on‐site detection. With continuous magnitude direction main stress rock with a roof, following observations made: first, plastic occurred shallow area; second, because undamaged hard coal seam cannot block expansion zone, zone crosses expands into deep part. The strong pressure caused by expanding interlayer leads to tensile at middle lower part seam, overall instability. According evolutionary pattern roadway, multi‐level coupling support technology (MCST) focusing on morphology is applied test roadway. field monitoring results reveal that application effect satisfactory.

Language: Английский

Citations

0
Geological Safety of Water Inrush in Complex Seabed Mining: A Case Study of X Gold Mine DOI
Jianshu Liu, Zhuoying Tan, Zhou Zhi

et al.

Mining Metallurgy & Exploration, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 15, 2025

Language: Английский

Citations

0
Research on dynamic prediction method of the water inflow in tunnels under complex geological conditions based on the non-darcy flow-energy method DOI
Guanqing Wang, Jianjun Luo, Ziwei Zhang

et al.

Bulletin of Engineering Geology and the Environment, Journal Year: 2025, Volume and Issue: 84(3)

Published: Feb. 26, 2025

Language: Английский

Citations

0
Dynamic Evolution of Fractures in Overlying Rocks Caused by Coal Mining Based on Discrete Element Method DOI Open Access

XU Jun-yu,

Jienan Pan,

Meng Li

et al.

Processes, Journal Year: 2025, Volume and Issue: 13(3), P. 806 - 806

Published: March 10, 2025

Mining-induced fractures and overlying rock movement change layer porosity permeability, raising water intrusion risks in the working face. This study explores fracture development face 31123-1 at Dongxia Coal Mine using UDEC 7.0 software theoretical analysis. The is a dynamic, spatially evolving process. As advances, water-conducting zone height (WFZH) increases stepwise, their relationship follows an S-shaped curve. Numerical simulations give WFZH of about 112 m fracture–mining ratio 14.93. Empirical formulas suggest 85.43 to 106.3 11.39 14.17. Key stratum theory calculations show that mining-induced reach 16th coarse-sandstone layer, with 97 113 12.93 15.07. Simulations confirm trapezoidal bottom angles 48° 50°, consistent mechanics theories. A fractal permeability model for mined overburden, based on K-C equation, shows positively correlates dimension. These results verify reliability analyses, guiding mining control this similar faces.

Language: Английский

Citations

0
Fractal interpretation and forewarning of mining area disasters via microseismic time-space-energy nested DOI
Congcong Zhao, Zilong Zhou, Dazhao Song

et al.

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2025, Volume and Issue: unknown, P. 103905 - 103905

Published: March 1, 2025

Language: Английский

Citations

0
Research on Data-Driven Prediction of Inrush Probability in Coal Mines Under the Mechanism of Feature Reconstruction in Information Interconnectivity DOI Open Access
Shuyuan Xu,

Peng Zhi-wen,

Qiushuang Zheng

et al.

Water, Journal Year: 2025, Volume and Issue: 17(6), P. 843 - 843

Published: March 14, 2025

As coal mining extends deeper, the complexities of groundwater systems and instability geological formations exacerbate challenges accurately investigating preventing water inrush incidents in mines. To tackle issues stemming from multifaceted causes such difficulties associated with data acquisition—coupled a limited sample size leading to prediction inaccuracies—this study introduces bicubic interpolation augmentation algorithm presents data-driven CNN-ResNet-RF model designed for effective expansion. The technique adeptly extracts correlational information evidence chain related events, thereby enriching training dataset. CNN facilitates extraction preliminary features augmented input variables through convolution pooling, which are subsequently concatenated raw derived ResNet. enriched reconstructed then inputted into Random Forest predict probability operations. Empirical validation reveals that coupled significantly enhances data, outperforming conventional predictive models. model’s efficacy is evidenced by RMSE 0.5946, MAE 0.4666, MAPE 0.38%, R2 0.9072. This method provides an accurate representation nonlinear dynamics mine inrushing—a process governed numerous factors characterized small dataset complex formation mechanism. Ultimately, it enables precise assessments high-risk areas, offering theoretical decision-making support proactive implementation targeted mitigation strategies.

Language: Английский

Citations

0