Accurately and dynamically predicting ground settlements during the construction of foundation pits is pivotal to the understanding of the potential risk of foundation pits and, therefore, enables constructors to take timely and effective actions to ensure the construction safety of foundation pits. Existing settlement prediction methods mainly focus on the prediction of the maximum ground settlements based on static influence factors, such as soil properties and the geometry of foundation pits. However, these methods are unable to be applied to the prediction of daily ground settlements in a direct way because daily ground settlements can be affected by many time-dependent influence factors, and an accurate prediction of daily ground settlements should take into consideration such factors. To address this problem, this paper proposes an artificial neural network-based daily ground settlement prediction method, where both static and time-dependent influence factors, as well as previous settlement monitoring data, are considered in the optimum artificial neural network. The proposed method is validated using data collected from a real cut-and-cover highway tunnel project in western Hangzhou, China. The results demonstrate that time-dependent influence factors and previous settlement monitoring data play vital roles in establishing an optimum artificial neural network for the accurate prediction of daily ground settlement.

This work presents the principle of virtual work and reciprocal theorem of partial-interaction composite beams. The principle of minimum potential energy is also obtained and proved along with the variational formulae for the frequency of free vibration and the critical load of buckling of partial-interaction composite beams. Approximate solutions for bending, vibration, and buckling are finally given to demonstrate their applications. It is shown that the deflections, resonant frequencies, and critical loads of buckling of composite beams under different boundary conditions can be readily obtained with enough accuracy by using these variational principles.

This paper uses the transfer matrix method (TMM) to analyze the interfacial behavior of a fiber-reinforced polymer (FRP)–plated beam with flexural cracks. The adhesive layer between the beam and the FRP sheet is simulated by the cohesive zone model (CZM) of a general interfacial bond-slip law. The flexural cracks are modeled by rotational springs whose rigidity is dependent on the relative depth of the cracks. The transfer matrix of the FRP-plated beam is then derived, and the joint coupling matrix (JCM) method is introduced to solve the stress resultants, displacements, interfacial shear stress, and axial force of the FRP sheet. Finally, some numerical examples are given, and the results are compared with the available analytical solutions to validate the present method.