• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3409-3416
• /
• 2023

Licensing the next-generation of nuclear reactor designs requires extensive use of Modeling and Simulation (M&S) to investigate system response to many operational conditions, identify possible accidental scenarios and predict their evolution to undesirable consequences that are to be prevented or mitigated via the deployment of adequate safety barriers. Deep Learning (DL) and Artificial Intelligence (AI) can support M&S computationally by providing surrogates of the complex multi-physics high-fidelity models used for design. However, DL and AI are, generally, low-fidelity 'black-box' models that do not assure any structure based on physical laws and constraints, and may, thus, lack interpretability and accuracy of the results. This poses limitations on their credibility and doubts about their adoption for the safety assessment and licensing of novel reactor designs. In this regard, Physics Informed Neural Networks (PINNs) are receiving growing attention for their ability to integrate fundamental physics laws and domain knowledge in the neural networks, thus assuring credible generalization capabilities and credible predictions. This paper presents the use of PINNs as surrogate models for accidental scenarios simulation in Nuclear Power Plants (NPPs). A case study of a Loss of Heat Sink (LOHS) accidental scenario in a Nuclear Battery (NB), a unique class of transportable, plug-and-play microreactors, is considered. A PINN is developed and compared with a Deep Neural Network (DNN). The results show the advantages of PINNs in providing accurate solutions, avoiding overfitting, underfitting and intrinsically ensuring physics-consistent results.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권1호
• /
• pp.29-36
• /
• 2016

Tensairity girder is a light weight inflatable fabric structural concept which can be used in road emergency transportation. It uses low pressure air to stabilize compression elements against buckling. With the purpose of obtaining the comprehensive target of minimum deflection and weight under ultimate load, the cross-section and the inner pressure of tensairity girder was optimized in this paper. The Variable Complexity Modeling (VCM) method was used in this paper combining the Kriging approximate method with the Finite Element Analysis (FEA) method, which was implemented by ABAQUS. In the Kriging method, the sample points of the surrogate model were outlined by Design of Experiment (DOE) technique based on Optimal Latin Hypercube. The optimization framework was constructed in iSIGHT with a global optimization method, Multi-Island Genetic Algorithm (MIGA), followed by a local optimization method, Sequential Quadratic Program (SQP). The result of the optimization gives a prominent conceptual design of the tensairity girder, which approves the solution architecture of VCM is feasible and efficient. Furthermore, a useful trend of sensitivity between optimization variables and responses was performed to guide future design. It was proved that the inner pressure is the key parameter to balance the maximum Von Mises stress and deflection on tensairity girder, and the parameters of cross section impact the mass of tensairity girder obviously.

• Smart Structures and Systems
• /
• 제22권5호
• /
• pp.561-574
• /
• 2018

In this paper, for efficiently reducing the computational cost of the model updating during the optimization process of damage detection, the structural response is evaluated using properly trained surrogate model. Furthermore, in practice uncertainties in the FE model parameters and modelling errors are inevitable. Hence, an efficient approach based on Monte Carlo simulation is proposed to take into account the effect of uncertainties in developing a surrogate model. The probability of damage existence (PDE) is calculated based on the probability density function of the existence of undamaged and damaged states. The current work builds a framework for Probability Based Damage Detection (PBDD) of structures based on the best combination of metaheuristic optimization algorithm and surrogate models. To reach this goal, three popular metamodeling techniques including Cascade Feed Forward Neural Network (CFNN), Least Square Support Vector Machines (LS-SVMs) and Kriging are constructed, trained and tested in order to inspect features and faults of each algorithm. Furthermore, three wellknown optimization algorithms including Ideal Gas Molecular Movement (IGMM), Particle Swarm Optimization (PSO) and Bat Algorithm (BA) are utilized and the comparative results are presented accordingly. Furthermore, efficient schemes are implemented on these algorithms to improve their performance in handling problems with a large number of variables. By considering various indices for measuring the accuracy and computational time of PBDD process, the results indicate that combination of LS-SVM surrogate model by IGMM optimization algorithm have better performance in predicting the of damage compared with other methods.

• 융합정보논문지
• /
• 제10권7호
• /
• pp.138-146
• /
• 2020

본 논문은 다양한 설계하중조건 상태에서 자동채염기 구조설계의 성능분석과 개선을 위해 실험계획법을 이용한 설계민감도 평가와 대리모델의 특성에 대한 비교연구를 수행하였다. 실험계획법은 수치해석 기반의 직교배열설계 방법을 이용하였다. 설계인자는 주요 구조부재의 두께치수 변수를 고려하였고, 응답치는 중량과 강도성능을 선정하였다. 직교배열실험을 통해 설계인자 별 응답치에 대한 정량적인 영향도를 분석하였다. 또한 최소의 중량증감으로 구조성능을 개선할 수 있는 최적의 설계조건을 탐색하였다. 직교배열실험 결과를 이용하여 반응표면모델, 크리깅모델, 그리고 체비쇼프 직교 다항식과 같은 다양한 대리모델을 생성하였다. 대리모델의 결과를 통해 직교배열실험 결과의 타당성을 검증하였다. 자동채염기 구조설계 공간 탐색에는 반응표면모델이 가장 적합한 대리모델로 평가되었다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집B
• /
• pp.501-506
• /
• 2001

Computer modeling is essential to evaluate possible design of suspension for a railway vehicles. By creating a simulation, the engineers are able to assess the feasibility of a given design and change the design factors to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have turned to surrogate modeling. A surrogate model is essentially a regression performed on a data sampling of the simulation. In the most general sense, metamodels(surrogate model) take the form $y(x)=f(x)+{\varepsilon}$, where y(x) is the true simulation output, f(x) is the metamodel output, and $\varepsilon$ is the error between the two. In this paper, a second order polynomial equation is partially used as a metamodel to represent the forty-six dynamic performances for high speed train. The number of factors as design variables of the metamodel is twenty-nine, which are composed the dynamic characteristics of suspension. This metamodel is used to search the optimum values of suspension characteristics which minimize the dynamic responses for high speed train. This optimization is a multi-objective problem which have many design variables. This paper shows that the response surface model which is made through the design of analysis of computer experiments method is very efficient to solve this complex optimization problem.

• 한국유체기계학회 논문집
• /
• 제14권1호
• /
• pp.66-76
• /
• 2011

The heat transfer and pressure loss characteristics of a rotating two-pass channel with a guide vane in the turning region have been studied using three-dimensional Reynolds-averaged Navier-Stokes (RANS) analysis, and the shape of the guide vane has been optimized using surrogate modeling optimization technique. For the optimization, thickness, location and angle of the guide vanes have been selected as design variables. The objective function has been defined as a linear combination of the heat transfer and the friction loss related terms with a weighting factor. Latin hypercube sampling has been applied to determine the design points as design of experiments. A weighted-average surrogate model, PBA has been used as the surrogate model. The guide vane in the turning region does not influence the heat transfer in the first passage upstream of the turning region, but enhances largely the heat transfer in the turning region and the second passage. In an example of the optimization, the objective function has been increased by 13.6%.

• International Journal of Fluid Machinery and Systems
• /
• 제9권3호
• /
• pp.265-276
• /
• 2016

Energy systems working coherently in different conditions may not have a specific design which can provide optimal performance. A system working for a longer period at lower efficiency implies higher energy consumption. In this effort, a methodology demonstrated by a jet pump design and optimization via numerical modeling for fluid dynamics and implementation of an evolutionary algorithm for the optimization shows a reduction in computational costs. The jet pump inherently has a low efficiency because of improper mixing of primary and secondary fluids, and multiple momentum and energy transfer phenomena associated with it. The high fidelity solutions were obtained through a validated numerical model to construct an approximate function through surrogate analysis. Pareto-optimal solutions for two objective functions, i.e., secondary fluid pressure head and primary fluid pressure-drop, were generated through a multi-objective genetic algorithm. For the jet pump geometry, a design space of several design variables was discretized using the Latin hypercube sampling method for the optimization. The performance analysis of the surrogate models shows that the combined surrogates perform better than a single surrogate and the optimized jet pump shows a higher performance. The approach can be implemented in other energy systems to find a better design.

• Nuclear Engineering and Technology
• /
• 제52권2호
• /
• pp.287-295
• /
• 2020

Group method of data handling (GMDH) is considered one of the earliest deep learning methods. Deep learning gained additional interest in today's applications due to its capability to handle complex and high dimensional problems. In this study, multi-layer GMDH networks are used to perform uncertainty quantification (UQ) and sensitivity analysis (SA) of nuclear reactor simulations. GMDH is utilized as a surrogate/metamodel to replace high fidelity computer models with cheap-to-evaluate surrogate models, which facilitate UQ and SA tasks (e.g. variance decomposition, uncertainty propagation, etc.). GMDH performance is validated through two UQ applications in reactor simulations: (1) low dimensional input space (two-phase flow in a reactor channel), and (2) high dimensional space (8-group homogenized cross-sections). In both applications, GMDH networks show very good performance with small mean absolute and squared errors as well as high accuracy in capturing the target variance. GMDH is utilized afterward to perform UQ tasks such as variance decomposition through Sobol indices, and GMDH-based uncertainty propagation with large number of samples. GMDH performance is also compared to other surrogates including Gaussian processes and polynomial chaos expansions. The comparison shows that GMDH has competitive performance with the other methods for the low dimensional problem, and reliable performance for the high dimensional problem.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.870-875
• /
• 2004

Current trend of design technologies shows engineers to objectify or automate the given decision-making process. The numerical optimization is an example of such technologies. However, in numerical optimization, the uncertainties are uncontrollable to efficiently objectify or automate the process. To better manage these uncertainties, Taguchi method, reliability-based optimization and robust optimization are being used. To obtain the target performance with the maximum robustness is the main functional requirement of a mechanical system. In this research, the robust design strategy is developed based on the DACE and the global optimization approaches. The DACE modeling, known as the one of Kriging interpolation, is introduced to obtain the surrogate approximation model of the system. The robustness is determined by the DACE model to reduce the real function calculations. The simulated annealing algorithm of global optimization methods is adopted to determine the global robust design of a surrogated model. The mathematical problems and the MEMS design problem are investigated to show the validity of the proposed method.

• 한국유체기계학회 논문집
• /
• 제12권4호
• /
• pp.44-53
• /
• 2009

Numerical design optimization of a fan-shaped hole for film-cooling has been carried out to improve film-cooling effectiveness by combining a three-dimensional Reynolds-averaged Navier-Stokes analysis with the radial basis neural network method, a well known surrogate modeling technique for optimization. The injection angle of hole, lateral expansion angle of hole and ratio of length-to-diameter of the hole are chosen as design variables and spatially averaged film-cooling effectiveness is considered as an objective function which is to be maximized. Twenty training points are obtained by Latin Hypercube sampling for three design variables. Sequential quadratic programming is used to search for the optimal point from the constructed surrogate. The film-cooling effectiveness has been successfully improved by the optimization with increased value of all design variables as compared to the reference geometry.