Karst Feature-Level Data Fusion of Comprehensive Exploration Data Using Improved DS Evidence Theory Algorithm
-
摘要: 地下岩溶会给陆路交通工程基础设施的设计、施工和安全运行带来巨大的安全隐患.为探明地下岩溶发育情况，对空天地多源异构综合勘察数据，包括遥感解译、工程地质调绘、钻孔、物探高密度电法和瞬变电磁法解译成果资料，统一时空坐标和数据标准，实现岩溶不良地质体的数据级融合.在此基础上，建立地下岩溶不良地质体的识别框架，构建地下空间点域初始基本概率分配函数赋值方法，采用基于Kendall相关系数改进的DS证据理论算法，对综合勘察数据证据进行多源数据融合获取岩溶评价指标，三维空间插值网格化后进行岩溶特征三维成像.结果表明，改进DS算法有效解决了综合勘察成果间的高度冲突问题，形成对岩溶目标体的智能决策，实现了综合勘察解译成果的岩溶地质信息特征级融合.融合结果的三维成像，提高了地下岩溶不良地质体勘察的可靠性和精度，提升工作效率30%以上.DS智能融合算法为陆路交通工程在设计、施工和运行的全寿命周期条件下，处置岩溶灾害提供了有效的方法指导和合适的评价手段.Abstract: Underground Karst formations pose significant safety risks to the design, construction, and safe operation of land transportation projects. To investigate the development of underground karst, comprehensive multi-source heterogeneous survey data were utilized, including remote sensing interpretation, engineering geological mapping, drill hole data, and the results from electrical resistivity tomography and transient electromagnetic methods. These data were unified in terms of temporal and spatial coordinates and standards to achieve data-level fusion of adverse karst geological bodies. Based on this foundation, a recognition framework for underground karst geological bodies was established. A method for assigning initial basic probability assignment (BPA) functions to underground spatial point domain was developed, and a modified Dempster-Shafer (DS) evidence theory algorithm based on Kendall's correlation coefficient was employed for multi-source data fusion to obtain karst evaluation indices. After 3D spatial interpolation, 3D imaging of karst features was plotted. The results indicate that the improved DS algorithm effectively solves the conflicts among comprehensive survey evidence, enabling intelligent decision-making regarding karst targets. The improved DS algorithm facilitated the integration of karst geological information features from comprehensive survey results. The 3D imaging of the integrated results enhanced the reliability and accuracy of underground karst geological body investigations, increasing work efficiency by 30% or more, and providing methodological guidance and evaluation tools for engineering design, construction, and operation.
-
Key words:
- DS evidence theory /
- karst /
- data fusion /
- comprehensive survey /
- multi-source heterogeneous data /
- geophysics
-
图 2 地下空间点域（球形子域）综合勘察数据点分布示意图
Fig. 2. Schematic diagram of distribution of comprehensive survey data points in underground space point domain (spherical domain)
图 3 基于DS证据理论的岩溶特征级融合算法与三维成像流程图
Fig. 3. Flowchart of karst feature-level data fusion algorithm and 3D imaging based on DS evidence theory
图 6 钻探、物探高密度电法、瞬变电磁法溶洞三维数据级融合图
钻孔岩心：红色表示溶洞；绿色为溶蚀性灰岩；蓝色为其他岩性（非岩溶）
Fig. 6. 3D data-level fusion map of karst by drill hole, geophysical electrical resistivity tomography and transient electromagnetic methods
图 9 地形、断层、溶洞智能融合三维图
Fig. 9. 3D map of terrain, fault, and karst data-level fusion results
表 1 基本概率指派函数值
Table 1. Basic probability assignment value
指标 命题A1岩溶 命题A2非岩溶 指标1：遥感解译资料m1 0.60 0.40 指标2：工程地质调绘资料m2 0.60 0.40 指标3：钻孔岩心资料m3 1.00 0.00 指标4：高密度电法解译资料m4 0.00 1.00 指标5：瞬变电磁法解译资料m5 0.00 1.00 
下载: 导出CSV
表 2 传统与改进DS证据理论算法的结果
Table 2. The results of traditional and improved DS evidence theory algorithms
证据合成算法 k m(A1) m(A2) 备注 传统DS证据理论算法 1 - - 完全冲突，无法计算 改进DS证据理论算法 0.87 0.69 0.31
下载: 导出CSV
表 3 勘察完成工作量
Table 3. Comprehensive survey workload
工作项目 单位 工作量 带状工程地质调绘 km 0.64 遥感解译 km2 0.80 工程地质钻探 m/孔 5 932.63/120 物探高密度电法 km 1.43 物探瞬变电磁法 km 0.55
下载: 导出CSV
-
Bai, C. H., 2021. Research on Intelligent Prediction Method of Hazard Risk of Waterand Mudinrush in Karst Tunnel Based on Machine Learning (Dissertation). Shandong University, Jinan, 35-55 (in Chinese with English abstract). Chen, N., Xie, W., 2022. Research on Risk of Liquidity Cargo Shipping Based on Combined Weighting-DS Evidence Theory. Journal of Safety and Environment, 22(2): 623-633 (in Chinese with English abstract). Chen, Z., Yuan, H., Huang, P. Y., et al., 2023. Safety Risk Evaluation of Tunnel Collapse Based on Bayesian Network of Improving Conditional Probability. Journal of Central South University (Science and Technology), 54(1): 327-340 (in Chinese with English abstract). Dempster, A. P., 1967. Upper and Lower Probabilities Induced by a Multivalued Mapping. The Annals of Mathematical Statistics, 38(2): 325-339. https://doi.org/10.1214/aoms/1177698950 Hou, S. J., 2023. Study on the Prediction Model of Surrounding Rock Deformation in Soft Rock Tunnel Based on Multivariate Algorithm Fusion and Its Application. Modern Tunnelling Technology, 60(6): 151-164 (in Chinese with English abstract). Hu, L. Y., Huang, L., Wen, J. G., 2023. Discussion on Geophysical Exploration Technology and Digital Development in Geotechnical Engineering Investigation-Take a Karst Area in Wuhan as an Example. Informatization of China Construction, 29(7): 84-87 (in Chinese with English abstract). Huang, Z. Y., Lin, R. M., Liu, H., et al., 2024. Multi-Source Network Security Data Fusion Model Based on DS Evidence Theory. Modern Electronics Technique, 47(7): 115-121 (in Chinese with English abstract). Lei, W. P., Yin, J., Chen, S. S., et al., 2022. Application of Comprehensive Electrical Method in Karst Exploration of Water Diversion Line. Express Water Resources & Hydropower Information, 43(S2): 23-26, 31 (in Chinese with English abstract). Li, B. C., Wang, B., Wei, J., et al., 2002. An Efficient Combination Rule of Evidence Theory. Journal of Data Acquisition & Processing, 17(1): 33-36 (in Chinese with English abstract). Li, J., Yang, X. Z., Zhou, L., 2019. Research on Target Identification Based on Improved DS Evidence of Multi-Period Fusion Method. Fire Control & Command Control, 44(7): 43-48 (in Chinese with English abstract). Luo, L. R., Liu, Z. G., 2011. Comparative Analysis of Geological Prediction Methods in Karst Aeras. Chinese Journal of Geotechnical Engineering, 33(S1): 351-355 (in Chinese with English abstract). Luo, Y. M., 2024. Improvement of Dempster-Shafer Evidence Theory and Its Application in Debris Flow Hazard Assessment Model (Dissertation). Yunnan Normal University, Kunming, 16-33 (in Chinese with English abstract). Peng, C., 2016. The Combined Application of Seismic Imaging Method and High-Density Electric Method to the Survey of Karst Collapse Areas. Chinese Journal of Engineering Geophysics, 13(1): 60-63 (in Chinese with English abstract). Shafer, G. A., 1976. Mathematical Theory of Evidence. Princeton University Press, Princeton. Song, X. P., Xiao, J. Y., Wu, K. F., et al., 2021. Improved D-S Evidence Theory Algorithm for Solving Conflict Evidence Combination Problem. Journal of Hubei Minzu University (Natural Science Edition), 39(2): 180-186 (in Chinese with English abstract). Sun, Q., Ye, X. Q., Gu, W. K., 2000. A New Combination Rules of Evidence Theory. Acta Electronica Sinica, 28(8): 117-119 (in Chinese with English abstract). Sun, Y. J., Yu, G. Z., Shi, G., et al., 2001. The Cross-Well Seismic Computerized Tomography Technology and It's Application in the Cavern Survey. Computerized Tomography Theory and Applications, 10(4): 10-13 (in Chinese with English abstract). Wang, A. N., Li, Y. S., He, Z., 2020. State Evaluation of Fire Control System Based on Fusion of D-S Evidence Theory and Rough Set. Control Engineering of China, 27(12): 2176-2184 (in Chinese with English abstract). Wang, H., Wei, B., Li, S. Q., et al., 2024. Fault Diagnosis of a DC Distribution Network Based on Bayesian Network Information Fusion. Power System Protection and Control, 52(5): 61-72 (in Chinese with English abstract). Wang, K., 2024. Integration of Some Survey Methods to Detect the High-Speed Railway Tunnel Basement Karst-A Case Study of the Huajiashan Tunnel. Chinese Journal of Engineering Geophysics, 21(5): 810-819 (in Chinese with English abstract). Wang, X., Xu, T., Ran, J., et al., 2023. Identification and Evaluation on Shield Construction Risk of Metro Tunnel in Karst Area. Railway Investigation and Surveying, 49(3): 5-11 (in Chinese with English abstract). Yager, R. R., 1987. On the Dempster-Shafer Framework and New Combination Rules. Information Sciences, 41(2): 93-137. https://doi.org/10.1016/0020-0255(87)90007-7 Yang, C. J., Pu, C., Xiong, H. M., et al., 2024. Research on Inrush Water Prediction Based on Fuzzy Analytic Hierarchy Process. Shanxi Architecture, 50(19): 167-170 (in Chinese with English abstract). Yang, Y. H., Huang, Z. F., 2001. Karst Geological Problems and Their Countermeasures in Southern Hubei Section of Beijing-Zhuhai Speedway. Earth Science, 26(4): 361-364 (in Chinese with English abstract). Zadeh, L. A., 1984. Review of Shafer's a Mathematical of Evidence. AI Magazine, 5(3): 81-83. Zhang, H., Lu, J. G., Tang, X. H., 2020. An Improved DS Evidence Theory Algorithm for Conflict Evidence. Journal of Beijing University of Aeronautics and Astronautics, 46(3): 616-623 (in Chinese with English abstract). Zhang, Y., 2021. The Application of Integrated Geophysical Prospecting Technology in Karst Exploration of Railway Subgrade. Chinese Journal of Engineering Geophysics, 18(5): 738-743 (in Chinese with English abstract). 柏成浩, 2021. 基于机器学习的岩溶隧道突水突泥灾害风险智能预测方法研究(硕士学位论文). 济南: 山东大学, 35-55. 陈宁, 谢旺, 2022. 基于组合赋权-DS证据理论的易流态化货物海运风险研究. 安全与环境学报, 22(2): 623-633. 陈钊, 袁航, 黄鹏宇, 等, 2023. 基于改进条件概率的贝叶斯网络隧道坍塌安全风险评价. 中南大学学报(自然科学版), 54(1): 327-340. 侯守江, 2023. 基于多元算法融合的软岩隧道围岩变形预测模型及应用研究. 现代隧道技术, 60(6): 151-164. 胡励耘, 黄亮, 文家刚, 2023. 论岩土工程勘察中物探技术及数字化发展——以武汉某岩溶地段为例. 中国建设信息化, 29(7): 84-87. 黄智勇, 林仁明, 刘宏, 等, 2024. 基于DS证据理论的多源网络安全数据融合模型. 现代电子技术, 47(7): 115-121. 雷伟平, 尹剑, 陈爽爽, 等, 2022. 综合电法在引水线路岩溶勘察中的应用. 水利水电快报, 43(S2): 23-26, 31. 李弼程, 王波, 魏俊, 等, 2002. 一种有效的证据理论合成公式. 数据采集与处理, 17(1): 33-36. 李捷, 杨雪洲, 周亮, 2019. 基于改进DS理论多周期数据融合的目标识别方法. 火力与指挥控制, 44(7): 43-48. 李文立, 郭凯红, 2010. D-S证据理论合成规则及冲突问题. 系统工程理论与实践, 30(8): 1422-1432. 罗利锐, 刘志刚, 2011. 岩溶地区超前地质预报方法对比分析. 岩土工程学报, 33(S1): 351-355. 罗雨梦, 2024. D-S证据理论的改进及其在泥石流危险性评价模型中的应用(硕士学位论文). 昆明: 云南师范大学, 16-33. 彭超, 2016. 地震映象法与高密度电法在岩溶塌陷勘察中的联合应用. 工程地球物理学报, 13(1): 60-63. 宋香鹏, 肖建于, 吴克凤, 等, 2021. 解决冲突证据合成问题的改进D-S证据理论算法. 湖北民族大学学报(自然科学版), 39(2): 180-186. 孙全, 叶秀清, 顾伟康, 2000. 一种新的基于证据理论的合成公式. 电子学报, 28(8): 117-119. 孙跃军, 俞国柱, 石桂, 等, 2001. 井间地震层析成像技术及其在岩溶勘察中的应用. CT理论与应用研究, 10(4): 10-13. 王嫒娜, 李英顺, 贺喆, 2020. D-S证据理论融合粗糙集的火控系统状态评估. 控制工程, 27(12): 2176-2184. 王鹤, 韦搏, 李石强, 等, 2024. 基于贝叶斯网络信息融合的直流配电网故障诊断方法. 电力系统保护与控制, 52(5): 61-72. 王凯, 2024. 多种勘察方法探测高铁隧道基底岩溶——以华家山隧道为例. 工程地球物理学报, 21(5): 810-819. 王祥, 徐甜, 冉军, 等, 2023. 岩溶地区地铁隧道盾构施工风险识别与评价研究. 铁道勘察, 49(3): 5-11. 杨超杰, 蒲超, 熊昊旻, 等, 2024. 基于模糊层次分析法的涌突水预测研究. 山西建筑, 50(19): 167-170. 杨银湖, 黄正发, 2001. 京珠线湖北省南段岩溶地质问题与勘察对策. 地球科学, 26(4): 361-364. http://www.earth-science.net/article/id/851 张欢, 陆见光, 唐向红, 2020. 面向冲突证据的改进DS证据理论算法. 北京航空航天大学学报, 46(3): 616-623. 张业, 2021. 综合物探方法在铁路路基岩溶勘察中的应用. 工程地球物理学报, 18(5): 738-743. -
点击查看大图
图(9) / 表(3)
计量
- 文章访问数: 130
- HTML全文浏览量: 11
- PDF下载量: 1
- 被引次数: 0
