|Table of Contents|

[1] Li Zhaozhong, Chang Xiangyu, Wang Hao, et al. Back-analysis method of rock mass propertiesin tunnel engineering using multiple monitoring databased on LS-SVR algorithm [J]. Journal of Southeast University (English Edition), 2023, (1): 1-7. [doi:10.3969/j.issn.1003-7985.2023.01.001]

Back-analysis method of rock mass propertiesin tunnel engineering using multiple monitoring databased on LS-SVR algorithm()

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Research Field:
Traffic and Transportation Engineering
Publishing date:


Back-analysis method of rock mass propertiesin tunnel engineering using multiple monitoring databased on LS-SVR algorithm
Li Zhaozhong1 2 Chang Xiangyu1 Wang Hao1 Mao Jianxiao1
1 Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education, Southeast University, Nanjing 211189, China
2 China Railway 24th Bureau Group Co., Ltd., Shanghai 200071, China
tunnel engineering back-analysis method rock mass properties least-squares support vector regression algorithm
To accurately estimate the rock mass properties of a high-speed railway tunnel, a back-analysis method using multiple monitoring data based on the least-squares support vector regression(LS-SVR)algorithm is presented. The root mean square error(RMSE)and mean absolute percentage error(MAPE)are used as evaluation indices. The results of the parameter estimation are compared with those of the back propagation neural network(BPNN)and Gaussian process regression(GPR). The results show that for the single type of monitoring data, the LS-SVR model with vault settlement has the lowest RMSE and MAPE values. Moreover, as the data type increases, the RMSE value of the LS-SVR decreases, especially for the model with the mixed data of vault settlement, convergence, and floor heave. The comparison results show that the presented model has lower RMSE and MAPE values than BPNN and GPR. The LS-SVR model using multiple monitoring data shows better performance than existing back-analysis methods, improving the accuracy of the estimation of rock mass properties.


[1] Chang X Y, Wang, H, Zhang Y M, et al. Bayesian prediction of tunnel convergence combining empirical model and relevance vector machine[J].Measurement, 2022, 188:110621. DOI: 10.1016/j.measurement.2021.110621.
[2] Fakhimi A, Salehi D, Mojtabai N. Numerical back analysis for estimation of soil parameters in the Resalat Tunnel project[J].Tunnelling and Underground Space Technology, 2004, 19(1): 57-67. DOI:10.1016/s0886-7798(03)00087-7.
[3] Gao W, Ge M M. Back analysis of rock mass parameters and initial stress for the Longtan tunnel in China[J].Engineering with Computers, 2016, 32(3): 497-515. DOI:10.1007/s00366-015-0428-8.
[4] Sun P M, Bao T F, Gu C S, et al. Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm[J]. Science China Technological Sciences, 2016, 59(9): 1442-1451. DOI:10.1007/s11431-016-0213-y.
[5] Nikakhtar L, Zare S, Nasirabad H M, et al. Application of ANN-PSO algorithm based on FDM numerical modelling for back analysis of EPB TBM tunneling parameters[J]. European Journal of Environmental and Civil Engineering, 2020, 26(8): 3169-3186. DOI:10.1080/19648189.2020.1795725.
[6] Sun J L, Wang F, Wang X L, et al. A quantitative evaluation method based on back analysis and the double-strength reduction optimization method for tunnel stability[J].Advances in Civil Engineering, 2021, 2021:8899685. DOI:10.1155/2021/8899685.
[7] Gao W, Chen D L, Dai S, et al. Back analysis for mechanical parameters of surrounding rock for underground roadways based on new neural network[J]. Engineering with Computers, 2017, 34(1): 25-36. DOI:10.1007/s00366-017-0518-x.
[8] Wu Y K, Yuan H N, Zhang B Y, et al. Displacement-based back-analysis of the model parameters of the Nuozhadu High Earth-Rockfill Dam[J]. Scientific World Journal, 2014. DOI:10.1155/2014/292450.
[9] Gao W. Inverse back analysis based on evolutionary neural networks for underground engineering[J]. Neural Processing Letters, 2016, 44(1): 81-101. DOI:10.1007/s11063-016-9498-x.
[10] Xu S, An X, Qiao X D, et al. Multi-task least-squares support vector machines[J].Multimedia Tools and Applications, 2013, 71(2): 699-715. DOI:10.1007/s11042-013-1526-5.
[11] Li Z Z, Wang H, Chang X Y, et al. Prediction of surrounding rock convergence deformation of high speed railway tunnel based on combined model[J]. Journal of Southeast University(Natural Science Edition), 2021, 51(05): 851-858. DOI: 10.3969/j.issn.1001-0505.2021.05.017.(in chinese)
[12] Torabi-Kaveh M, Sarshari B. Predicting convergence rate of Namaklan twin tunnels using machine learning methods[J].Arabian Journal for Science and Engineering, 2020, 45(5): 3761-3780. DOI:10.1007/s13369-019-04239-1.
[13] Zhu X Q, Gao Z H. An efficient gradient-based model selection algorithm for multi-output least-squares support vector regression machines[J]. Pattern Recognition Letters, 2018, 111: 16-22. DOI: 10.1016/j.patrec.2018.01.023.
[14] Luo Y B, Chen J X, Chen Y, et al. Longitudinal deformation profile of a tunnel in weak rock mass by using the back analysis method[J]. Tunnelling and Underground Space Technology, 2018, 71: 478-493. DOI: 10.1016/j.tust.2017.10.003.
[15] Kolivand F, Rahmannejad R. Estimation of geotechnical parameters using Taguchi’s design of experiment(DOE)and back analysis methods based on field measurement data[J]. Bulletin of Engineering Geology and the Environment, 2017, 77(4): 1763-1779. DOI:10.1007/s10064-017-1042-3.
[16] Zhuang D Y, Ma K, Tang C A, et al. Mechanical parameter inversion in tunnel engineering using support vector regression optimized by multi-strategy artificial fish swarm algorithm[J].Tunnelling and Underground Space Technology, 2019, 83:425-436. DOI: 10.1016/j.tust.2018.09.027.
[17] Wang H, Chang X Y, Zhang Y M, et al. Inversion analysis of mechanical parameters of surrounding rock in high-speed railway tunnel[J].Journal of Railway Engineering Society, 2020, 37: 47-53. DOI:10.3969/j.issn.1006-2106.2020.09.009. (in Chinese)
[18] Fei J B, Wu Z Z, Sun X H, et al. Research on tunnel engineering monitoring technology based on BPNN neural network and MARS machine learning regression algorithm[J].Neural Computing & Applications, 2021, 33(1): 239-255. DOI:10.1007/s00521-020-04988-3.
[19] Khatib T, Mohamed A, Sopian K, et al. Assessment of artificial neural networks for hourly solar radiation prediction[J].International Journal of Photoenergy, 2012, 2012:946890. DOI:10.1155/2012/946890.


Biographies: Li Zhaozhong(1984—), male, Ph. D. candidate; Wang Hao(corresponding author), male, doctor, professor, wanghao1980@seu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No. 51978155), the Science and Technology Program of Ministry of Housing and Urban-Rural Development(No. 2020-K-125).
Citation: Li Zhaozhong, Chang Xiangyu, Wang Hao, et al.Back analysis method of rock mass properties in tunnel engineering using multiple monitoring data based on LS-SVR algorithm[J].Journal of Southeast University(English Edition), 2023, 39(1):1-7.DOI:10.3969/j.issn.1003-7985.2023.01.001.
Last Update: 2023-03-20