A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Back analysis of surrounding rock parameters of tunnel considering displacement loss and space effect
https://orcid.org/0000-0002-2811-8006
Abstract Displacement back analysis is often performed to estimate rock parameters in tunnel construction. However, most researchers use the final values of monitoring displacement without considering the loss involved and the space effect, causing substantial errors. In this study, a displacement-based back analysis method is developed for estimating rock parameters, and both the displacement loss and space effect are considered when selecting and processing the output data of the algorithm. The method involves the following steps: First, reasonable training samples are set through numerical simulation, sensitivity analysis, and orthogonal design. Next, an extreme learning machine (ELM) optimized using particle swarm optimization (PSO) is trained to replace the time-consuming numerical analysis. Finally, the PSO algorithm is again utilized to determine the optimal parameters, and the displacement loss is calculated. The results of a simulation case indicate that the proposed method is highly precise and can be generalized adequately. The prediction accuracy can be improved by selecting rock parameters with high sensitivities and the typical monitoring data. An engineering application in the Jigongshan Tunnel in Shenzhen, China, demonstrates that this method can offer a reliable reference in terms of rock parameters to fulfill practical engineering demands, and provide an alternative approach for ground stress estimation during tunneling.
Back analysis of surrounding rock parameters of tunnel considering displacement loss and space effect
https://orcid.org/0000-0002-2811-8006
Abstract Displacement back analysis is often performed to estimate rock parameters in tunnel construction. However, most researchers use the final values of monitoring displacement without considering the loss involved and the space effect, causing substantial errors. In this study, a displacement-based back analysis method is developed for estimating rock parameters, and both the displacement loss and space effect are considered when selecting and processing the output data of the algorithm. The method involves the following steps: First, reasonable training samples are set through numerical simulation, sensitivity analysis, and orthogonal design. Next, an extreme learning machine (ELM) optimized using particle swarm optimization (PSO) is trained to replace the time-consuming numerical analysis. Finally, the PSO algorithm is again utilized to determine the optimal parameters, and the displacement loss is calculated. The results of a simulation case indicate that the proposed method is highly precise and can be generalized adequately. The prediction accuracy can be improved by selecting rock parameters with high sensitivities and the typical monitoring data. An engineering application in the Jigongshan Tunnel in Shenzhen, China, demonstrates that this method can offer a reliable reference in terms of rock parameters to fulfill practical engineering demands, and provide an alternative approach for ground stress estimation during tunneling.
Back analysis of surrounding rock parameters of tunnel considering displacement loss and space effect
https://orcid.org/0000-0002-2811-8006
Abstract Displacement back analysis is often performed to estimate rock parameters in tunnel construction. However, most researchers use the final values of monitoring displacement without considering the loss involved and the space effect, causing substantial errors. In this study, a displacement-based back analysis method is developed for estimating rock parameters, and both the displacement loss and space effect are considered when selecting and processing the output data of the algorithm. The method involves the following steps: First, reasonable training samples are set through numerical simulation, sensitivity analysis, and orthogonal design. Next, an extreme learning machine (ELM) optimized using particle swarm optimization (PSO) is trained to replace the time-consuming numerical analysis. Finally, the PSO algorithm is again utilized to determine the optimal parameters, and the displacement loss is calculated. The results of a simulation case indicate that the proposed method is highly precise and can be generalized adequately. The prediction accuracy can be improved by selecting rock parameters with high sensitivities and the typical monitoring data. An engineering application in the Jigongshan Tunnel in Shenzhen, China, demonstrates that this method can offer a reliable reference in terms of rock parameters to fulfill practical engineering demands, and provide an alternative approach for ground stress estimation during tunneling.
Back analysis of surrounding rock parameters of tunnel considering displacement loss and space effect
Zhao, Yong (author) / Feng, Shi-Jin (author)
2021
Article (Journal)
Electronic Resource
English
BKL:
56.00$jBauwesen: Allgemeines
/
38.58
Geomechanik
/
38.58$jGeomechanik
/
56.20
Ingenieurgeologie, Bodenmechanik
/
56.00
Bauwesen: Allgemeines
/
56.20$jIngenieurgeologie$jBodenmechanik
RVK:
ELIB18
Back Analysis for Mass Parameters of Tunnel Surrounding Rock
| Trans Tech Publications | 2012
Back Analysis for Mass Parameters of Tunnel Surrounding Rock
| British Library Conference Proceedings | 2012
Time Series Forecasting of Tunnel Surrounding Rock Displacement
| Trans Tech Publications | 2011