Surrogate models are widely used in engineering design and optimization to substitute computationally expensive simulations for efficient approximation of system behaviours. However, since actual system behaviours are usually not known a priori, it is very challenging to select the most appropriate surrogate model for a specific application. To tackle this, ensemble models that combine different surrogate models have been developed based on global measures and local measures respectively. This article proposes a novel ensemble of surrogates to take advantage of both global and local measures, and a unified strategy is conceived over the entire design space with proper trade-off between these two measures. The effectiveness of the proposed model is tested with 38 mathematical problems and an engineering optimization example. It is concluded that the proposed model has superior accuracy while keeping comparable robustness and efficiency with other ensemble models. The proposed model is also extended to non-uniform experimental design.z

Reinforced concrete (RC) is the result of a combination of steel reinforcing rods (which have high tensile) and concrete (which has high compressive strength). Additionally, the prediction of long-term deformations of RC flexural structures and the magnitude of the influence of the relevant material and geometric parameters are important for evaluating their serviceability and safety throughout their life cycles. Empirical methods for predicting the long-term deformation of RC structures are limited due to the difficulty of considering all the influencing factors. In this study, four popular surrogate models, i.e., polynomial chaos expansion (PCE), support vector regression (SVR), Kriging, and radial basis function (RBF), are used to predict the long-term deformation of RC structures. The surrogate models were developed and evaluated using RC simply supported beam examples, and experimental datasets were collected for comparison with common machine learning models (back propagation neural network (BP), multilayer perceptron (MLP), decision tree (DT) and linear regression (LR)). The models were tested using the statistical metrics ${\mathrm{R}}^2$, $\mathrm{R}\mathrm{A}\mathrm{A}\mathrm{E}$, $\mathrm{R}\mathrm{M}\mathrm{A}\mathrm{E}$, $\mathrm{R}\mathrm{M}\mathrm{S}\mathrm{E}, \mathrm{V}\mathrm{A}\mathrm{F}, \mathrm{P}\mathrm{I}, {\mathrm{A}}_{10-\mathrm{i}\mathrm{n}\mathrm{d}\mathrm{e}\mathrm{x}} \mathrm{a}\mathrm{n}\mathrm{d} {\mathrm{U}}_{95}$. The results show that all four proposed models can effectively predict the deformation of RC structures, with PCE and SVR having the best accuracy, followed by the Kriging model and RBF. Moreover, the prediction accuracy of the surrogate model is much lower than that of the empirical method and the machine learning model in terms of the RMSE. Furthermore, a global sensitivity analysis of the material and geometric parameters affecting structural deflection using PCE is proposed. It was found that the geometric parameters are more influential than the material parameters. Additionally, there is a coupling effect between material and geometric parameters that works together to influence the long-term deflection of RC structures.

A large number of criteria to model the onset of plasticity for ductile metals have been proposed by researchers in the last century. Strangely, very few researchers have tried to model the stress-induced crystalline phase transformation of Shape Memory Alloys (SMAs) according to yield criteria. This paper focuses on the question: is a yield criterion originally proposed for describing the plastic behavior of metals suitable to model the “pseudoelastic” behavior of SMAs? To answer this question, two yield criteria originally proposed by the present author are used to predict the initial surface of transformation onset of two different SMAs: Cu-Al-Be and Ni-Ti alloy. The predicted initial transformation onset surfaces of the two SMAs are compared with experimental results and existing theories reported in the literature and some significant conclusions and recommendations are given.

Seepage erosion around sheet pile walls represents a critical failure mechanism in geotechnical engineering, yet the underlying mechanisms governing the onset of erosion remain poorly understood. This study presents a comprehensive multi-scale investigation employing a coupled computational fluid dynamics (CFD)-discrete element method (DEM) to elucidate the onset mechanisms of seepage erosion in gap-graded soils with varying the fines content under different hydraulic gradients. The results demonstrate that increasing the fines content enhances the overall erosion resistance, as evidenced by reduced particle mobilization and eroded mass ratio. Particle tracking analysis reveals that the fines content fundamentally influences the spatial distribution of the erosion. Specimens with low fines content exhibit distributed erosion throughout the domain, while specimens with higher fines content show concentrated erosion around the sheet pile wall and downstream regions. Micromechanical analysis of local contact fabric and contact forces indicates that this spatial heterogeneity stems from the mechanical coordination number and mechanical redundancy, characterized by the reduced magnitudes of these parameters for the region with lower erosion resistance. These findings establish that the fines content governs both global erosion resistance and spatial erosion patterns, providing essential insights for optimizing soil gradation design and advancing fundamental understanding of seepage erosion mechanisms.