Explore the vast range of titles available.

PurposeThis study conducts a comparative study on the performance of reliability assessment methods based on adaptive surrogate models to accurately assess the reliability of automobile components, which is critical to the safe operation of vehicles.Design/methodology/approachIn this study, different adaptive learning strategies and surrogate models are combined to study their performance in reliability assessment of automobile components.FindingsBy comparing the reliability evaluation problems of four automobile components, the Kriging model and Polynomial Chaos-Kriging (PCK) have better robustness. Considering the trade-off between accuracy and efficiency, PCK is optimal. The Constrained Min-Max (CMM) learning function only depends on sample information, so it is suitable for most surrogate models. In the four calculation examples, the performance of the combination of CMM and PCK is relatively good. Thus, it is recommended for reliability evaluation problems of automobile components.Originality/valueAlthough a lot of research has been conducted on adaptive surrogate-model-based reliability evaluation method, there are still relatively few studies on the comprehensive application of this method to the reliability evaluation of automobile component. In this study, different adaptive learning strategies and surrogate models are combined to study their performance in reliability assessment of automobile components. Specially, a superior surrogate-model-based reliability evaluation method combination is illustrated in this study, which is instructive for adaptive surrogate-model-based reliability analysis in the reliability evaluation problem of automobile components.

In design engineering problems, the use of surrogate models (also called metamodels) instead of expensive simulations have become very popular. Surrogate models include individual models (regression, kriging, neural network...) or a combination of individual models often called aggregation or ensemble. Since different surrogate types with various tunings are available, users often struggle to choose the most suitable one for a given problem. Thus, there is a great interest in automatic selection algorithms. In this paper, we introduce a universal criterion that can be applied to any type of surrogate models. It is composed of three complementary components measuring the quality of general surrogate models: internal accuracy (on design points), predictive performance (cross-validation) and a roughness penalty. Based on this criterion, we propose two automatic selection algorithms. The first selection scheme finds the optimal ensemble of a set of given surrogate models. The second selection scheme further explores the space of surrogate models by using an evolutionary algorithm where each individual is a surrogate model. Finally, the performances of the algorithms are illustrated on 15 classical test functions and compared to different individual surrogate models. The results show the efficiency of our approach. In particular, we observe that the three components of the proposed criterion act all together to improve accuracy and limit over-fitting.

In an individualized shee metal assembly line, form and dimensional variation of the in-going parts and different disturbances from the assembly process result in the final geometrical deviations. Securing the final geometrical requirements in the sheet metal assemblies is of importance for achieving aesthetic and functional quality. Spot welding sequence is one of the influential contributors to the final geometrical deviation. Evaluating spot welding sequences to retrieve lower geometrical deviations is computationally expensive. In a geometry assurance digital twin, where assembly parameters are set to reach an optimal geometrical outcome, a limited time is available for performing this computation. Building a surrogate model based on the physical experiment data for each assembly is time-consuming. Performing heuristic search algorithms, together with the FEM simulation, requires extensive evaluations times. In this paper, a neural network approach is introduced for building surrogate models of the individual assemblies. The surrogate model builds the relationship between the spot welding sequence and geometrical deviation. The approach results in a drastic reduction in evaluation time, up to 90%, compared to the genetic algorithm, while reaching a geometrical deviation with marginal error from the global optimum after welding in a sequence.

Multi-fidelity (MF) surrogate models have been widely used in engineering optimization problems to reduce the design cost by replacing computat ional expensive simulations. Ignoring the prediction uncertainty of the MF model that is caused by a limited number of samples may result in infeasible solutions. Conservative MF surrogate model, which can effectively improve the feasibility of the constraints, has been a promising way to address this issue. In this paper, an ensemble weighted average (EWA) conservative multi-fidelity modeling method that integrates the performance of different error metrics is proposed. In the proposed method, the bootstrap method and mean-square-error method are reasonably weighted to calculate the safety margin of the MF surrogate model. The weights for the two metrics are determined through an optimization problem, which considers the performance of the two metrics in different subsets of the sample points. The effectiveness of the proposed method is illustrated through several numerical examples and a pressure vessel design problem. Results show that the proposed method constructs a more accurate conservative MF surrogate model than other methods in different problems. Furthermore, applying the constructed conservative MF surrogate model into optimization problems obtains more accurate optimal solutions while ensuring the feasibility of it.

Soft robotics holds immense promise for applications requiring adaptability and compliant interactions. However, the lack of sufficiently fast and accurate simulation environments for soft robots has hindered progress, particularly in linking with reinforcement learning (RL) applications. Traditional finite element method (FEM) models provide precise insights into soft robot dynamics but are computationally intensive and impractical for accelerated simulation. This work introduces a novel framework that integrates high‐fidelity FEM simulations with computationally efficient physics‐based simulations through a surrogate model tailored for RL. The surrogate model, trained on real‐world and FEM‐generated datasets, captures complex dynamics while maintaining efficiency. Sim2real experiments validate the framework, implementing the trajectory tracking and the force control tasks with high accuracy. These results demonstrate the framework's ability to bridge the simulation gap, enabling its application to advanced tasks, such as manipulation and interaction in unstructured environments. A surrogate‐model‐based framework is proposed for combining high‐fidelity finite element method and efficient physics simulations to enable fast, accurate soft robot simulation for reinforcement learning, validated through sim‐to‐real experiments.

Timely generation of accurate and reliable forecasts of flash flood events is of paramount importance for flood early warning systems in urban areas. Although physically based models are able to provide realistic reproductions of fast-developing inundation maps in high resolutions, the high computational demand of such hydraulic models makes them difficult to be implemented as part of real-time forecasting systems. This paper evaluates the use of a hybrid machine learning approach as a surrogate of a quasi-2D urban flood inundation model developed in PCSWMM for an urban catchment located in Toronto (Ontario, Canada). The capability to replicate the behavior of the hydraulic model was evaluated through multiple performance metrics considering error, bias, correlation, and contingency table analysis. Results indicate that the surrogate system can provide useful forecasts for decision makers by rapidly generating future flood inundation maps comparable to the simulations of physically based models. The experimental tool developed can issue reliable alerts of upcoming inundation depths on traffic locations within one to two hours of lead time, which is sufficient for the adoption of important preventive actions. These promising outcomes were achieved in a deterministic setup and use only past records of precipitation and discharge as input during runtime.

The use of data-driven surrogate models to produce deterministic flood inundation maps in a timely manner has been investigated and proposed as an additional component for flood early warning systems. This study explores the potential of such surrogate models to forecast multiple inundation maps in order to generate probabilistic outputs and assesses the impact of including quantitative precipitation forecasts (QPFs) in the set of predictors. The use of a k-fold approach for training an ensemble of flood inundation surrogate models that replicate the behavior of a physics-based hydraulic model is proposed. The models are used to forecast the inundation maps resulting from three out-of-the-dataset intense rainfall events both using and not using QPFs as a predictor, and the outputs are compared against the maps produced by a physics-based hydrodynamic model. The results show that the k-fold ensemble approach has the potential to capture the uncertainties related to the process of surrogating a hydrodynamic model. Results also indicate that the inclusion of the QPFs has the potential to increase the sharpness, with the tread-off also increasing the bias of the forecasts issued for lead times longer than 2 h.

In the reliability-based design optimization (RBDO) process, surrogate models are frequently used to reduce the number of simulations because analysis of a simulation model takes a great deal of computational time. On the other hand, to obtain accurate surrogate models, we have to limit the dimension of the RBDO problem and thus mitigate the curse of dimensionality. Therefore, it is desirable to develop an efficient and effective variable screening method for reduction of the dimension of the RBDO problem. In this paper, requirements of the variable screening method for deterministic design optimization (DDO) and RBDO are compared, and it is found that output variance is critical for identifying important variables in the RBDO process. An efficient approximation method based on the univariate dimension reduction method (DRM) is proposed to calculate output variance efficiently. For variable screening, the variables that induce larger output variances are selected as important variables. To determine important variables, hypothesis testing is used in this paper so that possible errors are contained in a user-specified error level. Also, an appropriate number of samples is proposed for calculating the output variance. Moreover, a quadratic interpolation method is studied in detail to calculate output variance efficiently. Using numerical examples, performance of the proposed method is verified. It is shown that the proposed method finds important variables efficiently and effectively

Human T-cell leukemia virus type 1 (HTLV-1) causes serious and intractable diseases in some carriers after infection. The elimination of infected cells is considered important to prevent this onset, but there are currently no means by which to accomplish this. We previously developed “virotherapy”, a therapeutic method that targets and kills HTLV-1-infected cells using a cytolytic recombinant vesicular stomatitis virus (rVSV). Infection with rVSV expressing an HTLV-1 primary receptor elicits therapeutic effects on HTLV-1-infected envelope protein (Env)-expressing cells in vitro and in vivo. Simian T-cell leukemia virus type 1 (STLV-1) is closely related genetically to HTLV-1, and STLV-1-infected Japanese macaques (JMs) are considered a useful HTLV-1 surrogate, non-human primate model in vivo. Here, we performed an in vitro drug evaluation of rVSVs against STLV-1 as a preclinical study. We generated novel rVSVs encoding the STLV-1 primary receptor, simian glucose transporter 1 (JM GLUT1), with or without an AcGFP reporter gene. Our data demonstrate that these rVSVs specifically and efficiently infected/eliminated the STLV-1 Env-expressing cells in vitro. These results indicate that rVSVs carrying the STLV-1 receptor could be an excellent candidate for unique anti-STLV-1 virotherapy; therefore, such antivirals can now be applied to STLV-1-infected JMs to determine their therapeutic usefulness in vivo.