High-strength concrete and shape steel are combined to form composite shear wall members to address the cross-section oversize of core tube shear walls at the bottom of tall and super-tall buildings. However, the existing investigation focus on rectangular shear walls, and insufficient study has been conducted on L-shaped shear walls. To better understand the seismic performance of L-shaped-section steel reinforced high-strength concrete (fcu≥ 60 MPa) shear walls (LSRHCW), four such specimens with distinct dimensions, reinforcement ratios and concrete strengths were tested under cyclic loading and high axial compression ratio (n = 0.5), and the lateral cyclic loading direction makes an angle of 45° with the wall limb length direction. The influence of improving concrete strength and reducing the steel and reinforcement ratios on the seismic performance is investigated. The results show that under high axial compression ratio, the specimens fail in flexure-shear mode due to strength reduction caused by concrete crushing, and exhibit excellent deformation performance (maximum drift ratio capacity, 3.03%). The wall specimens built with different strength concrete and shape steel ratios demonstrate comparable strength, deformation and initial stiffness. This suggests that the reinforcement ratio of LSRHCWs can be effectively reduced by upgrading concrete strength, while still maintaining their seismic performance.
Quasi-static testing is the primary seismic research method employed. The method proposed in this study utilizes the neural network (NN) algorithm for restoring force identification to extend the hysteretic performance of nonlinear complex components obtained from quasi-static tests shared or performed at a lower cost to the time history analysis of the seismic response of the entire structure. This approach enables accurate analysis of the seismic performance of the structure under real earthquake ground motions at a relatively low experimental costs. At the level of restoring force model recognition, the eight-path hysteresis model recognition theory and the corresponding complete set of input and output variables in the NN algorithm are proposed. The NN restoring force model was established using input and output parameters that characterize hysteresis state features, with a two-hidden-layer NN architecture. The case study results indicate that the prediction results of the NN restoring force model align well with the target values when trained on samples obtained under both seismic and quasi-static loading conditions. At the level of the nonlinear dynamic analysis of structures, the hybrid analysis method of structural seismic response based on NN restoring force model is proposed. In this method, the potentially severe nonlinear and elastic parts of the structure are divided into several NN substructures and principal numerical substructure, respectively. The pseudo-static test data of nonlinear regions were used to train the proposed NN restoring force model to identify the restoring force of NN substructures in the same region under time-history dynamic analysis. The platform was built to complete the data interaction between several NN substructures and principal numerical substructures, and a precise integration method was used to program the dynamic equation solving module, gradually completing dynamic response analysis of the entire structure. A multi-degree-of-freedom nonlinear frame case study indicate that the proposed method has good accuracy and can effectively analyze the structural nonlinear seismic response.
The modeling of cross-ply composite laminates using numerical methods has been a difficult task, leading to the development of various finite element method and other analytical solutions. However, as materials science advances, this problem has become more complex, presenting new challenges that require reliable and novel approaches. In this study, we propose the utilization of machine learning, specifically physics informed neural networks (PINN), for the first time to examine the behavior of composite plate. By solving a system of partial differential equations derived from the virtual work equilibrium principle, PINN are employed as a method to solve these equations using a generalized strong-form approach. To address the issue of imbalanced loss functions, we also propose adjusting the loss function in this research. Once trained, PINN serve as a surrogate model capable of predicting displacements and stresses in cross-ply composite laminates. To demonstrate the effectiveness and reliability of PINN, we investigate two examples of laminates with different material distributions and boundary conditions including boundary conditions on displacement and boundary conditions on stress, comparing the results with the benchmark Navier solution. The research and obtained results showcase the performance and accuracy of PINN, highlighting their potential as a surrogate model for solving problems related to cross-ply composite laminates.
The study focused on the intersecting section of the Nalong Underground Interchange Tunnel in Shenzhen and investigated the deformation mechanism of the intersecting section under excavation and overloading conditions using physical model tests and numerical simulation methods. First, the optimal similarity ratio was determined based on the tunnel’s actual geometric characteristics, spatial distribution, and engineering geological conditions. A physical model of the intersecting section was then established. Secondly, following the excavation compensation theory, the intersecting section was excavated and supported using scaled Negative Poisson’s Ratio (NPR) anchor cables. The analysis of tunnel stress−strain, displacement, and NPR anchor cable axial force revealed the stress redistribution characteristics of the tunnel during excavation. Subsequently, the tunnel underwent overloading tests to reveal the surrounding rock failure mechanism of the intersecting section. Finally, numerical simulations were used to compare and verify the test results. The deformation mechanism and damage mode of the similar physical model of the intersecting section of Shenzhen Nanlong Underground Interchange Tunnel under the condition of excavation support and overloading are investigated. The support effect of NPR anchors in the intersection tunnel is verified. The study provides a theoretical basis and practical guidance for the design of tunnel excavation and support with similar engineering background.
Deep mixing, also known as deep stabilization, is a widely used ground improvement method in Nordic countries, particularly in urban and infrastructural projects, aiming to enhance the properties of soft, sensitive clays. Understanding the shear strength of stabilized soils and identifying key influencing factors are essential for ensuring the structural stability and durability of engineering structures. This study introduces a novel explainable artificial intelligence framework to investigate critical soil properties affecting shear strength, utilizing a data set derived from stabilization tests conducted on laboratory samples from the 1990s. The proposed framework investigates the statistical variability and distribution of crucial parameters affecting shear strength within the collected data set. Subsequently, machine learning models are trained and tested to predict soil shear strength based on input features such as water/binder ratio and water content, etc. Global model analysis using feature importance and Shapley additive explanations is conducted to understand the influence of soil input features on shear strength. Further exploration is carried out using partial dependence plots, individual conditional expectation plots, and accumulated local effects to uncover the degree of dependency and important thresholds between key stabilized soil parameters and shear strength. Heat map and feature interaction analysis techniques are then utilized to investigate soil properties interactions and correlations. Lastly, a more specific investigation is conducted on particular soil samples to highlight the most influential soil properties locally, employing the local interpretable model-agnostic explanations technique. The validation of the framework involves analyzing laboratory test results obtained from uniaxial compression tests. The framework demonstrates an ability to predict the shear strength of stabilized soil samples with an accuracy surpassing 90%. Importantly, the explainability results underscore the substantial impact of water content and the water/binder ratio on shear strength.
The recurring occurrence of seismic hazards constitutes a significant and imminent threat to subway stations. Consequently, a meticulous assessment of the seismic resilience of subway stations becomes imperative for enhancing urban safety and ensuring sustained functionality. This study strives to introduce a probabilistic framework tailored to assess the seismic resilience of stations when confronted with seismic hazards. The framework aims to precisely quantify station resilience by determining the integral ratio between the station performance curve and the corresponding station recovery time. To achieve this goal, a series of finite element models of the soil-station system were developed and employed to investigate the impact of site type, seismic intensity, and station structural type on the dynamic response of the station. Then, the seismic fragility functions were generated by developing the relationships between seismic intensity and damage index, taking into account multidimensional uncertainties encompassing factors such as earthquake characteristics and construction quality. The resilience assessment was subsequently conducted based on the station’s fragility and the corresponding economic loss, while also considering the recovery path and recoverability. Additionally, the impacts of diverse factors, including structural characteristics, site types, functional recovery models, and peak ground acceleration (PGA) intensities, on the resilience of stations with distinct structural forms were also discussed. This work contributes to the resilience-based design and management of metro networks to support adaptation to seismic hazards, thereby facilitating the efficient allocation of resources by relevant decision makers.
This paper uses the three-dimensional numerical simulation method to analyze the first deep foundation pit project directly above the operating subway in a certain area. The monitoring data were compared with the numerical results to verify the accuracy of the numerical model, and then a series of analyses were performed. The soil beneath the tunnel is the most direct object of tunnel deformation caused by the excavation of deep foundation pits above the tunnel. The rebound deformation of the soil beneath the tunnel forces the tunnel to produce an upward deformation cooperatively. Therefore, after comparing and analyzing the prevention criteria of traditional excavation measures, which were not sufficient for this project, a new method of fortification is proposed for the foundation pit above the tunnel, which is called the micro-disturbance drill pipe pre-reinforcement method (PRM) for the soil beneath the tunnel. The comprehensive parameter analysis of the PRM shows that the PRM can effectively reduce the uplift value of the tunnel, and the reinforcement effect is obvious.
High performance concrete (HPC) properties depend on both its constituent materials and their interaction. This study presents a machine learning framework to quantify the effects of constituents on HPC compressive strength. We first develop a stochastic constitutive model using experimental data and subsequently employ an uncertainty quantification method to identify key parameters in relation to the compressive strength of HPC. The resultant sensitivity indices indicate that fly ash content has the strongest influence on compressive strength, followed by concrete age at test and blast surface slag content.
Corrosion significantly impacts the integrity of steel structures, making them more prone to damage and failure. Coating the steel surface with anti-corrosion paint is a prevalent method. Nevertheless, these coatings are susceptible to damage, and corrosion tends to initiate at and spread from the damaged points, potentially leading to severe localized deterioration. Accurately predicting the progression of corrosion and coating deterioration at these critical points is essential for effective maintenance of steel structures. This study focused on two different paint-coatings applied to SM400 steel, onto which defects of varied sizes and shapes were artificially induced to mimic real-world paint-coating damage. These specimens underwent the accelerated corrosion test (ISO 16539 Method B) to generate data on corrosion depth at various time intervals. Subsequently, a modified generative adversarial network (GAN) model was employed to develop a highly accurate prediction model for the deterioration of steel surfaces, where the inputs to the model are four sequential corrosion depth measurements, and the output is the predicted future corrosion depth distribution. The performance of the proposed model was quantitatively evaluated using the root mean square error (RMSE). The model demonstrated outstanding predictive accuracy across all defect scenarios presented in this study. Compared with both traditional GAN variants (Conditional GAN and Information Maximizing GAN), the proposed model demonstrated a lower RMSE in predictive accuracy. This finding underscores its capability for precise corrosion prediction in steel structures, even with a relatively small data set. This predictive capability holds significant potential for predictive maintenance and failure analysis in steel infrastructure. This study not only validates the use of GAN in predictive maintenance but also provides a novel approach for the early detection and management of corrosion, crucial for extending the lifespan of critical infrastructure.
Many engineering systems incorporate viscoelastic membranes of different geometries and boundary conditions experiencing large deformations. This paper presents a formulation based on the theory of nonlinear viscoelasticity. First, the kinematics of membrane deformation is expressed in three-dimensional space, and then the viscoelastic formulation for membranes is obtained based on the multiplicative decomposition of the tensor of deformation gradient. Also, the right Cauchy−Green viscoelastic tensor is considered as an internal variable. To solve the integration of evolution equation, a predictor-corrector method is used. Finally, due to the nonlinearity of the equations governing the problem, a nonlinear finite element formulation is derived. To check the effectiveness of the obtained formulation, several problems are studied. The comparisons show that the results of this formulation are in good agreement with the analytical and experimental results in the literature. It is shown that the current simplified viscoelastic model can successfully predict the results in the literature with more complicated viscoelastic models. Moreover, it is proven that the present model can predict the experimental data with just four material parameters, while the previous models should employ 12 material parameters. Therefore, the model presented in this paper is capable of predicting the experimental results more accurately with fewer material parameters.
