Hybrid Surrogate Model Research Articles

Hybrid Surrogate Modeling Approach for Data Reduction and Design Space Exploration of Turbine Blades

Hybrid Surrogate Modeling Approach for Data Reduction and Design Space Exploration of Turbine Blades

A hybrid surrogate model for real-time coastal urban flood prediction: An application to Macao

Tropical cyclones could cause co-occurrences of storm tides and rainfall and, therefore, induce flooding hazards, posing high risks to coastal cities. Accurate and timely prediction of flood hazards in time–space domain is essential for flood risk management. In this study, a hybrid surrogate model is proposed for real-time flooding prediction by considering the compound effects of storm tides, rainfall, and drainage outflows. The hybrid surrogate model combines a long short-term memory (LSTM) neural network for predicting drainage outflows with a one-dimensional convolutional neural network (1D CNN) for predicting water depths. The model is tested using performance metrics, and the simulation results agree well with the historical measurements. Moreover, a sensitivity analysis of the drainage outflows using the modified Morris screening method reveals the importance of considering drainage systems in flood modelling, particularly when rainfall return periods are relatively small. The sensitivity indices vary over the computation domain in terms of different driving factors, with positive values corresponding to rainfall-dominated area while negative values corresponding to storm tide-dominated area. The computation cost of the model is quite low, and the fast prediction speed could provide a sound basis for early warning and real-time flood management. The proposed hybrid surrogate model offers a promising function for rapid and accurate flood inundation prediction in coastal cities, enabling more effective flood risk management and emergency response planning.

Hybrid surrogate model combining physics and data for seismic drift estimation of shear‐wall structures

AbstractTo address the issue of costly computational expenditure related to high‐fidelity numerical models, surrogate models have been widely used in various engineering tasks, including design optimization. Despite the successful application of the existing surrogate models, physics‐based models depend largely on simplifications and assumptions, which render parameter calibration challenging; whereas data‐driven models require substantial data to reach their full potential, with their performance often being constrained in tasks when obtaining massive data is difficult. In this study, a hybrid surrogate model is proposed combining physics‐based and data‐driven models to rapidly estimate building seismic responses. The application of this model is exemplified through effective estimation of inter‐story drift ratios (IDRs), being a critical factor in shear‐wall structure design. Initially, a data augmentation technique and a parametric modeling procedure are introduced to significantly enhance the dataset diversity. Subsequently, a task decomposition strategy is proposed to effectively integrate a data‐driven graph neural network (GNN) and a physics‐based flexural‐shear model. Additionally, the output layer and the loss function of the GNN are modified to enhance the estimation accuracy by eliminating fundamental errors. Results of numerical experiments indicate that the proposed hybrid model can complete IDR estimations in an average time of 0.56 s, with a mean absolute percentage error of 12.7%. This performance significantly surpasses that of existing purely data‐driven and physics‐based models. A case study shows that the efficiency of the proposed hybrid model is approximately 100 times greater than that of conventional finite element software. This enables an accurate assessment of the design compliance with code requirements. The results of this study can be applied to the design optimization of seismic‐resistant building structures.

Kinematic accuracy reliability evaluation method of space deployable mechanism based on dynamic model

Space deployable mechanisms are widely used in aerospace missions. The uncertainties in the geometric or physical parameters seriously affect the kinematic accuracy of the mechanism during the deployment process. In this paper, a kinematic accuracy reliability evaluation method of the space deployable mechanism based on dynamic model and adaptive hybrid surrogate models is presented. Firstly, the dynamic model of the space deployable mechanism is established based on the Lagrange method, and the motion error function considering the factors such as the mass, dimension and load is established. In order to improve the efficiency, an adaptive hybrid surrogate model reliability evaluation method based on improved weight measurement method is further proposed. The weight measurement method considers the global errors and local errors of the models. Finally, the Monte Carlo method is used to verify the accuracy of the hybrid surrogate model method. The relative error of the failure probability calculated by the proposed method is within 2.5 %, indicating that the proposed method has high calculation accuracy and efficiency.

Hybrid AI-Analytical Modeling of Droplet Dynamics on Inclined Heterogeneous Surfaces

This work presents a novel approach for the study of the movement of droplets on inclined surfaces under the influence of gravity and chemical heterogeneities. The developed numerical methodology uses data-driven modeling to extend the applicability limits of an analytically derived reduced-order model for the contact line velocity. More specifically, while the reduced-order model is able to capture the effects of the chemical heterogeneities to a satisfactory degree, it does not account for gravity. To alleviate this shortcoming, datasets generated from direct numerical simulations are used to train a data-driven model for the contact line velocity, which is based on the Fourier neural operator and corrects the reduced-order model predictions to match the reference solutions. This hybrid surrogate model, which comprises of both analytical and data-driven components, is then integrated in time to simulate the droplet movement, offering a speedup of five orders of magnitude compared to direct numerical simulations. The performance of this hybrid model is quantified and assessed in different wetting scenarios, by considering various inclination angles and values for the Bond number, demonstrating the accuracy of the predictions as long as the adopted parameters lie within the ranges considered in the training dataset.

Multiobjective Optimization of Composite Material Seat Plate for Mortar Based on the Hybrid Surrogate Model

As an important force transmission component of mortars, the seat plate affects some core indicators of mortars such as range, shooting accuracy, and maneuverability. In order to withstand huge impact loads, the seat plate was previously made of metal, which accounts for approximately 30%–45% of the total weight of the gun. The drawbacks of the heavy weight of the seat plate, which are not conducive to transportation and transfer, run counter to the current direction of the mortar’s lightweight development. The application of composite materials can greatly reduce the weight of the seat plate, but it exacerbates the contradiction between the mobility and combat effectiveness of mortars. In order to achieve the best match between mortar stability and maneuverability, a multiobjective optimization of composite material layers for seat plates is proposed, utilizing the designability of composite material layers. First, a fiber continuity model based on dropout sequence is adopted to solve the problems existing in the design of inherent continuity classes for composite layered fibers. Second, a hybrid surrogate model that considers the composite material seat plate quality, structural strength, shooting stability, shooting accuracy, and various working conditions is considered. Then, in order to improve the optimization efficiency and robustness of the algorithm, a multiobjective optimization algorithm based on the Chebyshev combination pattern is used to solve the mixed surrogate model. Finally, the optimization results are comprehensively evaluated against the optimization objectives. Research has shown that the method proposed in this article can effectively solve the time-consuming problem of multiobjective optimization, improve the accuracy of hybrid surrogate models, and meet the expected requirements of multiobjective optimization of composite material seat plates. While ensuring shooting stability, the weight of the seat plate is reduced by 18.43% compared to the metal seat plate, which has important application value for lightweight design of mortars.

Hybrid Surrogate Model based Multi-objective Optimization Design of Flux-Modulated Permanent Magnet Machine for Shaftless Pump-Jet Propulsor

Hybrid Surrogate Model based Multi-objective Optimization Design of Flux-Modulated Permanent Magnet Machine for Shaftless Pump-Jet Propulsor

An adaptive hybrid surrogate model for FEA of telescopic boom of rock drilling jumbo

The rapid collaborative optimization (CO) has an increasing demand for high-fidelity surrogate models. However, the traditional surrogate model cannot be applied to all working conditions due to the limitations of model applicability. A hybrid surrogate model is proposed, which uses the attention mechanism to automatically decide the weights of the sub models according to the working conditions to ensure its approximation ability under all working conditions. First, according to the characteristics of the finite element analysis (FEA) parameters, a comprehensive design of experiment (DOE) is proposed, which ensures the space-filling property of the samples. Secondly, a Self-attention artificial neural network (ANN) is proposed to automatically adjust the weights of sub-surrogate models, improving the attention to the working condition-related features. The proposed Self-attention ANN is a general framework that can provide support for the adaptive weight decision in other equipment simulation hybrid surrogate models. The experiment on the database shows that the error of the two hybrid surrogate models established by the proposed method is 36.04% and 33.31% lower than that of the advanced model, respectively, and is significantly superior to other methods. This achievement not only combines the spatial approximation ability of sub models to establish nonlinear model, achieving the purpose of high-fidelity simulation of FEA systems, but also enables surrogate model covering complete space using limited samples, making the model suitable for various practical engineering problems. In summary, the proposed method has obvious advantages in solving existing problems, provides strong support for research and practical applications.

A transferred hybrid surrogate model integrating Gaussian membership virtual sample generation for small sample prediction: Applications in metal tube bending

The high-performance virtual sample generation (VSG) method has been extensively introduced to solve the problem of small sample sizes. Data distribution information is a key element of current VSG methods at the data-driven level. Herein, we propose an improved VSG method with a Gaussian distribution and explore the relationship between the Gaussian function and data expansion. To obtain more feasible virtual samples, information expanded based on the Gaussian membership function (GMIE) was established. For further improvement, a hybrid surrogate model based on transfer (THSM) is proposed, which differs from the general hybrid surrogate model (HSM) methods that only mix single models. Using a prevailing evaluation method, our proposed method, which combines a Gaussian membership function with a hybrid surrogate model, outperforms other competing approaches in 12 numerical cases owing to its feasibility and efficacy. Additionally, the proposed approach is applied to a metal tube rotary draw bending (RDB) prediction problem to illustrate its ability to support complex engineering designs.

Development of hybrid surrogate model structures for design and optimization of CO2 capture processes: Part I. Vacuum pressure swing adsorption in a confined space

Design and optimization of CO2 capture processes have become a tremendously active area of research particularly in the past decade. In this context, development of intelligent techniques on the basis of first-principles models coupled with data-driven algorithms for such purpose looks very promising. In a series of works, we intend to present mechanism approaches in order to develop applicable structures for design and optimization of the CO2 capture processes of interest via hybrid models. A systematic method is presented for optimizing a process for capturing CO2 from a confined space through a Vacuum Pressure Swing Adsorption (VPSA) operation using a Hybrid Surrogate Model (HSM) and Non-dominated Sorting Genetic Algorithm (NSGA-III). The surrogate model is structured based on the VPSA process model offered in the Aspen Adsorption® environment and an artificial intelligence (AI) data-driven algorithm. The developed HSM is then used to predict the key process outputs including CO2 purity, air recovery ratio and energy consumption rate. Accordingly, the optimized parameters are re-substituted into the VPSA process simulator for further data processing. It is demonstrated that the proposed model architecture provides considerable computational efficiency for the process optimization with only 48 h to complete the corresponding evolutionary search, while the optimization time by the conventional NSGA-direct method is close to 1129 h. The optimization results also show that the CO2 purity changes from 1000 ppm to 399 ppm, the air recovery ratio remains at 93 %, and the energy consumption per unit product (ECP) decreases by 38.5 % to 99.7 kJ·Nm−3 air after an optimized air purification operation. The idea of chemical mechanism and industrial data twin modeling in this study holds substantial importance for the development of digital chemical twin systems and the process optimization of intelligent factory.

Resistance prediction and optimization of Tri-SWACH using hybrid surrogate model with particular consideration of outrigger layout

Trimarans, as high-performance ships, the complex flow field of which generated by the interaction between the main hull and the outrigger plays a crucial role in its hydrodynamic performance compared with conventional mono-hulls. In this paper, a new framework is proposed for calm water resistance prediction and optimization of a novel Trimaran, Tri-SWACH with particular consideration of its outrigger layouts. Firstly, Through the comparison of calm water resistances for the novel Tri-SWACH hull in semi-constrained state using CFD simulations and model tests, the CFD simulation is verified to be a valid approach to build the database for surrogate model. PRS, BPNN and KRG methods are used to build the hybrid surrogate models. The effect of using different weight calculation strategies are examined. It is found that the hybrid surrogate model established by using the heuristic method shows higher prediction accuracy and generalization ability compared with single surrogate models and other weight calculation strategies. Based on the proposed hybrid surrogate model, the particle swarm algorithm is used to optimize the solution in the design space. The effectiveness of the optimal outrigger layout is verified by comparing with the CFD method. Compared to the worst outrigger layout, the calm water resistance of the optimal outrigger layout can be reduced by 5.12%. Finally, the hydrodynamic mechanism behind the difference of resistance under the initial, optimal, and worst outrigger layouts are revealed by comparing and analyzing the wave-making interference of the main hull and outriggers. The methods and findings of this study can provide theoretical guidance and support for the design and operation of Tri-SWACH.

Three-stage optimization framework of functionally graded stiffened cylindrical shells under thermal environment

Functionally graded materials (FGMs) display remarkable potential for thermal and mechanical applications, which attracts increasing interest in the aerospace industry. In this study, the FGMs are used in the stiffened cylindrical shells (SCSs) to improve their heat resistance and bearing capacity. For the functional gradient stiffened cylindrical shell (FG-SCS), the smeared stiffener method (SSM) is improved, and the analytical solution of its critical buckling load is obtained. In addition, a new three-stage optimization framework is proposed based on the hybrid surrogate model and the active learning strategy, and the lightweight design of FG-SCSs is conducted. The illustrative examples are evaluated, which indicate that FG-SCSs can promote the bearing capacity under the thermal environment, and the corresponding designs are very competitive.

Optimization Method Based on Hybrid Surrogate Model for Pulse-Jet Cleaning Performance of Bag Filter

The pulse-jet cleaning process is a critical part of the bag filter workflow. The dust-cleaning effect has a significant impact on the operating stability of bag filters. Aiming at the multi-parameter optimization problem involved in the pulse-jet cleaning process of bag filters, the construction method of hybrid surrogate models based on second-order polynomial response surface models (PRSMs), radial basis functions (RBFs), and Kriging sub-surrogate models is investigated. With four sub-surrogate model hybrid modes, the corresponding hybrid surrogate models, namely PR-HSM, PK-HSM, RK-HSM, and PRK-HSM, are constructed for the multi-parameter optimization involved in the pulse-jet cleaning process of bag filters, and their objective function is the average pressure on the inner side wall of the filter bag at 1 m from the bag bottom. The genetic algorithm is applied to search for the optimal parameter combination of the pulse-jet cleaning process. The results of simulation experiments and optimization calculations show that compared with the sub-surrogate model PRSM, the evaluation indices RMSE, R2, and RAAE of the hybrid surrogate model RK-HSM are 9.91%, 4.41%, and 15.60% better, respectively, which greatly enhances the reliability and practicability of the hybrid surrogate model. After using the RK-HSM, the optimized average pressure F on the inner side wall of the filter bag at 1 m from the bag bottom is −1205.1605 Pa, which is 1321.4543 Pa higher than the average pressure value under the initial parameter condition set by experience, and 58.4012 Pa to 515.2836 Pa higher than using the three sub-surrogate models, verifying its usefulness.

Scalable and portable computational framework enabling online probabilistic remaining useful life (RUL) estimation

This work demonstrates a framework that enables online prognostics in adhesive joints by estimating the real-time probabilistic remaining useful life (RUL) using ANNs based hybrid physics models and vectorized sequential Monte Carlo (SMC) simulations. The framework is developed by integrating the physics-based damage degradation model and uncertainty quantification (UQ) techniques to estimate both probabilistic fatigue failure life and RUL. The fatigue damage growth (FDG) simulator, a hybrid surrogate model that simulates real-time fatigue degradation in adhesive joints, is used. In the initial set of results, the generalized framework is validated by estimating the probabilistic fatigue failure life using two UQ methods: Markov Chain Monte Carlo (MCMC) and SMC method. The computational results are successfully compared against experimental data. The conventional MCMC sampling methods are inherently serial, which limits the exploitation of the computational speed-up provided by the FDG simulator and hinders the real-time life predictions. The SMC method quantifies the uncertainties by parallelizing the sampling process, significantly reducing computational time and enabling real-time prediction. Next, the generalized framework is used to estimate probabilistic RUL from the fatigue crack propagation data. The parallel SMC method showed very good speedup compared to the MCMC method. To further enhance the computational speed-up with SMC method, vectorized FDG simulations are introduced into the framework and good scalability is achieved. Finally, the portability of the framework is demonstrated by deploying it on the portable Raspberry Pi cluster.

A dual objective global optimization algorithm based on adaptive weighted hybrid surrogate model for the hydrogen fuel utilization in hydrogen fuel cell vehicle

Current engineering optimizations mainly use surrogate models (SMs) to approximate complex black-box problems. However, SMs with different approximate characteristics may make the designers unable to accurately judge which type of SMs is more suitable for the actual optimization design. A reasonable combination of different SMs might be one of the solutions. To this end, a global optimization algorithm based on an adaptive weighted hybrid surrogate model (GOA-AWHS) is proposed. In each iteration, a hybrid model based on kriging and RBF is first constructed by adaptively selecting weight coefficients. Next, two objectives consisting of predicted objective, root mean square error and distance parameters are optimized to generate the Pareto frontier. Finally, further selection of data points on the Pareto front yields multiple promising optimal solutions. A series of standard numerical functions and hydrogen fuel utilization in hydrogen fuel cell vehicles are tested to demonstrate the effectiveness and robustness of the GOA-AWHS method.

Efficient parametric study of a stochastic airfoil system based on hybrid surrogate modeling with advanced automatic kriging construction

Flutter is one of the most important aeroelastic instability phenomena that arises from the interaction between the structural dynamics of the mechanical airfoil system and the surrounding airflow. This instability phenomenon can lead not only to a reduction in aircraft performance but also to catastrophic structural failure.Therefore, one of the major challenges is to perform parametric and sensitivity studies on the stability behavior of a wing system subject to many random uncertainties in order to achieve a thorough understanding and reliable estimation of the role played by each parameter in the flutter phenomenon. To carry out such a study, an advanced surrogate modeling technique based on kriging and polynomial chaos expansion (PCE) is proposed for the prediction of flutter instability. In addition, a methodology based on hybrid surrogate modeling with advanced automatic kriging construction is discussed to promote an efficient parametric study of the airfoil system with uncertainties subjected to flutter. The Sobol indices highlight that the role played by each random parameter depends strongly on the flow speed and airfoil geometry with complex behaviors, giving valuable insights into the physics and the complexity of flutter.

Optimization of stamping process parameters based on an improved particle swarm optimization–genetic algorithm and sparse auto-encoder–back-propagation neural network model

Stamping is a very important manufacturing process. To optimize the process parameters, a hybrid surrogate model based on the back-propagation neural network and sparse auto-encoder is proposed and compared with classical surrogate models to verify its reliability. Furthermore, the hybrid improved particle swarm optimization–genetic algorithm, based on chaos theory, is proposed and compared with other algorithms. A double-C part is used as an engineering example to verify the proposed method. The Latin hypercube sampling method is used for sampling and the response value is obtained by AutoForm simulation software. On this basis, the hybrid surrogate model is used to establish the mapping relationship between the forming quality of the double-C part and the stamping process parameters. The optimal stamping process parameters are obtained through the improved hybrid algorithm. The results demonstrate that the wrinkling of the optimized double-C part is significantly reduced and the forming quality is improved.

Analytical robust design optimization based on a hybrid surrogate model by combining polynomial chaos expansion and Gaussian kernel

Analytical robust design optimization based on a hybrid surrogate model by combining polynomial chaos expansion and Gaussian kernel

Bounds of mechanical properties of fibre reinforced polymer composites with hybrid random and interval uncertainties

Due to the hierarchical structure, fibre reinforced polymer composites exhibits randomness at multiple scales, for example, the constituent material properties and the layer thickness could be random at micro and macroscale, respectively. In addition, some of these uncertainties may not have sufficient probability information to be precisely described as random variables, and they are treated as interval variables. This study, proposes a novel framework to estimate the boundary of mechanical properties of fibre reinforced polymer composites with hybrid and internal uncertainties. Within this framework, the random and interval uncertainties are expressed in terms of Hermite and Chebyshev polynomials, respectively, within the PCE-based surrogate model. By doing so, the multiscale analysis is embedded in the hybrid surrogate model to realize the multiscale random-interval uncertainty analysis. Numerical examples are carried out to demonstrate the feasibility of the proposed method, and results show that this method can accurately obtain the upper and lower bounds of structural responses, e.g. failure probability, of FRP composite structures.

Upskilling Low‐Fidelity Hydrodynamic Models of Flood Inundation Through Spatial Analysis and Gaussian Process Learning

AbstractAccurate flood inundation modeling using a complex high‐resolution hydrodynamic (high‐fidelity) model can be very computationally demanding. To address this issue, efficient approximation methods (surrogate models) have been developed. Despite recent developments, there remain significant challenges in using surrogate methods for modeling the dynamical behavior of flood inundation in an efficient manner. Most methods focus on estimating the maximum flood extent due to the high spatial‐temporal dimensionality of the data. This study presents a hybrid surrogate model, consisting of a low‐resolution hydrodynamic (low‐fidelity) and a Sparse Gaussian Process (Sparse GP) model, to capture the dynamic evolution of the flood extent. The low‐fidelity model is computationally efficient but has reduced accuracy compared to a high‐fidelity model. To account for the reduced accuracy, a Sparse GP model is used to correct the low‐fidelity modeling results. To address the challenges posed by the high dimensionality of the data from the low‐ and high‐fidelity models, Empirical Orthogonal Functions analysis is applied to reduce the spatial‐temporal data into a few key features. This enables training of the Sparse GP model to predict high‐fidelity flood data from low‐fidelity flood data, so that the hybrid surrogate model can accurately simulate the dynamic flood extent without using a high‐fidelity model. The hybrid surrogate model is validated on the flat and complex Chowilla floodplain in Australia. The hybrid model was found to improve the results significantly compared to just using the low‐fidelity model and incurred only 39% of the computational cost of a high‐fidelity model.