基于APSO-SVR算法的隧道三台阶法开挖参数优化研究

Optimization of Excavation Parameters of Tunnel Three-Bench Excavation Method Based on APSO-SVR Algorithm

摘要

为解决浅埋软弱围岩（Ⅴ级）隧道三台阶法开挖参数优化问题，选择台阶进尺与隧道半跨的比值R、黏聚力、内摩擦角、围岩弹性模量、泊松比为影响因素，通过设计多水平正交有限元分析获取不同参数组合对应的拱顶沉降值。基于自适应粒子群算法（APSO算法）对支持向量回归模型（SVR）进行优化，建立三台阶法开挖拱顶沉降预测模型，并设置SVR模型对比分析；建立以拱顶沉降为输入值，以比值R、黏聚力、内摩擦角、围岩弹性模量、泊松比为输出值的APSO-SVR模型，实现比值R的反演分析；依托实际工程，利用Midas GTX NX对台阶开挖极限进尺参数进行精度验证。结果表明：ASPO-SVR模型相较于SVR模型误差明显减小、精度明显提高，验证优化SVR模型的可行性与优越性；反演结果在Midas中显示拱顶沉降模拟值与规定值相差0.72 %，验证优化参数方案的准确性及合理性；基于APSO-SVR的三台阶法开挖参数反演优化模型精度较高，可为类似工程的结构安全施工提供借鉴。

Abstract

To address the parameter optimization problem in the three-bench excavation method for tunnels in shallow-buried soft surrounding rock (Class V), the following influencing factors were selected: the ratio of bench advance to half-span R, cohesion, internal friction angle, elastic modulus of the surrounding rock, and Poisson’s ratio. Through multi-level orthogonal finite element analysis and design, the crown settlement values corresponding to different parameter combinations were obtained. An adaptive particle swarm optimization (APSO algorithm) was applied to optimize the surrounding rock parameters, ultimately establishing an optimized relationship between surrounding rock settlement and the advance length per stage in the three-bench excavation method. Using Poisson’s ratio as an influencing factor, multi-level orthogonal finite element analysis was employed to determine the crown settlement values under various parameter combinations. An APSO-optimized support vector regression (SVR) model was developed to construct a prediction model for crown settlement during three-bench excavation. A comparative analysis was conducted using a conventional SVR model. Furthermore, an APSO-SVR model was established with crown settlement as the input and the strength ratio R, cohesion, internal friction angle, elastic modulus, and Poisson’s ratio as outputs, enabling the inversion of ratio R. Based on an actual engineering case, multi-level orthogonal finite element analysis was applied for inversion analysis. Using the same project, Midas software was utilized to validate the accuracy of the limiting advance distance parameters in the sequential excavation process. The results show: the APSO-SVR model has lower error and higher accuracy than the SVR model, validating its optimization. Midas inversion shows a 0.72% difference between the simulated and specified arch top settlement values, confirming the optimized parameter scheme’s accuracy. The inversion optimization model based on APSO-SVR for three-bench excavation has high accuracy and can guide similar project safety construction.

关键词

台阶开挖进尺 / 参数反演 / APSO-SVR算法 / 数值模拟

Key words

bench excavation footage / parameter inversion / APSO-SVR algorithm / numerical simulation

参考文献

[1] ERHARTER G H, HANSEN T F, LIU Z Q, et al. Reinforcement learning based process optimization and strategy development in conventional tunneling[J]. Automation in Construction, 2021, 127: 103701.

[2] 杨晓俊 . 公路隧道松散地层洞段三台阶法开挖参数的优化[J]. 中国公路, 2022(18): 152-153.

[3] YANG X J . Optimization of excavation parameters of three—step method in loose stratum tunnel section of highway tunnel[J]. China Highway, 2022(18): 152-153.

[4] FANG Z C, ZHU Z G, CHEN X Y . Research on construction method and deformation control technology of high ground stress interbedded soft rock tunnel[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(4): 6175-6183.

[5] WAN F, WANG B, FU C T, et al. Stability control measures of soft and broken surrounding rocks of super—large section tunnel constructed using benching tunneling method[J]. IOP Conference Series: Earth and Environmental Science, 2021, 769(3): 032082.

[6] HU J Q, MIN X Y, SI J P, et al. A comparison between two tunneling methods (SEM and THBM) for large cross—section mountain tunnel: a case study of Qikeng tunnel in Zhejiang driven[J]. Hans Journal of Civil Engineering, 2021, 10(9): 912-924.

[7] ZHANG S B, HE S Y, QIU J L, et al. Displacement characteristics of an urban tunnel in silty soil by the shallow tunnelling method[J]. Advances in Civil Engineering, 2020: 3975745.

[8] 颜杜民, 何平, 陈峥, 等 . Ⅳ级围岩隧道两台阶法开挖进尺研究[J]. 铁道标准设计, 2016, 60(9): 99-103.

[9] YAN D M, HE P, CHEN Z, et al. Research on excavation footage of tunnels in Ⅳ rock with two—bench construction method[J]. Railway Standard Design, 2016, 60(9): 99-103.

[10] 林可夫, 项彦勇 . 深埋富水岩体隧道三台阶法施工数值模拟和参数优化: 以正盘台隧道工程为例[J]. 隧道建设(中英文), 2021, 41(增刊1): 199-206.

[11] LIN K F, XIANG Y Y . Numerical simulation and parameter optimization of deep—buried water—rich rock tunnel construction by three—step method: taking Zhengpantai tunnel project as an example[J]. Tunnel Construction, 2021, 41(S1): 199-206.

[12] 王记平, 王凯, 夏勇, 等 . 隧道三台阶带仰拱一次开挖台阶长度研究[J]. 公路, 2021, 66(7): 345-348.

[13] WANG J P, WANG K, XIA Y, et al. Study on the length of three steps with inverted arch in one excavation of tunnel[J]. Highway, 2021, 66(7): 345-348.

[14] 张宁, 张光伟, 刘瑞辉, 等 . 隧道台阶法施工中台阶长度的优化分析[J]. 公路, 2019, 64(10): 299-303.

[15] ZHANG N, ZHANG G W, LIU R H, et al. Optimization analysis of step length in tunnel construction by bench method[J]. Highway, 2019, 64(10): 299-303.

[16] 张士朝, 王亚琼, 高启栋, 等 . 基于不同优化算法的隧道洞口段拱顶沉降SVR预测模型及其比较评价[J]. 现代隧道技术, 2023, 60(6): 139-150.

[17] ZHANG S C, WANG Y Q, GAO Q D, et al. Tunnel portal section crown settlement SVR prediction models based on different optimization algorithms and their comparative evaluation[J]. Modern Tunnelling Technology, 2023, 60(6): 139-150.

[18] 赵俊杰, 贾斌, 张东, 等 . 基于BP神经网络的阿拉套山隧道围岩物理力学参数反演分析[J]. 隧道建设(中英文), 2019, 39(增刊1): 220-226.

[19] ZHAO J J, JIA B, ZHANG D, et al. Inverse analysis of physical and mechanical parameters of Alataoshan tunnel surrounding rock based on BP neural network[J]. Tunnel Construction, 2019, 39(S1): 220-226.

[20] 马金刚, 丰光亮, 吝曼卿, 等 . 机器学习在隧道岩爆微震监测预警中的应用[J]. 华东交通大学学报, 2023, 40(5): 10-18.

[21] MA J G, FENG G L, LIN M Q, et al. Application status of machine learning in microseismic monitoring and early warning of rockburst[J]. Journal of East China Jiaotong University, 2023, 40(5): 10-18.

[22] 阮永芬, 高春钦, 刘克文, 等 . 基于粒子群算法优化小波支持向量机的岩土力学参数反演[J]. 岩土力学, 2019, 40(9): 3662-3669.

[23] RUAN Y F, GAO C Q, LIU K W, et al. Inversion of rock and soil mechanics parameters based on particle swarm optimization wavelet support vector machine[J]. Rock and Soil Mechanics, 2019, 40(9): 3662-3669.

[24] ZHAN Z H, ZHANG J, LI Y, et al. Adaptive particle swarm optimization[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2009, 39(6): 1362-1381.

[25] TONG H Z, CHEN D R, PENG L Z . Analysis of support vector machines regression[J]. Foundations of Computational Mathematics, 2009, 9(2): 243-257.

[26] CHICCO D, WARRENS M J, JURMAN G . The coefficient of determination R—squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation [J]. Peerj Computer Science, 2021, 7: e623.

[27] 赵宏喆 . 公路隧道围岩初期支护参数智能优化方法及应用[D]. 北京: 北京交通大学, 2022.

[28] ZHAO H Z . Intelligent optimization method and application of initial supporting parameters of surrounding rock of highway tunnel[D]. Beijing: Beijing Jiaotong University, 2022.

[29] 邱道宏, 傅康, 薛翊国, 等 . 深埋隧道TBM掘进参数LSTM时序预测模型及应用研究[J]. 中南大学学报(自然科学版), 2021, 52(8): 2646-2660.

[30] QIU D H, FU K, XUE Y G, et al. LSTM time—series prediction model for TBM tunneling parameters of deep—buried tunnels and application research[J]. Journal of Central South University (Science and Technology), 2021, 52(8): 2646-2660.

[31] 赵雪, 顾伟红 . 基于人工蜂群优化支持向量机回归的隧道塌方风险预测[J]. 科学技术与工程, 2023, 23(9): 3997-4003.

[32] ZHAO X, GU W H . Tunnel collapse risk prediction based on artificial bee colony optimization support vector machine regression[J]. Science Technology and Engineering, 2023, 23(9): 3997-4003.

[33] 方智淳, 朱正国, 徐世祥, 等 . 一种改进的位移释放率计算方法及其在Ⅴ级围岩中的应用[J]. 中国公路学报, 2021, 34(1): 116-126.

[34] FANG Z C, ZHU Z G, XU S X, et al. Improved calculation method of displacement release rate and its application in V—level surrounding rock[J]. China Journal of Highway and Transport, 2021, 34(1): 116-126.

基金资助

国家重点研发计划(2022YFB2602200)