Research on intelligent tunnel support method based on IPSO-MOC-RF algorithm
MA Chunchi1，LI Xiang1，XU Hongwei1，LI Tianbin1，MA Zhiguo2，ZHANG Hang3
(1. State Key Laboratory of Geohazard Prevention and Geoenvironment Protection，Chengdu University of Technology，Chengdu，Sichuan 610059，China；2. Sichuan Chuanjiao Cross Road and Bridge Co.，Ltd.，Guanghan，Sichuan 618300，China；
3. Chongqing City Construction Investment(Group) Co.，Ltd.，Chongqing 400023，China)
Abstract：The idea of intelligent tunnel support is an effective solution to the problem of low matching degree between tunnel support parameters and actual geological conditions. However，the research and implementation of tunnel intelligent support method are few，and the establishment and application of this method is in great demand. In this paper，by improving random forest algorithm and particle swarm optimization algorithm，an IPSO-MOC-RF intelligent decision algorithm adapted to multi-label and multi-output data types was proposed to analyze the complex and diverse support parameters of tunnels. The tunnel support parameter system was established according to three research scenarios of tunnel survey and design stage，construction stage and rock burst disaster，and 285，480 and 543 data samples were collected respectively for training models. According to the training results，the MR values were 0.886，0.917，0.897，and Hamming Loss values were 0.046–0.091，respectively，which verified that the model could effectively extract the complex nonlinear mapping characteristics between geological indicators and tunnel support parameters. In addition，a tunnel intelligent support platform was established by integrating BIM model and intelligent decision model with Cesium cloud platform，and applied to the Grand Canyon tunnel of the Ehan expressway in China. The validity of the intelligent tunnel support decision is verified by statistical analysis，theoretical analysis and field continuous monitoring. The results show that only 1 of the 7 samples in the survey and design stage failed；only 3 of the 47 samples in the construction stage failed，and the 3 selected test sections were all successful(the maximum displacement of the tunnel vault and side wall were 36.4 mm and 25.8 mm，respectively)；the three test sections of rockburst disasters were successful. The application effect of intelligent tunnel support model is remarkable，which verifies the feasibility of the practical application of this method，and provides a new idea for the research of intelligent tunnel construction.
马春驰1，李 想1，徐洪伟1，李天斌1，马志国2，张 航3. 基于IPSO-MOC-RF算法的隧道智能支护方法研究[J]. 岩石力学与工程学报, 2024, 43(3): 556-572.
MA Chunchi1，LI Xiang1，XU Hongwei1，LI Tianbin1，MA Zhiguo2，ZHANG Hang3. Research on intelligent tunnel support method based on IPSO-MOC-RF algorithm. , 2024, 43(3): 556-572.
[1] 徐建平，桑运龙，刘学增，等. 节理发育岩体隧道支护的动态设计方法与应用[J]. 地下空间与工程学报，2017，13(2)：416–421.(XU Jianping，SANG Yunlong，LIU Xuezeng，et al. Observational method and its application for tunnel supporting in jointed rock[J]. Chinese Journal of Underground Space and Engineering，2017，13(2)：416–421.(in Chinese))
[2] 中华人民共和国行业标准编写组. JTG 3370.1—2018公路隧道设计规范[S]. 北京：人民交通出版社，2018.(The Professional Standards Compilation Group of People?s Republic of China. JTG 3370.1—2018 Code for design of highway tunnel[S]. Beijing：China Communications Press，2018.(in Chinese))
[3] 王建宇，王 锋. 隧道支护系统设计的模糊类比方法[J]. 土木工程学报，1990，23(4)：51–59.(WANG Jianyu，WANG Feng. Fuzzy analogy method for tunnel support system design[J]. China Civil Engineering Journal，1990，23(4)：51–59.(in Chinese))
[4] CHEN Y X，LI L P，ZHOU Z Q，et al. Support scheme optimization aimed at the asymmetric deformation of the supported rock in a deep tunnel[J]. Arabian Journal of Geosciences，2022，15(6)：505–521.
[5] 李德军，于程硕，谢东武. 大跨度城市山岭隧道初期支护参数优化研究[J]. 现代隧道技术，2020，57(增1)：387–393.(LI Dejun，YU Chengshuo，XIE Dongwu. Optimization of initial support parameters for large-span urban mountain tunnels[J]. Modern Tunnelling Technology，2020，57(Supp.1)：387–393.(in Chinese))
[6] LIU Q W，LI Y S，LI W T，et al. Primary support optimization of large-span and shallow buried hard rock tunnels based on the active support concept[J]. Scientific Reports，2022，12(1)：1–21.
[7] 梅 竹. 单线重载铁路隧道复合式衬砌结构优化研究[J]. 隧道建设(中英文)，2021，41(9)：1 547–1 554.(MEI Zhu. Optimization of composite lining structure of a single-track heavy-haul railway tunnel[J]. Tunnel Construction，2021，41(9)：1 547–1 554.(in Chinese))
[8] 黄海昀，仇文革，黄 黆，等. 石质铁路隧道初期支护优化研究[J]. 铁道科学与工程学报，2019，16(1)：152–161.(HUANG Haiyun，QIU Wenge，HUANG Guang，et al. Study on primary support optimization for railway tunnel in rock[J]. Journal of Railway Science and Engineering，2019，16(1)：152–161.(in Chinese))
[9] 仇文革，孙克国，王立川，等. 基于围岩稳定性的大断面隧道初期支护优化[J]. 土木工程学报，2017，50(增2)：8–13.(QIU Wenge，SUN Keguo，WANG Lichuan，et al. Primary support optimization of large section tunnel based on surrounding rock stability[J]. China Civil Engineering Journal，2017，50(Supp.2)：8–13.(in Chinese))
[10] LIU K Y，LIU B G. Intelligent information-based construction in tunnel engineering based on the GA and CCGPR coupled algorithm[J]. Tunnelling and Underground Space Technology，2019，88：113–128.
[11] FENG X T，ZHANG C Q，QIU S L，et al. Dynamic design method for deep hard rock tunnels and its application[J]. Journal of Rock Mechanics and Geotechnical Engineering，2016，8(4)：443–461.
[12] LIU K Y，LIU B G，FANG Y. An intelligent model based on statistical learning theory for engineering rock mass classification[J]. Bulletin of Engineering Geology and the Environment，2019，78(6)：4 533–4 548.
[13] 柳厚祥，李汪石，查焕奕，等. 基于深度学习技术的公路隧道围岩分级方法[J]. 岩土工程学报，2018，40(10)：1 809–1 817.(LIU Houxiang，LI Wangshi，ZHA Huanyi，et al. Method for surrounding rock mass classification of highway tunnels based on deep learning technology[J]. Chinese Journal of Geotechnical Engineering，2018，40(10)：1 809–1 817.(in Chinese))
[14] 夏述光，刘 辉，何玉清，等. 围岩模糊信息分级模型在软岩隧道中的应用[J]. 隧道建设，2008，28(2)：137–139.(XIA Shuguang，LIU Hui，HE Yuqing，et al. Application of fuzzy information classification model of surrounding rock in soft rock tunnel[J]. Tunnel Construction，2008，28(2)：137–139.(in Chinese))
[15] 杨小永，伍法权，苏生瑞. 公路隧道围岩模糊信息分类的专家系统[J]. 岩石力学与工程学报，2006，25(1)：100–105.(YANG Xiaoyong，WU Faquan，SU Sshengrui. Expert system of fuzzy information for classification of surrounding rock mass in highway tunnel[J]. Chinese Journal of Rock Mechanics and Engineering，2006，25(1)：100–105.(in Chinese))
[16] YANG G，LI T B，MA C C，et al. Intelligent rating method of tunnel surrounding rock based on one-dimensional convolutional neural network[J]. Journal of Intelligent and Fuzzy Systems，2022，42(3)：2 451–2 469.
[17] ZHAO S G，WANG M N，YI W H，et al. Intelligent classification of surrounding rock of tunnel based on 10 machine learning algorithms[J]. Applied Sciences，2022，12(5)：2 656–2 675.
[18] 马世伟，李守定，李 晓，等. 隧道岩体质量智能动态分级KNN方法[J]. 工程地质学报，2020，28(6)：1 415–1 424.(MA Shiwei，LI Shouding，LI Xiao，et al. KNN method for intelligent observational classification of rock mass quality in tunnel[J]. Journal of Engineering Geology，2020，28(6)：1 415–1 424.(in Chinese))
[19] LI X，WANG Q. Prediction of surrounding rock classification of highway tunnel based on PSO-SVM[C]// International Conference on Robots and Intelligent System (ICRIS)，IEEE. [S. l.]：[s. n.]，2019：443–446.
[20] 任建喜. 岩体隧道支护神经网络决策系统[J]. 西安公路交通大学学报，1998，18(4)：61–64.(REN Jianxi. Neural network decision system for rock mass tunnel supporing[J]. Journal of Xi?an Highway University，1998，18(4)：61–64.(in Chinese))
[21] 魏莉萍，张 清. 隧道工程喷锚支护的自动化设计方法[J]. 铁道学报，2000，22(1)：83–86.(WEI Liping，ZHANG Qing. An automatic design approach for tunnel anchor bolt-shotcrete support[J]. Journal of the China Railway Society，2000，22(1)：83–86.(in Chinese))
[22] 裘军良. 公路隧道围岩判别和支护设计人工神经元网络方法的研究[硕士学位论文][D]. 西安：长安大学，2003.(QIU Junliang. Research on artificial neural network method of surrounding rock discrimination and support design of highway tunnel[M. S. Thesis][D]. Xi?an：Chang?an University，2003.(in Chinese))
[23] 夏永旭，裘军良，王永东. 神经元网络在公路隧道支护设计中的应用[J]. 长安大学学报：自然科学版，2005，25(2)：69–72.(XIA Yongxu，QIU Junliang，WANG Yongdong. Application of neuronal networks in highway tunnel support design[J]. Journal of Chang?an University：Natural Science，2005，25(2)：69–72.(in Chinese))
[24] 陈子全，何 川，周子寒，等. 基于机器学习的隧道支护体系智能化设计与评价方法[J/OL]. 中国公路学报，DOI：https://kns.cnki.net/kcms/detail/ 61.1313.u.20230320.1658.005.html.(CHEN Ziquan，HE Chuan，ZHOU Zihan，et al. Intelligent design and evaluation method for tunnel support system based on machine learning[J/OL]. Chinese Journal of Highways，DOI：https://kns.cnki.net/kcms/detail/61.1313.u.20230320.1658.005.html. (in Chinese))
[25] BREIMAN L. Random forests[J]. Machine Learning，2001，45(1)：5–32.
[26] BI X A，XING Z X，ZHOU W Y，et al. Pathogeny detection for mild cognitive impairment via weighted evolutionary random forest with brain imaging and genetic data[J]. IEEE Journal of Biomedical and Health Informatics，2022，26(7)：3 068–3 079.
[27] ZHENG G，GU X Y，ZHANG T Q，et al. Random forest method-based prediction and control of bridge pier displacements during construction of two overlapped EPBM tunnels[J]. European Journal of Environmental and Civil Engineering，2022，26(6)：2 273–2 293.
[28] 朱梦琦，朱合华，王 昕，等. 基于集成CART算法的TBM掘进参数与围岩等级预测[J]. 岩石力学与工程学报，2020，39(9)：1 860–1 871.(ZHU Mengqi，ZHU Hehua，WANG Xin，et al. Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(9)：1 860–1 871. (in Chinese))
[29] 马忠臣，陈松灿. 多输出分类综述[J]. 杭州电子科技大学学报：自然科学版，2019，39(3)：1–9.(MA Zhongchen，CHEN Songcan. Overview of multi-output classification[J]. Journal of Hangzhou Dianzi University：Natural Science，2019，39(3)：1–9.(in Chinese))
[30] 崔浩康. 多标签学习算法的改进与研究[硕士学位论文][D]. 成都：电子科技大学，2020.(CUI Haokang. Improvement and research of multi-label learning algorithm[M. S. Thesis][D]. Chengdu：University of Electronic Science and Technology of China，2020.(in Chinese))
[31] EBERHART R，KENNEDY J. A new optimizer using particle swarm theory[C]// Proceedings of the Sixth International Symposium on Micro Machine and Human Science. [S. l.]：[s. n.]，1995：39–43.
[32] 杨超杰，裴以建，刘 朋. 改进粒子群算法的三维空间路径规划研究[J]. 计算机工程与应用，2019，55(11)：117–122.(YANG Chaojie，PEI Yijian，LIU Peng. Improved particle swarm algorithm for 3D spatial path planning research[J]. Computer Engineering and Applications，2019，55(11)：117–122.(in Chinese))
[33] 高 玮. 基于蚁群聚类算法的岩爆预测研究[J]. 岩土工程学报，2010，32(6)：874–880.(GAO Wei. Research on rockburst prediction based on ant colony clustering algorithm[J]. Journal of Geotechnical Engineering，2010，32(6)：874–880.(in Chinese))
[34] 周煦桐. 基于神经网络算法的岩爆预测方法研究[硕士学位论文][D]. 湘潭：湘潭大学，2020.(ZHOU Xutong. Research on rockburst prediction method based on neural network algorithm[M. S. Thesis][D]. Xiangtan：Xiangtan University，2020.(in Chinese))
[35] PU Y，APEL D，XU H. A principal component analysis/fuzzy comprehensive evaluation for rock burst potential in kimberlite[J]. Pure and Applied Geophysics，2018，175(6)：2 141–2 151.
[36] ZHOU J，LI X B，SHI X Z et al. Long-term prediction model of rock burst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science，2012，50(4)：629–644.
[37] 汤志立，徐千军. 基于9种机器学习算法的岩爆预测研究[J]. 岩石力学与工程学报，2020，39(4)：773–781.(TANG Zhili，XU Qianjun. Research on rockburst prediction based on 9 machine learning algorithms[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(4)：773–781.(in Chinese))
[38] 杨 玲，魏 静. 基于支持向量机和增强学习算法的岩爆烈度等级预测[J]. 地球科学，2023，48(5)：2 011–2 023.(YANG Ling，WEI Jing. Rockburst intensity class prediction based on support vector machines and augmented learning algorithms[J]. Earth Sciences，2023，48(5)：2 011–2 023.(in Chinese))
[39] 周科平，雷 涛，胡建华. 深部金属矿山RS-TOPSIS岩爆预测模型及其应用[J]. 岩石力学与工程学报，2013，32(增2)：3 705–3 711. (ZHOU Keping，LEI Tao，HU Jianhua. RS-TOPSIS rockburst prediction model for deepmetal mines and its application[J]. Chinese Journal of Rock Mechanics and Engineering，2013，32(Supp.2)：3 705–3 711. (in Chinese))
[40] 张乐文，张德永，邱道宏. 基于粗糙集的可拓评判在岩爆预测中的应用[J]. 煤炭学报，2010，35(9)：1 461–1 465.(ZHANG Leiwen，ZHANG Deyong，QIU Daohong. Application of rough set–based topologizable judgments to rockburst prediction[J]. Journal of China Coal Society，2010，35(9)：1 461–1 465.(in Chinese))
[41] 陈 语. 隧道大变形灾害动态风险评估与支护决策研究[硕士学位论文][D]. 成都：成都理工大学，2017.(CHEN Yu. Dynamic risk assessment and support decisions for large deformation hazards in tunnels[M. S. Thesis][D]. Chengdu：Chengdu University of Technology，2017.(in Chinese))
[42] FAN X M，ROSSITER D G，WESTEN C J，et al. Empirical prediction of coseismic landslide dam formation[J]. Earth Surface Processes and Landforms，2014，39(14)：1 913–1 926.
[43] FENG T G，WANG C R，ZHANG J，et al. An improved artificial bee colony–random forest(IABC–RF) model for predicting the tunnel deformation due to an adjacent foundation pit excavation[J]. Underground Space，2022，7(4)：514–527.
[44] XU D N，SHI X Y，TSANG I W，et al. A survey on multi–output learning[J]. IEEE Transactions on Neural Networks and Learning Systems，2020，31(7)：2 409–2 429.
[45] ZHANG M L，ZHOU Z H. ML–KNN：A lazy learning approach to multi–label learning[J]. Pattern Recognition，2007，40(7)：2 038–2 048.
[46] ZHANG M L，ZHOU Z H. Multilabel neural networks with applications to functional genomics and text categorization[J]. IEEE Transactions on Knowledge and Data Engineering，2006，18(10)：1 338–1 351.
[47] ZHANG H，ZENG J，MA C C，et al. Multi–classification of complex microseismic waveforms using convolutional neural network：a case study in tunnel engineering[J]. Sensors，2021，21(20)：6 762–6 777.
[48] MA Chunchi，FAN Junqi，JI Xiang，et al. Effect of the initial support of the tunnel on the characteristics of rockburst：case study and mechanism analysis[J]. Advances in Civil Engineering，DOI：https://doi.org/10.1155/2022/7235619.
2024, Vol. 43 
