The prediction of joint opening-closing deformations helps improve the operational safety of immersed tunnel systems. Addressing issues such as the poor accuracy and limited applicability of existing models, a novel method for predicting the joint opening-closing deformations of immersed tunnels is proposed. Firstly, the Sparrow Search Algorithm (SSA) is used to adaptively optimize the hyperparameters of the Long Short-Term Memory (LSTM) network, constructing an SSA-LSTM model to achieve feature learning and preliminary prediction of the deformation information. Based on this, the Ljung-Box (LB) test is employed to analyze the residual sequences, and a Wavelet Neural Network (WNN) is introduced to further extract effective information from the residual sequences, obtaining corrected values for the residual sequences. Finally, the prediction results from the SSA-LSTM model and the corrected residual sequence results are superimposed and reconstructed to obtain the predicted values of the joint opening-closing deformations. The proposed method is validated based on the immersed tube tunnel project of the Hong Kong-Zhuhai-Macao Bridge. The results show that: The proposed model exhibits excellent overall prediction performance, effectively mining useful information from the deformation sequences and having an advantage in considering the local features of the deformation sequences. The final prediction achieve an R2 of 0.999 4, RMSE of 0.007 2 mm, and MAE of 0.006 6 mm, which are higher in accuracy and stability compared to LSTM, SSA-LSTM, and traditional SVR, BP, and XGBoost models. This method can serve as a means to deeply explore the development and variation patterns of joint opening-closing deformations.
[1] 王野,李宏哲,那通兴.基于相场法的沉管隧道结构损伤区识别[J].公路交通科技,2022,39(6):111-118. (Wang Ye, Li Hongzhe, Na Tongxing. Identification of damage zone in immersed tunnel structure based on phase field method[J]. Journal of Highway and Transportation Research and Development,2022,39(6):111-118. (in Chinese))
[2] 李志军,王秋林,陈旺,等.中国沉管法隧道典型工程实例及技术创新与展望[J].隧道建设(中英文),2018,38(6):879-894. (Li Zhijun, Wang Qiulin, Chen Wang, et al. Innovation and prospect of key technologies of immersed tunnels in China[J]. Tunnel Construction,2018,38(6):879-894. (in Chinese))
[3] Zhang X,Broere W. Monitoring seasonal deformation behavior of an immersed tunnel with distributed optical fiber sensors. Measurement[J]. 2023, 219(1):113268.
[4] 刘洪洲,徐国平,许昱, 等.复杂环境下沉管隧道接头渐进破坏模式探析[J].公路, 2022, 67(2): 308-314. (Liu Hongzhou, Xu Guoping, Xu Yu, et al. Analysis on progressive failure mode of immersed tunnel joint in complex environment[J]. Highway, 2022, 67(2): 308-314. (in Chinese))
[5] 李宏哲,姜国栋,张国柱,等.沉管隧道常见病害及检查维护思考[J].隧道建设(中英文), 2019, 39(增1):465-470. (Li Hongzhe, Jiang Guodong, Zhang Guozhu, et al. Consideration on common diseases of immersed tunnel and its inspection and maintenance[J] Tunnel Construction, 2019, 39(Supp.1): 465-470. (in Chinese))
[6] 史志想,吴华勇,文水兵.沉管隧道管节接头专项检测及分析[J].上海建设科技,2021(3):82-86. (Shi Zhixiang, Wu Huayong, Wen Shuibing. Special inspection and analysis of pipe joint in immersed tube tunnel[J] Shanghai Construction Science & Technology, 2021(3): 82-86. (in Chinese))
[7] 谢雄耀,张乃元,周彪,等.滨海软土沉管隧道结构性能演化规律及成因分析[J].工业建筑,2021,51(7):1-5,24. (Xie Xiongyao, Zhang Naiyuan, Zhou Biao, et al. Analysis on evolution laws and causes of structure performances for coastal immersed tunnels in soft soil[J] Industrial Construction, 2021, 51(7): 1-5,24. (in Chinese))
[8] 魏纲,魏新江.海底沉管隧道长期沉降及受力性状研究[J].市政技术,2012,30(1):61-63,66. (Wei Gang, Wei Xinjiang. Research on long-term settlement and force characteristics of submarine immersed tunnel[J]. Journal of Municipal Technology, 2012, 30(1):61-63,66. (in Chinese))
[9] 裘慧杰. 沉管隧道施工期沉降监测分析及基础层模型试验研究[D].杭州: 浙江大学,2014. (Qiu Huijie. Study of base layer model experiment and construction settlement analysis in immersed tube tunnel[D]. Hangzhou: Zhejiang University,2014. (in Chinese))
[10] 王勇.深埋长大沉管隧道沉降分析及控制措施研究[D]. 北京: 北京交通大学,2018. (Wang Yong. Settlement analysis and settlement control treatment of large deep buried immerse tunnel[D]. Beijing: Beijing Jiaotong University, 2018. (in Chinese))
[11] 梁禹.广州地铁一号线越江隧道运营期结构变形监测[J].现代隧道技术, 2008 (3):84-87. (Liang Yu. Structural deformation monitoring of the submerged tunnel on Guangzhou metro line 1 during operation[J]. Modern Tunnelling Technology, 2008 (3): 84-87. (in Chinese))
[12] 谢雄耀,易成敏,李伟平,等.甬江沉管隧道运营期接头监测数据安全性分析[J].岩土工程学报,2019,41(12):2338-2344. (Xie Xiongyao, Yi Chengmin, Li Weiping, et al. Safety analysis of settlement monitoring data of joints of Yongjiang immersed tube tunnel during operation period[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(12): 2338-2344. (in Chinese))
[13] 李瀚源. 沉管隧道结构及接头力学性能分析[D].北京: 北京交通大学, 2018. (Li Hanyuan. Mechanical properties analysis of structure and joints of immersed tube tunnels[D]. Beijing: Beijing Jiaotong University, 2018. (in Chinese))
[14] Li K, Zhang Z, Guo H, et al. Prediction method of pipe joint opening-closing deformation of immersed tunnel based on singular spectrum analysis and SSA-SVR[J]. Applied Ocean Research,2023,135(1): 103526.
[15] 李世贵,严韬.灰色-趋势最优加权组合模型在滑坡变形预测中的应用[J].土工基础,2022,36(4):514-517. (Li Shigui, Yan Tao. Application of a combined and weighted gray-trend optimal model in prediction of landslide deformation[J].Soil Engineering and Foundation, 2022, 36(4):514-517. (in Chinese))
[16] Shi S, Zhao R, Li S, et al. Intelligent prediction of surrounding rock deformation of shallow buried highway tunnel and itsengineering application[J]. Tunnelling and Underground Space Technology, 2019, 90: 1-11.
[17] 渠孟飞,谢强,李朝阳,等.基于支持向量机的膨胀土深基坑变形预测研究[J].施工技术,2016,45(19):30-32,37. (Qu Mengfei, Xie Qiang, Li Zhaoyang, et al. Prediction of slope displacement of deep foundation excavation based on support vector machine[J]. Construction Technology, 2016,45(19):30-32,37. (in Chinese))
[18] Hochreite S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735.
[19] 沈一鸣,张冬梅,黄忠凯,等.基于EMD-多层LSTM的盾构隧道长期沉降预测[J].地下空间与工程学报,2025,21(2):684-694. (Chen Yiming, Zhang Dongmei, Huang Zhongkai, et al. Long-term settlement prediction of shield tunnel based on EMD-multilayer LSTM[J]. Chinese Journal of Underground Space and Engineering,2025,21(2):684-694. (in Chinese))
[20] Xue J, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[21] 岳荣花.小波神经网络在沉降预测中的应用研究[D].南京: 河海大学,2007. (Yue Ronghua. The application of wavelet neural network in settlement predicition[D]. Nanjing: Hohai University,2007. (in Chinese))
[22] Jiang X, Lang Q, Jing Q, et al. An improved wavelet thresholddenoising method for health monitoring data: A case study of the Hong Kong-Zhuhai-Macao Bridge immersed tunnel[J]. Applied Sciences, 2022, 12(13): 6743.
[23] 汪朝阳,苏长权.双重改进的等维递补动态GM(1,1)模型探析[J].统计与决策,2020,36(19):34-37. (Wang Zhaoyang, Su Changquan. Analysis of double improved dimension-fixed and recursion-compensated dynamic GM (1,1) model [J]. Statistics & Decision,2020,36(19):34-37. (in Chinese))
