|
|
|
| Inversion model of compressive strength of blasting rock mass based on ground-penetrating radar waves |
| XU Xianlei1*, YAN Kun1, 2, LI Pingfeng3, CAO Shilong1, 2 |
| (1. State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology (Beijing), Beijing 100083, China; 2. College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China; 3. Key Laboratory of Safe and Intelligent Mining in Non-coal Open-pit Mines, State Administration of Mine Safety Supervision, Hongda Blasting Engineering Group Co., Ltd., Guangzhou, Guangdong 510623, China) |
|
|
|
|
Abstract Intelligent blasting is a fundamental aspect of intelligent mine construction, where the compressive strength of the rock mass is a crucial parameter that characterizes the energy characteristics of blasting. To facilitate accurate and rapid predictions of rock mass compressive strength in blasting zones, an electromagnetic-mechanical response model was established, linking radar waves to rock mass compressive strength by integrating Maxwell?s equations with mechanical parameter equations. A novel neural network architecture was specifically designed to train and learn the parameters of this model. Utilizing ground-penetrating radar data and drilling-while-drilling data collected from open-pit mining areas, and incorporating rock mass density as input while constraining the drilling rate, the neural network was employed to predict regional rock mass compressive strength. Experimental results demonstrate a significant electromagnetic-mechanical response relationship between radar waves and rock mass compressive strength. The prediction accuracy of the proposed model exceeds 90%, confirming the feasibility of inverting rock mass compressive strength using radar wave data. In comparison to traditional backpropagation (BP) neural networks, the model developed in this study achieves higher prediction accuracy. Moreover, the three-dimensional compressive strength attribute model derived from the inversion clearly illustrates the spatial distribution patterns and variation trends of rock mass compressive strength. This methodology enables efficient, non-destructive inversion of rock mass compressive strength and offers substantial engineering value for guiding blast hole design, optimizing blasting parameters, and enhancing overall blasting efficiency.
|
|
|
|
|
|
[1] JING L. A review of techniques，advances and outstanding issues in numerical modelling for rock mechanics and rock engineering[J]. International Journal of Rock Mechanics and Mining Sciences，2003，40(3)：283–353.
[2] WANG Q，ZHANG Y，FENG G，et al. Research and application of the calculation method for vertical stress of interlayer rock in coal mining under pillar goaf[J]. Rock Mechanics and Rock Engineering，2025，58(11)：1–22.
[3] 王 鹏，房 凯，赵同彬，等. 基于压痕试验的岩石力学参数的卡尔曼滤波反演[J]. 山东科技大学学报：自然科学版，2024，43(4)：1–11.(WANG Peng，FANG Kai，ZHAO Tongbin，et al. Inversion of rock mechanical parameters with Kalman filter based on indentation test[J]. Journal of Shandong University of Science and Technology： Natural Science，2024，43(4)：1–11.(in Chinese))
[4] 刘学伟，刘云豪，刘 滨，等. 考虑分区劣化的围岩力学参数精细化反演机器学习模型研究[J]. 岩土工程学报，2025，47(11)：2 305–2 315.(LIU Xuewei，LIU Yunhao，LIU Bin，et al. Research on machine learning model for refined inversion of mechanical parameters of surrounding rock considering zonal deterioration[J]. Chinese Journal of Geotechnical Engineering，2025，47(11)：2 305–2 315.(in Chinese))
[5] SUN J，WU S，WANG H，et al. Inversion of surrounding rock mechanical parameters in a soft rock tunnel based on a hybrid model EO-LightGBM[J]. Rock Mechanics and Rock Engineering，2023，56(9)：6 691–6 707.
[6] DONG F，WANG S，YANG R，et al. Time-series traction prediction of surrounding rock deformation in tunnel construction based on mechanical parameter inversion[J]. Tunnelling and Underground Space Technology，2024，152：105933.
[7] HAKALA M，KUULA H，HUDSON J A. Estimating the transversely isotropic elastic intact rock properties for in situ stress measurement data reduction：A case study of the Olkiluoto mica gneiss，Finland[J]. International Journal of Rock Mechanics and Mining Sciences，2007，44(1)：14–46.
[8] ZHANG Z，WANG G，CARRANZA E J M，et al. An integrated machine learning framework with uncertainty quantification for three-dimensional lithological modeling from multi-source geophysical data and drilling data[J]. Engineering Geology，2023，324：107255.
[9] CHEN H. Seismic frequency component inversion for elastic parameters and maximum inverse quality factor driven by attenuating rock physics models[J]. Surveys in Geophysics，2020，41(4)：835–857.
[10] WU K，DESESQUELLES H，COCKENPOT R，et al. Ground- penetrating radar full-wave inversion for soil moisture mapping in Trench-Hill potato fields for precise irrigation[J]. Remote Sensing，2022，14(23)：6 046.
[11] ZHANG B，HE R，ZHANG H，et al. Diffraction separation by a coherence analysis framework for ground penetrating radar applications[J]. IEEE Transactions on Geoscience Remote Sensing，2023，61：1–15.
[12] TONG Z，GAO J，YUAN D. Advances of deep learning applications in ground-penetrating radar：A survey[J]. Construction Building Materials，2020，258：120371.
[13] LÓPEZ Y Á，GARCIA-FERNANDEZ M，ALVAREZ-NARCIANDI G，et al. Unmanned aerial vehicle-based ground-penetrating radar systems：A review[J]. IEEE Geoscience Remote Sensing Magazine，2022，10(2)：66–86.
[14] YANG H，ZENG X，WU X. An approach to solving Maxwell?s equations in time domain[J]. Journal of Mathematical Analysis and Applications，2023，518(1)：126678.
[15] CHEN G，CHACON L，YIN L，et al. A semi-implicit，energy-and charge-conserving particle-in-cell algorithm for the relativistic Vlasov-Maxwell equations[J]. Journal of Computational Physics，2020，407：109228.
[16] ASSYLBEKOV Y M，ZHOU T. Direct and inverse problems for the nonlinear time-harmonic Maxwell equations in Kerr-type media[J]. Journal of Spectral Theory，2020，11(1)：1–38.
[17] GREAVES R J，LESMES D P，LEE J M，et al. Velocity variations and water content estimated from multi-offset，ground-penetrating radar[J]. Geophysics，1996，61：683–695.
[18] 黄赵美，曹广勇，程 桦，等. 侏罗系冻结砂岩单轴抗压强度与孔隙度的关联性分析[J]. 煤矿安全，2020，51(6)：227–231.(HUANG Zhaomei，CAO Guangyong，CHENG Hua，et al. Correlation analysis of porosity and uniaxial compressive strength of jurassic frozen sandstone[J]. Safety in Coal Mines，2020，51(6)：227–231.(in Chinese))
[19] 李小军，张誉潇，荣棉水，等. 场地土层速度结构的贝叶斯反演方法及其应用[J]. 岩土力学，2025，46(7)：2 237–2 252.(LI Xiaojun，ZHANG Yuxiao，RONG Manshui，et al. Bayesian inversion method for soil layer velocity structure and its application[J]. Rock and Soil Mechanics，2025，46(7)：2 237–2 252.(in Chinese))
[20] 戴前伟，宁晓斌，张 彬. 基于共中心点道集约束的探地雷达波阻抗反演[J]. 煤田地质与勘探，2020，48(3)：211–218.(DAI Qianwei，NING Xiaobin，ZHANG Bin. Common midpoint gather constraint-based impedance inversion of ground penetrating radar[J]. Coal Geology and Exploration，2020，48(3)：211–218.(in Chinese))
[21] JAMES G，WITTEN D，HASTIE T，et al. An introduction to statistical learning：With applications in Python[M]. [S. l.]：Springer，2023：69–134.
[22] SINGH S，SHRIVASTAVA A. Evalnorm：Estimating batch normalization statistics for evaluation[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. [S.l.]：[s. n.]，2019：3 633–3 641.
[23] LIU Z，XU Z，JIN J，et al. Dropout reduces underfitting[C]// Proceedings of the International Conference on Machine Learning. [S. l.]：[s. n.]，2023：22 233–2 2248.
[24] XU J，LI Z，DU B，et al. Reluplex made more practical：Leaky ReLU[C]// Proceedings of the 2020 IEEE Symposium on Computers and Communications(ISCC). [S. l.]：[s. n.]，2020：1–7.
[25] BALASUNDARAM S，PRASAD S C. Robust twin support vector regression based on Huber loss function[J]. Neural Computing and Applications，2020，32(15)：11 285–11 309.
[26] 刘勇斌，张晓平，李馨芳，等. 基于冲击回转钻进的岩石强度随钻识别研究[J]. 岩土力学，2024，45(3)：857–866.(LIU Yongbin，ZHANG Xiaoping，LI Xinfang，et al. Rock strength identification while drilling based on percussive rotary drilling[J]. Rock and Soil Mechanics，2024，45(3)：857–866.(in Chinese))
|
|
|
|
2026, Vol. 45 
