Full length articleAn active learning metamodeling approach by sequentially exploiting difference information from variable-fidelity models
Introduction
Computational simulation models have been widely used to explore design alternatives during preliminary design phase. In spite of sustained growths in computer capability and speed, the enormous computational expensive associated with high fidelity engineering simulation codes still makes it impractical to rely exclusively on high fidelity models for design and optimization. Just taking Ford Motor Company as an example, it was reported that it takes the company about 36–160 h to run one crash simulation for a full passenger car [1]. Indeed, it is still impractical to directly use these simulations with an optimizer to evaluate a lot of design alternatives when exploring the design space for an optimum [2], [3]. This limitation can be addressed by adopting global metamodel (or surrogate), which can mimic the original system at a considerably reduced computational cost [4], [5]. There are a lot of commonly used metamodels, such as Polynomial Response Surface (PRS) models [6], Kriging models [7], Artificial Neural Networks (ANN) models [8], [9], Radial Basis Function (RBF) models [10], and Support Vector Regression (SVR) models [11]. A more detailed overview on various metamodeling techniques can refer to [12]. It is important to point out that the quality of the metamodels has a profound impact on the computational cost and convergence characteristics of the metamodel-based design optimization. The quality of the metamodels directly depends on the sample points at which the computer simulation or physical experiments are conducted. Generally, more sample points offer more information of the system, however, at a higher cost [13]. Less sample points require lower expense, while leading to inaccurate metamodels even distorted metamodels. Hence, conflict between high accuracy and low expense seems to be inevitable in building metamodels.
To ease this problem, variable-fidelity (VF) metamodeling approaches based on the interaction of high-fidelity (HF) and low-fidelity (LF) models have been widespread concerned [4], [14]. A HF model is one that is able to accurately describing the physical features of the system but with an unaffordable computational expense, e.g., physical experiment, finite element, computational fluid dynamics, etc. A LF model is one that is able to reflect the most prominent characteristics of the system at a considerably less computationally demanding, e.g., numerical empirical formula. Commonly used VF metamodeling approaches are scaling methods, which tune the LF model according to the response values of the HF model. These scaling methods can be divided into two distinct types: local VF metamodeling approaches and global VF metamodeling approaches. In local VF metamodeling approaches, the scaling function is approximated using local metamodels, e.g., linear regression [15], first/s Taylor series [16], [17], [18]. The local VF metamodeling approaches are easy to implement and can achieve a relative high accuracy within an appropriate trust region size, e.g., Chang et al. [15] used a multiplicative scaling approach to correct the response values of LF model to match the HF model. An application of this metamodel was tested on a wing-box model of a high-speed civil transport. Alexandrov et al. [16], [17] integrated first-order additive and multiplicative scaling modeling method with the convergent techniques of nonlinear programming in engineering analysis and design; and have successfully applied this method to a 3-D aerodynamic wing optimization problem and a 2-D airfoil optimization problem, achieving a threefold savings and twofold savings in computing effort, respectively. The main shortcoming of these approaches is that they are only suitable for local optimization problems [19], [20], [21]. While in global VF metamodeling approaches, the scaling function is approximated using global metamodels, e.g., Qian et al. [22] proposed a Bayesian approach to integrate LF model and HF simulation values for engineering design. Xiong et al. [23] put forward a model scaling technique based on Bayesian–Gaussian process to integrate the information from both LF and HF models. Han et al. [24] put forward a gradient-enhanced Kriging to form a generalized corrected based method, which was tested on the design of airfoil. Zheng et al. [25] proposed a hybrid VF global metamodeling method, which a RBF base model and a Kriging linear correction were combined to make full use of LF and HF information. Tyan et al. [26] adopted RBF network as the scaling function to replace Taylor series, making the global VFM approach more efficient for high-dimensional design problems. Compared with the local VF metamodeling approach, the most obvious advantage of these global VF metamodeling approaches is that they are able to cope with multiple optimum situations sophisticatedly on the entire domain. Until now, more researches have been carried out to develop new types of LF model tuning that will further improve the accuracy and reduce the computational effort of VF metamodeling, but little attention has been paid to utilize the already-acquired information of difference characteristics between the HF and LF models. In other words, how to appropriately arrange and make full use of the sample points for HF models to run simulations according to the already-acquired difference information between the HF and LF models during the tuning process should be drawn more attention, especially when the computational cost is limited.
Instead of developing novel types of LF model tuning as in the past, this paper proposes an active learning VF metamodeling approach (AL-VFM), in which the one-shot VF metamodeling process is transformed into an active learning iterative process. The goal of the active learning process is to exploit the already-acquired information from the previous VF data to guide the VF metamodeling. The already-acquired information represents the location of regions where the differences between the HF and LF models are multi-model, non-smooth and have abrupt changes. The approximation performance of AL-VFM approach is demonstrated using some mathematical and engineering cases, and a rough comparison of AL-VFM approach and other metamodeling techniques are made. It is expected that more accurate metamodels can be developed with AL-VFM for the same number of simulation evaluations.
The rest of this paper is organized as follows. In Section 2, the background and several definitions used in this work are put forward. Details of the proposed approach are presented in Section 3. Numerical cases and comparison results are provided in Section 4. Two engineering examples are provided in Section 5 to demonstrate that the proposed VF modeling approach is applicable to complex problems. Conclusions and future work are discussed in Section 6.
Section snippets
Background and definitions
In this section, we provide the background and related definitions to the proposed approach, including: Kriging metamodeling, VF metamodeling, difference unstable region (DUR).
Proposed approach
The goal of the proposed approach is to obtain a good estimate of the output response by integrating the information from both LF and HF models. Based on the variable-fidelity data, a LF model/metamodel is created as a start. Then, the obtained metamodel is taken as a base metamodel and is mapped to the studied HF model using scaling function. The combination of the LF model/metamodel with scaling function is based on an active learning process to exploit the already-acquired information.
Examples and results
In this section, we use a one-dimensional nonlinear numerical function example to illustrate the proposed method. We also apply the proposed modeling method to ten well-known numerical test problems with two or more design parameters and an engineering example to demonstrate that the proposed method is applicable to complex problems. For comparison, we model all tests with two other variable-fidelity metamodeling approaches, including maximum distance variable-fidelity metamodeling (MMD-VFM)
Engineering case 1: modeling aerodynamic data for NACA 0012 airfoil
In this section, we consider a NACA 0012 airfoil and use the proposed AL-VFM metamodeling approach to generate VFM models for the lift coefficient () as a function of two independent variables: Mach number Ma and angle of attact α. The ranges for the variables are , . Two different fidelity models are adopted to calculate . The grid of LF model consists of about 15,000 elements, shown in the Fig. 14(a), which extended to 15 times the airfoil length in each direction. For
Conclusion
In this paper, we propose the AL-VFM approach by transforming the one-shot VF metamodeling process into an active learning iterative process, in which the already-collected information is made full use of to guide the VF metamodeling. Since Kriging metamodel is adopted to map the difference between the HF and LF model, the proposed AL-VFM approach can approach the HF model on a global level. The active learning strategy introduced in AL-VFM is general in the sense that it can be integrated with
Acknowledgements
This research has been supported by the National Natural Science Foundation of China (NSFC) under Grant Nos. 51505163, 51421062 and 51323009, National Basic Research Program (973 Program) of China under Grant No. 2014CB046703, and the Fundamental Research Funds for the Central Universities, HUST: Grant No. 2014TS040. The authors also would like to thank the anonymous referees for their valuable comments.
References (40)
- et al.
Efficient space-filling and non-collapsing sequential design strategies for simulation-based modeling
Euro. J. Operat. Res.
(2011) - et al.
An adaptive global variable fidelity metamodeling strategy using a support vector regression based scaling function
Simul. Model. Pract. Theory
(2015) - et al.
A new methodology for multi-objective multidisciplinary design optimization problems based on game theory
Expert Syst. Appl.
(2015) - et al.
Process parameter optimization of lap joint fillet weld based on FEM–RSM–GA integration technique
Adv. Eng. Softw.
(2015) - et al.
Classification of major construction materials in construction environments using ensemble classifiers
Adv. Eng. Inform.
(2014) - et al.
A hybrid system for SPC concurrent pattern recognition
Adv. Eng. Inform.
(2007) - et al.
Taguchi-tuned radial basis function with application to high precision motion control
Artif. Intell. Eng.
(2001) - et al.
Support vector regression for anomaly detection from measurement histories
Adv. Eng. Inform.
(2013) - et al.
Improving variable-fidelity surrogate modeling via gradient-enhanced Kriging and a generalized hybrid bridge function
Aerosp. Sci. Technol.
(2013) - et al.
Variable-fidelity model selection for stochastic simulation
Reliab. Eng. Syst. Safety
(2014)
Improving surrogate-assisted variable fidelity multi-objective optimization using a clustering algorithm
Appl. Soft Comput.
A two-stage multi-fidelity optimization procedure for honeycomb-type cellular materials
Comput. Mater. Sci.
An efficient algorithm for constructing optimal design of computer experiments
J. Statist. Plan. Infer.
Optimization of laser brazing onto galvanized steel based on ensemble of metamodels
J. Intell. Manuf.
Cross-validation based single response adaptive design of experiments for Kriging metamodeling of deterministic computer simulations
Struct. Multidisc. Optim.
An enhanced analytical target cascading and Kriging model combined approach for multidisciplinary design optimization
Math. Prob. Eng.
Review of metamodeling techniques in support of engineering design optimization
J. Mech. Des.
Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions
Struct. Multidisc. Optim.
Metamodeling in multidisciplinary design optimization: how far have we really come?
AIAA J.
Sensitivity-based scaling for approximating structural response
J. Aircraft
Cited by (69)
An improved time advance method for distributed multi-resolution modelling with interactive deviation characterization
2024, Simulation Modelling Practice and TheoryEnsemble learning of multi-kernel Kriging surrogate models using regional discrepancy and space-filling criteria-based hybrid sampling method
2023, Advanced Engineering InformaticsDigital twin modeling for structural strength monitoring via transfer learning-based multi-source data fusion
2023, Mechanical Systems and Signal ProcessingEfficient multi-objective CMA-ES algorithm assisted by knowledge-extraction-based variable-fidelity surrogate model
2023, Chinese Journal of AeronauticsSelecting informative data for defect segmentation from imbalanced datasets via active learning
2023, Advanced Engineering Informatics