摘要The settlement of tunnel vault, which is a complicated process that includes combined actions of multiple factors together, is difficult to calculate accurately with mathematical model. In the actual construction process, the surrounding rock often changes, so we must strictly control the tunnel vault settlement to meet design requirements. Traditional prediction models can obtain only a rough estimate of the vault settlement by using the monitoring data to fit and forecast its changes. To solve the problem, this paper constructs a time-series model, GM (1, 2) model, and BP model with input variables to predict the settlement of the vault. The effectiveness of the model is verified by examples, which show that the GM (1,1) prediction model of a single variable is completely ineffective. To avoid the lower prediction accuracy of single model and use the complementary advantages of different models, this paper establishes an integrated prediction model based on the above three models, and its weighting coefficient is determined by the application of the entropy method. The model is applied to Baimiaozi Tunnel for testing, which provides high-speed travel from Baoji to Hanzhong (two cities in Shanxi Province). The integrated model is effective in practice and has a high prediction accuracy.
Abstract：The settlement of tunnel vault, which is a complicated process that includes combined actions of multiple factors together, is difficult to calculate accurately with mathematical model. In the actual construction process, the surrounding rock often changes, so we must strictly control the tunnel vault settlement to meet design requirements. Traditional prediction models can obtain only a rough estimate of the vault settlement by using the monitoring data to fit and forecast its changes. To solve the problem, this paper constructs a time-series model, GM (1, 2) model, and BP model with input variables to predict the settlement of the vault. The effectiveness of the model is verified by examples, which show that the GM (1,1) prediction model of a single variable is completely ineffective. To avoid the lower prediction accuracy of single model and use the complementary advantages of different models, this paper establishes an integrated prediction model based on the above three models, and its weighting coefficient is determined by the application of the entropy method. The model is applied to Baimiaozi Tunnel for testing, which provides high-speed travel from Baoji to Hanzhong (two cities in Shanxi Province). The integrated model is effective in practice and has a high prediction accuracy.
肖大海, 谢全敏, 杨文东. 基于多变量的集成预测模型在隧道拱顶沉降变形预测中的应用[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 46-52.
XIAO Da-hai, XIE Quan-min, YANG Wen-dong. Application of Integrated Forecasting Model Based on Multi-variables in Tunnel Vault Settlement. Journal of Highway and Transportation Research and Development, 2018, 12(3): 46-52.
[1] HAO Zhe,LUO Ao, LIU Bin.Multi-factor Model for Tunnel System Prediction[J]. Geotechnical Engineering, 2004,18(3):116-121.(in Chinese)
[2] QI Su, ZHOU De-jun, WANG Li-ying, et al.Study on Deformation Prediction of Tunnel Surrounding Rock Based on Gray-Markov Chain[J]. Modern Tunneling Technology, 2013, 50(1):80-86.(in Chinese)
[3] AN Yong-lin, HUANG Kan, PENG Li-min, et al. Study on Stability of Tunnels by Strength Reduction Method[J]. Journal of Highway and Transportation Research and Development, 2011, 28(4):91-95.(in Chinese)
[4] YANG Wei-chao, PENG Li-min, HUANG Juan, et al. Application of Non-stationary Time Series Analysis Method in Deformation Prediction of Tunnel Construction[J]. Journal of Zhengzhou University:Engineering Science, 2008,29(1):132-135.(in Chinese)
[5] LONG Hao, GAO Rui, KONG De-xin, et al. Prediction of Tunnel Surrounding Rock Displacement Based on BP Neural Network-Markov Chain Model[J]. Journal of Yangtze River Scientific Research Institute, 2013,30(3):40-43, 55.(in Chinese)
[6] WANG Shou-yang, YU Le-an, LI Jian-qiang. Application of TEI@I Methodology to Foreign Exchange Rate Forecasting[J].Chinese Journal of Management, 2007,4(1):21-27.(in Chinese)
[7] WANG Yuan-zheng, XU Ya-jing.Application of Multiple Stationary Time Series ARIMAX Model[J]. Statistics and Decision, 2007(18):132-135.(in Chinese)
[8] WANG Li-ming.Application Time Series[M]. Shanghai:Fudan University Press,2008:220-226.(in Chinese)
[9] GAO Wen-hua, ZHU Jian-qun, HUANG Zi-yong, et al. Gray Self-adaptive Model of Dynamic Prediction of Surrounding Rock Deformation and Its Parameter Identification[J]. Journal of Highway and Transportation Research and Development, 2012, 29(1):114-132.(in Chinese)
[10] LIN Kuo-huang,LIU Bin-da. A Gray System Modeling Approach to the Prediction of Calibration Intervals[J]. IEEE Transactions on Instrumentation and Measurement,2005,54(1):297-304.
[11] LI Jian-lin, LI Zhi-qiang, ZHENG Ji-dong.Gray GM (1,2) Prediction Model for Mine Water Discharge[J]. Journal of Henan Polytechnic University:Natural Science Edition, 2016, 35(3):368-372.
[12] ZHOU Guo-xiong, MO Xiao-shan. Integrated Prediction Method Based on Gray Prediction and BP Manifold Pressure[J]. Journal of Instrumentation, 2011,32(7):1648-1654.(in Chinese)
[13] AN Yong-lin, PENG Li-min.Comparative Analysis and Demonstration of Predicting Water Gushing in Tunnel with BP and GM (1,1)[J]. Science and Technology Review, 2008,13:71-74.(in Chinese)
[14] ZHAO Zhi-ye,GONG Qiu-ming,ZHANG Yun,et al. Prediction Model of Tunnel Boring Machine Performance by Ensemble Neural Networks[J]. Geomechanics and Geoengineering,2007,2(2):123-128.
[15] CHEN Hua-you.Application of Entropy Method in Determining Weight of Combination Forecast[J]. Journal of Anhui University:Natural Science, 2003,27(4):1-6.(in Chinese)
[16] WANG Chun-sheng, WU Min, Cao Wei-hua. An Intelligent Integrated Forecasting Model of Sintered ore Returning Quantity Based on GIS and SVM[J].Control and Decision, 2008,23(4):450-454,459.(in Chinese)
[1]
谭仪忠, 刘元雪, 蔡守军, 王培勇, 陈愈龙. 浅埋隧道单侧扩建优化施工方案探讨[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 45-55.
[2]
李高盛, 彭玲, 李祥, 吴同. 基于LSTM的城市公交车站短时客流量预测研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 65-72.
[3]
杨相如. 海底隧道衬砌混凝土高温后性能试验研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 53-59.
[4]
罗福君, 周晓军, 王媛, 张福麟. 框架型棚洞承受落石冲击力的模型试验研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(2): 59-66.
[5]
肖旺, 郭全元, 苏永华. 考虑峰后特性的隧道围岩锚固力学效应[J]. Journal of Highway and Transportation Research and Development, 2017, 11(1): 49-58.
[6]
张缓缓, 向绪爱, 叶克宝. 基于稳定性的四轮驱动电动汽车转矩分配策略研究[J]. Journal of Highway and Transportation Research and Development, 2017, 11(1): 98-102.
[7]
史晓花, 杜志刚, 周立平, 李平凡. 公路隧道中部视错觉减速标线优化研究[J]. Journal of Highway and Transportation Research and Development, 2016, 10(4): 63-70.
[8]
石钰锋, 罗青, 赵秀绍, 皮圣. 浅覆大跨度小净距隧道中岩墙及初支力学特性研究[J]. Journal of Highway and Transportation Research and Development, 2016, 10(3): 51-59.
[9]
胡俊, 王平. 含EPS颗粒夹层的隧道结构抗爆性能有限元分析[J]. Journal of Highway and Transportation Research and Development, 2016, 10(2): 53-58.
[10]
杨春霞, 付睿, 符义琴. 基于相似性的短时交通流预测[J]. Journal of Highway and Transportation Research and Development, 2016, 10(1): 92-97.
[11]
邵良杉, 徐波. 基于因子分析与Fisher判别分析法的隧洞围岩分类研究[J]. Journal of Highway and Transportation Research and Development, 2015, 9(4): 50-57.
[12]
王如意, 闫倩倩, 田波, 谢晋德. 含湿量和纤维对隧道二衬混凝土高温性能的影响[J]. Journal of Highway and Transportation Research and Development, 2015, 9(3): 63-68.
[13]
汪波, 王杰, 吴德兴, 徐建强, 赵玉东. 让压支护技术在软岩大变形隧道中的应用探讨[J]. Journal of Highway and Transportation Research and Development, 2015, 9(3): 69-77.
[14]
宋克志, 李福献, 朱雷敏, 王梦恕. 隧道二衬结构受力影响因素的敏感性分析[J]. Journal of Highway and Transportation Research and Development, 2014, 8(4): 69-75.
[15]
石钰锋, 林辉, 阳军生, 徐长节. 软弱地层浅埋隧道加固范围及强度参数的研究[J]. Journal of Highway and Transportation Research and Development, 2014, 8(4): 76-81.
2018, Vol. 12 
