Prediction of road settlement caused by LGWO top pipe tunnel construction
-
摘要: 为了准确预测大断面顶管隧道下穿既有公路引起的变形沉降规律，结合实际工程，提出基于自适应灰狼优化算法的沉降量预测模型。引入Logistic映射生成初始值，将灰狼算法中的收敛因子A分解为决策因子A1与衰减因子A2，以改善收敛因子在全局与局部搜索时的能力不足问题。通过沧州九河路通道人防工程进行实例验证，并与传统的灰狼算法、粒子群算法对比预测精度，结果表明，通过Logistic映射优化后灰狼算法的预测精度更高，较优化前的灰狼算法提高了6.9%、较粒子群算法提高了2.3%，说明新模型具有较高的实用性与准确度。Abstract: To accurately predict the deformation and settlement caused by a large cross-section pipe tunnel passing through the existing highway, a settlement prediction model based on the adaptive Grey Wolf optimization algorithm was proposed in conjunction with the actual project. Logistic mapping was introduced to generate the initial value, and the convergence factor A in the Grey Wolf algorithm is decomposed into decision factor and attenuation factor to improve the lack of ability of the convergence factor in global and local search. Through the Cangzhou Jiuhe Road Passage human security project for example verification, and with the traditional Grey Wolf algorithm, particle swarm algorithm to compare the prediction accuracy, the analysis results show that the accuracy of Grey Wolf algorithm prediction optimized by Logistic mapping is higher. The accuracy increased by 6.9% compared with the Grey Wolf algorithm without optimization and increased by 2.3% compared with the particle swarm algorithm. The new model has a high degree of practicality and accuracy.
-
表 1 Rastrigin函数测试结果对比
算法 最优解 最差值 平均值 标准方差 DWO 7.44×10−4 4.31×10−3 2.18×10−3 2.06×10−4 GA-GWO 3.18×10−6 5.11×10−5 5.71×10−6 5.64×10−7 PSO-GWO 1.14×10−5 6.32×10−6 1.87×10−6 1.28×10−7 LGWO 0 1.32×10−6 0.67×10−6 1.09×10−7 
下载: 导出CSV
表 2 九河路顶管隧道2-2断面路面沉降监测数据
量测时间/d 累积沉降量/mm 量测时间/d 累积沉降量/mm 2-2 3-3 2-2 3-3 1 0.13 0.11 16 27.17 28.36 2 2.36 2.14 17 35.32 33.67 3 2.84 2.48 18 44.18 46.19 4 3.65 3.88 19 50.81 51.32 5 4.12 4.23 20 54.63 56.66 6 4.57 4.59 21 50.52 52.36 7 5.88 5.91 22 49.37 47.47 8 6.34 3.15 23 55.43 58.03 9 7.53 6.95 24 63.55 65.38 10 8.12 8.12 25 68.38 69.56 11 8.12 7.16 26 71.39 74.11 12 12.54 15.66 27 70.42 73.54 13 22.68 24.36 28 69.72 71.14 14 30.28 26.22 29 70.32 72.16 15 21.53 24.62 30 71.42 71.89
下载: 导出CSV
表 4 不同预测模型沉降量预测结果对比
评价指标
算法R MAPE/% RMSE/mm GWO 0.9423 10.22 3.4760 GA-GWO 0.9612 6.81 1.4578 PSO-GWO 0.9866 1.35 0.8512 L-GWO 0.9986 1.20 0.1796
下载: 导出CSV
-
[1] 潘鹏旭, 陈 伟, 郑京承. 富水强风化砂岩地层顶管隧道下穿既有铁路施工技术[J]. 科学技术与工程,2023,23(29):12714-12720. (PAN P X, CHEN W, ZHENG J C. Construction technology of pipe-jacking tunnel in water-rich intensely weathered sandstone formation crossing underneath existing railway[J]. Science Technology and Engineering,2023,23(29):12714-12720. (in Chinese).PAN P X, CHEN W, ZHENG J C. Construction technology of pipe-jacking tunnel in water-rich intensely weathered sandstone formation crossing underneath existing railway[J]. Science Technology and Engineering, 2023, 23（29）: 12714-12720. (in Chinese). [2] 张 波, 刘晶晶. 顶管法下穿既有轨道交通隧道安全性研究[J]. 中国安全生产科学技术,2023,19(S1):162-167. (ZHANG B, LIU J J. Study on safety of existing rail transit tunnel undercrossing with pipe jacking method[J]. Journal of Safety Science and Technology,2023,19(S1):162-167. (in Chinese)ZHANG B, LIU J J. Study on safety of existing rail transit tunnel undercrossing with pipe jacking method[J]. Journal of Safety Science and Technology, 2023, 19（S1）: 162-167. (in Chinese) [3] 伍毅敏, 刘延安, 王 恒, 等. 北京市隧道下穿施工引起城市路面沉降的影响规律回归分析[J]. 交通运输工程学报,2022,22(2):176-186. (WU Y M, LIU Y A, WANG H, et al. Regression analysis of influence law of urban pavement settlement caused by underpass tunnel construction in Beijing[J]. Journal of Traffic and Transportation Engineering,2022,22(2):176-186. (in Chinese)WU Y M, LIU Y A, WANG H, et al. Regression analysis of influence law of urban pavement settlement caused by underpass tunnel construction in Beijing[J]. Journal of Traffic and Transportation Engineering, 2022, 22（2）: 176-186. (in Chinese) [4] 张 杰. 顶管穿越施工对既有地铁区间隧道保护技术研究[J]. 江苏建筑,2021(2):63-66. (ZHANG J. Research on the protection technology of existing subway tunnel by pipe jacking crossing construction[J]. Jiangsu Construction,2021(2):63-66. (in Chinese)ZHANG J. Research on the protection technology of existing subway tunnel by pipe jacking crossing construction[J]. Jiangsu Construction, 2021（2）: 63-66. (in Chinese) [5] 刘 智, 李欣雨, 李 震, 等. 基于Bayes-LSTM的公路隧道围岩变形预测方法研究[J]. 中外公路,2024,44(1):166-176. (LIU Z, LI X Y, LI Z, et al. Prediction method of surrounding rock deformation of highway tunnels based on bayes-LSTM[J]. Journal of China & Foreign Highway,2024,44(1):166-176. (in Chinese)LIU Z, LI X Y, LI Z, et al. Prediction method of surrounding rock deformation of highway tunnels based on bayes-LSTM[J]. Journal of China & Foreign Highway, 2024, 44（1）: 166-176. (in Chinese) [6] 李 鹏, 李 洋, 高 毅, 等. 基于“CC工法”的顶管隧道施工地表变形规律分析与研究[J]. 隧道建设(中英文),2019,39(11):1838-1847. (LI P, LI Y, GAO Y, et al. Analysis and research on surface deformation law of pipe jacking tunnel constructed by cut and convert method[J]. Tunnel Construction (Chinese and English),2019,39(11):1838-1847. (in Chinese)LI P, LI Y, GAO Y, et al. Analysis and research on surface deformation law of pipe jacking tunnel constructed by cut and convert method[J]. Tunnel Construction (Chinese and English), 2019, 39（11）: 1838-1847. (in Chinese) [7] 朱宝强, 王述红, 张 泽, 等. 基于时间序列与DEGWO-SVR模型的隧道变形预测方法[J]. 浙江大学学报(工学版),2021,55(12):2275-2285. (ZHU B Q, WANG S H, ZHANG Z, et al. Prediction method of tunnel deformation based on time series and DEGWO-SVR model[J]. Journal of Zhejiang University (Engineering Science),2021,55(12):2275-2285. (in Chinese)ZHU B Q, WANG S H, ZHANG Z, et al. Prediction method of tunnel deformation based on time series and DEGWO-SVR model[J]. Journal of Zhejiang University (Engineering Science), 2021, 55（12）: 2275-2285. (in Chinese) [8] 王小龙, 全强明, 熊立新. 基于改进粒子群-GRNN模型的地铁隧道沉降预测[J]. 世界科技研究与发展,2016,38(6):1142-1146. (WANG X L, QUAN Q M, XIONG Lixin. Prediction on metro tunnel settlement based on modified PSO-GRNN model[J]. World Sci-Tech R & D,2016,38(6):1142-1146. (in Chinese)WANG X L, QUAN Q M, XIONG Lixin. Prediction on metro tunnel settlement based on modified PSO-GRNN model[J]. World Sci-Tech R & D, 2016, 38（6）: 1142-1146. (in Chinese) [9] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software,2014,69:46-61. doi: 10.1016/j.advengsoft.2013.12.007 [10] FENG X D, JIMENEZ R, ZENG P, et al. Prediction of time-dependent tunnel convergences using a Bayesian updating approach[J]. Tunnelling and Underground Space Technology,2019,94:103118. doi: 10.1016/j.tust.2019.103118 [11] 于明洋, 李 婷, 许 静. 基于IMQ惯性权重策略的自适应灰狼优化算法[J]. 计算机科学,2024,51(7):354-361. (YU M Y, LI T, XU J. Adaptive grey wolf optimizer based on IMQ inertia weight strategy[J]. Computer Science,2024,51(7):354-361. (in Chinese)YU M Y, LI T, XU J. Adaptive grey wolf optimizer based on IMQ inertia weight strategy[J]. Computer Science, 2024, 51（7）: 354-361. (in Chinese) [12] MAY R M. Simple mathematical models with very complicated dynamics[J]. Nature, 261(5560): 459-467. [13] 陈 平, 周 娟, 吴名功. 基于改进GWO-GM(1, 1)模型的直流充电桩在线计量误差预测方法研究[J]. 现代电子技术,2024,47(5):112-117. (CHEN P, ZHOU J, WU M G. Research on DC charging pile online measurement error prediction method based on improved GWO-GM(1, 1) model[J]. Modern Electronics Technique,2024,47(5):112-117. (in Chinese)CHEN P, ZHOU J, WU M G. Research on DC charging pile online measurement error prediction method based on improved GWO-GM(1, 1) model[J]. Modern Electronics Technique, 2024, 47（5）: 112-117. (in Chinese) [14] 董福贵, 夏美娟, 李婉莹. 基于PSO-GWO的省级能耗强度预测与碳减排潜力估算[J]. 中国电力,2023,56(9):226-234. (DONG F G, XIA M J, LI W Y. Prediction of provincial energy consumption intensity and estimation of carbon emission reduction potential based on PSO-GWO[J]. Electric Power,2023,56(9):226-234. (in Chinese)DONG F G, XIA M J, LI W Y. Prediction of provincial energy consumption intensity and estimation of carbon emission reduction potential based on PSO-GWO[J]. Electric Power, 2023, 56（9）: 226-234. (in Chinese) [15] 刘 宇. 基于支持向量机的隧道变形预测模型研究[J]. 内蒙古科技大学学报,2015,34(4):370-373. (LIU Y. Research on tunnel displacement forecast model based on support vector machines[J]. Journal of Inner Mongolia University of Science and Technology,2015,34(4):370-373. (in Chinese)LIU Y. Research on tunnel displacement forecast model based on support vector machines[J]. Journal of Inner Mongolia University of Science and Technology, 2015, 34（4）: 370-373. (in Chinese) [16] 张亚辉, 彭立飞, 刘 凯, 等. 基于人工蜂群优化小波神经网络的深基坑开挖对既有盾构隧道变形的预测分析[J]. 高速铁路技术,2024,15(4):1-7,99. (ZHANG Y H, PENG L F, LIU K, et al. Prediction analysis of existing shield tunnel deformation induced by deep excavation using artificial bee colony optimized wavelet neural network[J]. High Speed Railway Technology,2024,15(4):1-7,99. (in Chinese)ZHANG Y H, PENG L F, LIU K, et al. Prediction analysis of existing shield tunnel deformation induced by deep excavation using artificial bee colony optimized wavelet neural network[J]. High Speed Railway Technology, 2024, 15（4）: 1-7,99. (in Chinese) [17] 袁森林. 小净距三车道矩形顶管隧道施工扰动实测分析[J]. 岩土工程技术,2024,38(2):175-180. (YUAN S L. Analysis of construction disturbance measurement of three lane rectangular pipe jacking tunnel with small clear distance[J]. Geotechnical Engineering Technique,2024,38(2):175-180. (in Chinese)YUAN S L. Analysis of construction disturbance measurement of three lane rectangular pipe jacking tunnel with small clear distance[J]. Geotechnical Engineering Technique, 2024, 38（2）: 175-180. (in Chinese) -
图(10) / 表(4)
计量
- 文章访问数: 27
- HTML全文浏览量: 13
- PDF下载量: 4
- 被引次数: 0
