Adaptive infill sampling strategy for metamodeling: Challenge and future research directions (original) (raw)
Related papers
Exploration of Metamodeling Sampling Criteria for Constrained Global Optimization
Engineering Optimization, 2002
The use of surrogate models or metamodeling has lead to new areas of research in simulation-based design optimization. Metamodeling approaches have advantages over traditional techniques when dealing with the noisy responses and=or high computational cost characteristic of many computer simulations. This paper focuses on a particular algorithm, Efficient Global Optimization (EGO) that uses kriging metamodels. Several infill sampling criteria are reviewed, namely criteria for selecting design points at which the true functions are evaluated. The infill sampling criterion has a strong influence on how efficiently and accurately EGO locates the optimum. Variance-reducing criteria substantially reduce the RMS error of the resulting metamodels, while other criteria influence how locally or globally EGO searches. Criteria that place more emphasis on global searching require more iterations to locate optima and do so less accurately than criteria emphasizing local search.
Metamodeling for High Dimensional Simulation-Based Design Problems
Journal of Mechanical Design, 2010
Computational tools such as finite element analysis and simulation are widely used in engineering, but they are mostly used for design analysis and validation. If these tools can be integrated for design optimization, it will undoubtedly enhance a manufacturer’s competitiveness. Such integration, however, faces three main challenges: (1) high computational expense of simulation, (2) the simulation process being a black-box function, and (3) design problems being high dimensional. In the past two decades, metamodeling has been intensively developed to deal with expensive black-box functions, and has achieved success for low dimensional design problems. But when high dimensionality is also present in design, which is often found in practice, there lacks of a practical method to deal with the so-called high dimensional, expensive, and black-box (HEB) problems. This paper proposes the first metamodel of its kind to tackle the HEB problem. This paper integrates the radial basis function ...
Adaptive multi-fidelity sampling for CFD-based optimisation via radial basis function metamodels
International Journal of Computational Fluid Dynamics, 2019
The paper presents a study on four adaptive sampling methods of a multi-fidelity (MF) metamodel, based on stochastic radial basis functions (RBF), for global design optimisation based on expensive CFD computer simulations and adaptive grid refinement. The MF metamodel is built as the sum of a low-fidelity-trained metamodel and an error metamodel, based on the difference between high-and low-fidelity simulations. The MF metamodel is adaptively refined using dynamic sampling criteria, based on the prediction uncertainty in combination with the objective optimum and the computational cost of high-and low-fidelity evaluations. The adaptive sampling methods are demonstrated by four analytical benchmark and two design optimisation problems, pertaining to the resistance reduction of a NACA hydrofoil and a destroyer-type vessel. The performance of the adaptive sampling methods is assessed via objective function convergence.
Comparative studies of metamodelling techniques under multiple modelling criteria
Structural and Multidisciplinary Optimization, 2001
Despite advances in computer capacity, the enormous computational cost of running complex engineering simulations makes it impractical to rely exclusively on simulation for the purpose of design optimization. To cut down the cost, surrogate models, also known as metamodels, are constructed from and then used in place of the actual simulation models. In this paper, we systematically compare four popular metamodelling techniques -polynomial regression, multivariate adaptive regression splines, radial basis functions, and kriging -based on multiple performance criteria using fourteen test problems representing different classes of problems. Our objective in this study is to investigate the advantages and disadvantages of these four metamodelling techniques using multiple criteria and multiple test problems rather than a single measure of merit and a single test problem.
Numerical assessment of metamodelling strategies in computationally intensive optimization
Environmental Modelling & Software, 2011
Metamodelling is an increasingly more popular approach for alleviating the computational burden associated with computationally intensive optimization/management problems in environmental and water resources systems. Some studies refer to the metamodelling approach as function approximation, surrogate modelling, response surface methodology or model emulation. A metamodel-enabled optimizer approximates the objective (or constraint) function in a way that eliminates the need to always evaluate this function via a computationally expensive simulation model. There is a sizeable body of literature developing and applying a variety of metamodelling strategies to various environmental and water resources related problems including environmental model calibration, water resources systems analysis and management, and water distribution network design and optimization. Overall, this literature generally implies metamodelling yields enhanced solution efficiency and (almost always) effectiveness of computationally intensive optimization problems. This paper initially develops a comparative assessment framework which presents a clear computational budget dependent definition for the success/ failure of the metamodelling strategies, and then critically evaluates metamodelling strategies, through numerical experiments, against other common optimization strategies not involving metamodels. Three different metamodel-enabled optimizers involving radial basis functions, kriging, and neural networks are employed. A robust numerical assessment within different computational budget availability scenarios is conducted over four test functions commonly used in optimization as well as two real-world computationally intensive optimization problems in environmental and water resources systems. Numerical results show that metamodelling is not always an efficient and reliable approach to optimizing computationally intensive problems. For simpler response surfaces, metamodelling can be very efficient and effective. However, in some cases, and in particular for complex response surfaces when computational budget is not very limited, metamodelling can be misleading and a hindrance, and better solutions are achieved with optimizers not involving metamodels. Results also demonstrate that neural networks are not appropriate metamodelling tools for limited computational budgets while metamodels employing kriging and radial basis functions show comparable overall performance when the available computational budget is very limited.
Comparative studies of metamodeling techniques under multiple modeling criteria
8th Symposium on Multidisciplinary Analysis and Optimization, 2000
Despite the advances in computer capacity, the enormous computational cost of complex engineering simulations makes it impractical to rely exclusively on simulation for the purpose of design optimization. To cut down the cost, surrogate models, also known as metamodels, are constructed from and then used in lieu of the actual simulation models. In the paper, we systematically compare four popular metamodeling techniques-Polynomial Regression, Multivariate Adaptive Regression Splines, Radial Basis Functions, and Kriging-based on multiple performance criteria using fourteen test problems representing different classes of problems. Our objective in this study is to investigate the advantages and disadvantages these four metamodeling techniques using multiple modeling criteria and multiple test problems rather than a single measure of merit and a single test problem.
Development of metamodeling based optimization system for high nonlinear engineering problems
A metamodeling optimization system for nonlinear problems was developed in this study. Boundaries and best neighbors searching (BBNS) intelligent sampling method and fuzzy based progressive metamodeling for space reduction were integrated and applied for this system. The BBNS scheme generates new samples derived from information of boundaries and the best samples of initial sparse distributed samples. It is easy to obtain better samples and avoid local convergence due to boundary information. In order to construct accuracy metamodel, the fuzzy based progressive metamodeling method was implemented to cluster samples generated by BBNS several patches in optimization domain. Only better sets of them are involved in construction of metamodels in each patch by response surface and kriging method. The nonlinear problems with multi-humps as test functions were used for proving accuracy and efficiency of developed system. The practical nonlinear engineering problems were also successfully optimized by this system.
11th International Conference on Evolutionary and Deterministic Methods for Design, Optimization and Control with Applications to Industrial and Societal Problems, EUROGEN-2015, Glasgow, UK, 2015
The paper presents a global method for simulation-based design optimiza- tion (SBDO), which combines a dynamic radial basis function (DRBF) surrogate model with a sequential multi-criterion adaptive sampling (MCAS) technique. Start- ing from an initial training set, groups of new samples are sequentially selected aiming at both the improvement of the surrogate model global accuracy and the reduction of the objective function. The objective prediction and the associated un- certainty provided by the DRBF model are used by a multi-objective particle swarm optimization algorithm in order to define Pareto-optimal solutions. These are used by the MCAS technique, which selects new samples by down-sampling the Pareto front, allowing for a parallel infill of an arbitrary number of points at each iteration. The method is applied to a set of 28 unconstrained global optimization test prob- lems and a six-variable SBDO of the DTMB 5415 hull-form in calm water, based on potential flow simulations. Results show the effectiveness of the method in re- ducing the computational cost of the SBDO, providing the background for further developments and application to more complex ship hydrodynamic problems.
Review of metamodeling techniques in support of engineering design optimization
2007
Computation-intensive design problems are becoming increasingly common in manufacturing industries. The computation burden is often caused by expensive analysis and simulation processes in order to reach a comparable level of accuracy as physical testing data. To address such a challenge, approximation or metamodeling techniques are often used. Metamodeling techniques have been developed from many different disciplines including statistics, mathematics, computer science, and various engineering disciplines. The metamodels are initially developed as "surrogates" of the expensive simulation process in order to improve the overall computation efficiency. They are then found to be a valuable tool to support a wide scope of activities in modern engineering design, especially design optimization. This work reviews the state-of-the-art metamodel-based techniques from a practitioner's perspective according to the role of metamodeling in supporting design optimization, including model approximation, design space exploration, problem formulation, and solving various types of optimization problems. Challenges and future development of metamodeling in support of engineering design is also analyzed and discussed.
A multi-point sampling method based on kriging for global optimization
Structural and Multidisciplinary Optimization, 2017
In general, sampling strategy plays a very important role in metamodel based design optimization, especially when computationally expensive simulations are involved in the optimization process. The research on new optimization methods with less sampling points and higher convergence speed receives great attention in recent years. In this paper, a multi-point sampling method based on kriging (MPSK) is proposed for improving the efficiency of global optimization. The sampling strategy of this method is based on a probabilistic distribution function converted from the expected improvement (EI) function. It can intelligently draw appropriate new samples in an area with certain probability according to corresponding EI values. Besides, three strategies are also proposed to speed up the sequential sampling process and the corresponding convergence criterions are put forward to stop the searching process reasonably. In order to validate the efficiency of this method, it is tested by several numerical benchmark problems and applied in two engineering design optimization problems. Moreover, an overall comparison between the proposed method and several other typical global optimization methods has been made. Results show that the higher global optimization efficiency of this method makes it particularly suitable for design optimization problems involving computationally expensive simulations.