This paper presents an experimental study on the pullout behaviour of inclined shallow plate anchors subjected to axial pull in sand. The 1g model tests were performed to examine the effects of anchor inclination and sand–anchor interface conditions on the load–displacement response and the associated failure and deformation mechanisms of plate anchors at various embedment ratios and sand densities. The anchor pullout capacity was found to increase continuously with the load inclination angle to the vertical (α), and the increase was more significant for α from 45° to 90°. The effect of sand–anchor interface conditions was negligible for horizontal plate anchors (α = 0°), but it became increasingly significant at larger inclination angles. The effects of these two factors both decreased with an increasing embedment ratio. Their influences on the failure and deformation mechanisms were measured and analysed using a digital image correlation (DIC) technique. Based on the test data and results available in the literature, a simple empirical method for the prediction of pullout resistance of inclined plate anchors in sand is calibrated and recommended.

This paper presents a limit equilibrium solution for calculating the ultimate pullout resistance of shallow vertical plate anchors in sand, considering the combined effects of anchor embedment ratio, sand shear strength, sand-anchor interface strength and anchor aspect ratio. The geometry of the failure mechanism in the solution reflects observations from model tests. The ultimate failure load of a strip plate anchor was then determined by global equilibrium analysis of the passive and active failure soil wedge. The two-dimensional limit equilibrium solution is extended for rectangular plate anchors by introducing the shape factors of Ovesen and Strømann. The solution is compared with a database of 102 pullout model tests of vertical plate anchors in sand assembled from the literature and some limit analysis results. The comparison results suggest that the proposed solution can provide a reliable analytical tool for the ultimate pullout capacity prediction of shallow vertical plate anchors buried in sand.

Physics-informed machine learning has been a promising data-driven and physics-informed approach in geotechnical engineering. This study proposes a physics-informed extreme learning machine (PIELM) framework for analyzing tunneling-induced soil-pile interactions. The pile foundation is modeled as an Euler-Bernoulli beam, and the surrounding soil is modeled as a Pasternak foundation. The soil-pile interaction is formulated into a fourth-order ordinary differential equation (ODE) that constitutes the physics-informed component, while measured data are incorporated into PIELM as the data-driven component. Combining physics and data yields a loss vector of the extreme learning machine (ELM) network, which is trained within 1 second by the least squares method. After validating the PIELM approach by the boundary element method (BEM) and finite difference method (FDM), parametric studies are carried out to examine the effects of ELM network architecture, data monitoring locations and numbers on the performance of PIELM. The results indicate that monitored data should be placed at positions where the gradients of pile deflections are significant, such as at the pile tip/top and near tunneling zones. Two application examples highlight the critical role of physics-informed and data-driven approach for tunnelling-induced soil-pile interactions. The proposed approach shows great potential for real-time monitoring and safety assessment of pile foundations, and benefits for intelligent early-warning systems in geotechnical engineering.

The inverse Stefan problem, as a typical phase-change problem with moving boundaries, finds extensive applications in science and engineering. Recent years have seen the applications of physics-informed neural networks (PINNs) to solving Stefan problems, yet they still exhibit shortcomings in hyperparameter dependency, training efficiency, and prediction accuracy. To address this, this paper develops a physics-informed extreme learning machine (PIELM), a rapid physics-informed learning method framework for inverse Stefan problems. PIELM replaces conventional deep neural networks with an extreme learning machine network. The input weights are fixed in the PIELM framework, and the output weights are determined by optimizing a loss vector of physical laws composed by initial and boundary conditions and governing partial differential equations (PDEs). Then, solving inverse Stefan problems is transformed into finding the Moore-Penrose generalized inverse by the least squares method. Case studies show that the PIELM can increase the prediction accuracy by 3-7 order of magnitude in terms of the relative L2 error, and meanwhile saving more than 94% training time, compared to conventional PINNs.

This paper presents theoretical methods for the undrained stability analysis of shallow tunnels/sinkholes in clay based on the cavity contraction theory, with some assumptions and simplifications. To examine the accuracy and reliability of the new methods, a database was assembled, which consists of stability numbers of tunnel/sinkholes in clays from 22 centrifuge model tests, 10 field tests, and 62 FELA results. It is shown that the proposed methods give an average of 2.5% overestimation for the stability numbers from model tests and is in a good agreement with the FELA results. The cavity contraction theory-based methods are then discussed, which could provide useful guidance for designers to roughly assess shallow tunnel/sinkhole stability in clays.