Hybrid methods for shotcrete and segmental linings tunnel shells – Combining displacement and rotation measurements with computational multiscale mechanics

Pichler, Bernhard; Hellmich, Christian

doi:10.1002/geot.201800014

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different methods have been proposed to directly identify the lining internal forces or the surrounding loads from displacement measurements at construction sites. In [1,2,3], histories of in-situ displacement fields are combined with non-linear finite element analyses in a hybrid combination concept to quantify for the loading situation on shotcrete shells, which were used as the tunnel lining in the New Austrian Tunneling Method. The hybrid analysis is also validated using monitored displacement from a full-scale test of a segmented tunnel ring [4].…”

Section: Introductionmentioning

confidence: 99%

Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

Chen¹,

Cao²,

Yuan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, a class of machine learning methods called physics-informed neural networks (PINNs) has been proposed and gained great prevalence in solving various scientific computing problems. This approach enables the solution of partial differential equations (PDEs) via embedding physical laws into the loss function of neural networks. Many inverse problems can also be tackled by simply combining the observational data from real life scenarios with existing PINN algorithms. In this paper, we present a multi-task learning method to improve the training stability of PINNs for linear elastic problems, and the homoscedastic uncertainty is introduced as a basis for weighting losses. Furthermore, we demonstrate an application of PINNs to a practical inverse problem in tunnel engineering: prediction of external loading distributions of tunnel rings based on a limited number of displacement monitoring points. To this end, we first determine a simplified tunneling scenario at the offline stage. By setting unknown boundary conditions as learnable parameters, PINNs can predict the external loads applied on the tunnel lining with the support of enough measurement data. When it comes to the online stage in real tunnel projects, the Kriging method is adopted to reconstruct the whole displacement field based on very limited measurements. Then transfer learning is employed to fine-tune the pre-trained model from offline stage. Our results show that, although the reconstructed displacement field generated from gappy measurements is accompanied by errors, satisfactory results can still be obtained from the PINN model due to the dual regularization of physics laws and prior knowledge, which exhibits better robustness compared to traditional analysis methods. The convergence of training is also accelerated, thus making it possible for PINNs to be applied in actual tunnel projects.

show abstract

Section: Introductionmentioning

confidence: 99%

Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

Chen¹,

Cao²,

Yuan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Identification Method for Internal Forces of Segmental Tunnel Linings via the Combination of Laser Scanning and Hybrid Structural Analysis

Zhang

Karlovšek

Liu

2022

Sensors

View full text Add to dashboard Cite

This paper provides a new solution to identify the internal forces of segmental tunnel linings by combining laser scanning and hybrid structural analysis. First, a hybrid structural analysis method for quantifying the internal forces based on displacement monitoring is established, which requires comprehensive displacement monitoring with high precision and a complete trace history. Motivated by the development of laser scanning, two remedial solutions are proposed for typically insufficient engineering conditions, i.e., lack of displacement developing process and poor accuracy of measurements, which is highlighted in this paper. Therefore, with the help of remedial solutions, the structural analysis is able to be adopted with the application of laser scanning. The tool for developing remedial solutions is the first-order theory of slender circular arches. Virtual tests, based on a calibrated finite element model, were performed to verify the feasibility of the presented hybrid analysis and remedial solutions. In addition, parametric analyses were conducted to study the error propagation from laser scanning to the results of hybrid analysis. The resolution and measurement noise of laser scanning were investigated and discussed. On this basis, advice on combining laser scanning and hybrid structural analysis is proposed. Finally, on-site application of the hybrid analysis on an actual tunnel is presented and discussed.

show abstract

Hybrid methods for shotcrete and segmental linings tunnel shells – Combining displacement and rotation measurements with computational multiscale mechanics

Cited by 2 publications

References 18 publications

Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

Identification Method for Internal Forces of Segmental Tunnel Linings via the Combination of Laser Scanning and Hybrid Structural Analysis

Contact Info

Product

Resources

About