检索结果-内蒙古大学图书馆

loading pattern optimization using simulated annealing and binary machine learning pre-screening

NUCLEAR ENGINEERING AND TECHNOLOGY 2024年第5期56卷 1672-1678页

作者： Sim, Ga-Hee Park, Moon-Ghu Bae, Gyu-ri Sohn, Jung-Uk Sejong Univ Dept Quantum & Nucl Engn 209 Neungdong Ro Seoul 05006 South Korea ZettaCognition 310 Yulgok Gwan209 Neungdong Ro Seoul 05006 South Korea

We introduce a creative approach combining machine learning with optimization techniques to enhance the optimization of the loading pattern (LP). Finding the optimal LP is a critical decision that impacts both the reload safety and the economic feasibility of the nuclear fuel cycle. While simulated annealing (SA) is a widely accepted technique to solve the LP optimization problem, it suffers from the drawback of high computational cost since LP optimization requires three-dimensional depletion calculations. In this note, we introduce a technique to tackle this issue by leveraging neural networks to filter out inappropriate patterns, thereby reducing the number of SA evaluations. We demonstrate the efficacy of our novel approach by constructing a machine learning-based optimization model for the LP data of the Korea Standard Nuclear Power Plant (OPR-1000).

关键词： loading pattern optimization Binary learning Neural network Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

loading pattern optimization of VVER-1000 reactor core based on the discrete golden eagle optimization algorithm

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2024年第8期56卷 3425-3434页

作者： Fashami, Sajjad Abbasi Zangian, Mahdi Minuchehr, Abdolhamid Zolfaghari, Ahmadreza Shahid Beheshti Univ Engn Dept POB *** Tehran Iran

The main features of the loading pattern optimization (LPO) problem, such as high-dimensionality, multi-modality, and non-linearity, make it difficult to achieve a truly optimal configuration. In recent years, metaheuristic methods have been successfully used to solve this problem. In this research, a discrete golden eagle optimization (DGEO) algorithm has been developed to solve the LPO problem in the first cycle of VVER-1000 reactor core. To evaluate the proposed algorithm, a linear multi-purpose fitness function has been used to improve the safety parameters of the reactor core by obtaining a flatter power distribution during the first cycle, and also to enhance the economic parameters by increasing the cycle length and reducing the cost of fuel recycling. For this purpose, a FORTRAN program has been written to map the DGEO algorithm for the LPO problem using the PMAX and PARCS core calculation code to compute the fitness function in each iteration. To speed up the calculations, parallel computing has been applied in the written program. The results demonstrated that the loading pattern, which is suggested by the DGEO algorithm, enhances all the safety and economic parameters in the fitness function. Thus, the DGEO algorithm is highly reliable for the LPO problems in the VVER 1000 reactor core.

关键词： Nuclear reactor Metaheuristic methods loading pattern optimization Golden eagle optimization

来源：评论

学校读者我要写书评

暂无评论

A deterministic method for PWR loading pattern optimization

引用

ANNALS OF NUCLEAR ENERGY 2018年第Jul.期117卷 131-144页

作者： Rahman, Fariz B. Abdul Lee, John C. Franceschini, Fausto GE Hitachi Nucl Energy 3901 Castle Hayne Rd Wilmington NC 28402 USA Univ Michigan Ann Arbor MI 48109 USA Westinghouse Elect Co LLC Cranberry Township PA USA

A new deterministic approach to core loading optimization is presented. Selection of fuel enrichment and burnable poison (BP) arrangement in a pressurized water reactor (PWR) core are optimally determined subject to power peaking factor (PF) constraints. The deterministic approach is based on the method of Lagrange multipliers and the direct adjoining approach for the inequality power PF constraint. The optimality conditions are derived using calculus of variations resulting in the presence of jump conditions and a linear control Hamiltonian. The optimal control problems are addressed by simultaneously minimizing the Hamiltonian using the gradient method and performing Newton's method in different regions of the core to produce viable solutions for the controls. Without active control of the power profile in PWRs during depletion, our methodology is able to satisfy the power PF constraint at all times by proper loading selection at the beginning of cycle (BOC). This is achieved by promoting the proper burnup path forward in time during the calculation of the forward optimality conditions. This information is utilized in the adjoint burnup calculation, which acts to propagate the optimal control path back to the BOC during the calculation of the adjoint optimality conditions. The methodology has been developed into a new code DMCO (Deterministic Multi-Control optimization) which can produce two-dimensional two-group depletion results in approximately seven minutes per optimization iteration on a personal computer. No application of heuristics is required and the code is capable of finding solutions from initial control distributions. A preliminary case study is presented for the Westinghouse AP600 first cycle fuel loading design which achieved an extended fuel cycle while satisfying power PF constraints. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Deterministic method Multi-control loading pattern optimization

来源：评论

学校读者我要写书评

暂无评论

Neutronic and thermal-hydraulic aspects of loading pattern optimization during the first cycle of VVER-1000 reactor using Polar Bear optimization method

引用

ANNALS OF NUCLEAR ENERGY 2019年 133卷 538-548页

作者： Nasr, Mandi Aghili Zangian, Mandi Abbasi, Mohammadreza Zolfaghari, Ahmadreza Shahid Beheshti Univ Engn Dept POB *** Tehran Iran

loading pattern optimization (LPO) is an extremely important issue for the safe and economic operation at nuclear power plants because the core configuration affects many of the neutronic and thermal-hydraulic parameters (NTPs) of the reactor. Most researches were done in this area limited to employing different heuristic optimizing algorithm and the neutronic aspects at the beginning of the cycle (BOC). In this research, a comprehensive code package has been developed using coupling the PARCS code and the COBRA-EN code with the new Polar Bear optimization (PBO) algorithm, which tries to find an optimal loading pattern with maximized cycle length, maximized departure from the nucleate boiling ratio (DNBR), and flatter power distribution. Other core safety parameters such as maximum boric acid concentration at the BOC, maximum power peaking factor (PPF), the maximum temperature of the fuel center and the maximum clad surface temperature are considered as penalties for accepting or rejecting optimal configuration alongside the fitness function. This code Package which named PBLPO (Polar Bear loading pattern optimization) code, was implemented for the core of WER-1000 reactor in Bushehr Nuclear Power Plant (BNPP). The optimized pattern that found with PBLPO improved safety parameters comparing to loading pattern that the proposed in the Final Safety Analysis Report (FSAR) and shows that the polar bear algorithm has a good performance in LPO. (C) 2019 Published by Elsevier Ltd.

关键词： loading pattern optimization Polar Bear optimization method Working cycle length Neutronic Thermal-hydraulic WER-1000 reactor

来源：评论

学校读者我要写书评

暂无评论

Application of metaheuristics to loading pattern optimization problems based on the IAEA-3D and BIBLIS-2D data

引用

ANNALS OF NUCLEAR ENERGY 2018年第Jan.期111卷 329-339页

作者： de Moura Meneses, Anderson Alvarenga Araujo, Lenilson Moreira Nast, Fernando Nogueira da Silva, Patrick Vasconcelos Schirru, Roberto Fed Univ Western Para Inst Geosci & Engn Lab Computat Intelligence R Vera Paz S-N BR-68035110 Santarem PA Brazil Univ Fed Rio de Janeiro Nucl Engn Program COPPE Rio De Janeiro Brazil

The loading pattern optimization (LPO) of a Nuclear Power Plant (NPP), or in-core-fuel management optimization, is a real-world and prominent problem in Nuclear Engineering with the goal of finding an optimal (or near-optimal) loading pattern (LP), in terms of energy production, within adequate safety margins. Most of the reactor models used in the LPO problem are particular cases, such as research or power reactors with technical data that cannot be made available for several reasons, which makes the reproducibility of tests unattainable. In the present article we report the results of LPO of problems based upon reactor physics benchmarks. Since such data are well-known and widely available in the literature, it is possible to reproduce tests for comparison of techniques. We performed the LPO with the data of the benchmarks IAEA-3D and BIBLIS-2D. The Reactor Physics code RECNOD, which was used in previous works for the optimization of Angra 1 NPP in Brazil, was also used for further comparison. Four optimization Metaheuristics (OMHs) were applied to those problems: Particle Swarm optimization (PSO), Cross-Entropy algorithm (CE), Artificial Bee Colony (ABC) and Population-Based Incremental Learning (PBIL). For IAEA-3D, the best algorithm was the ABC. For BIBLIS-2D, PBIL was the best OMH. For Angra 1 / RECNOD optimization problem, PBIL, ABC and CE were the best OMHs. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： loading pattern optimization Nuclear Power Plant optimization Metaheuristics Pressurized water reactor Nuclear fuel

来源：评论

学校读者我要写书评

暂无评论

A loading pattern optimization method based on discrete differential evolution

引用

ANNALS OF NUCLEAR ENERGY 2020年 137卷 107057-107057页

作者： Ding, Hui Sun, Guangyao Hao, Lijuan Wu, Bin Wu, Yican Chinese Acad Sci Inst Nucl Energy Safety Technol Key Lab Neutron & Radiat Safety Hefei 230031 Anhui Peoples R China Univ Sci & Technol China Hefei 230027 Anhui Peoples R China

Core loading pattern (LP) optimization is a combinatorial optimization problem with significant impact on the economic and safety performance of a reactor. However, finding an optimal solution for core loading patterns is a very complex problem due to the large number of combinations of fuel assemblies. For this paper, a loading pattern optimization method based on discrete differential evolution was developed. To evaluate the method, a program coupled with SuperMC was developed and validated using a PWR test case. The program was then applied to minimize the radial power peak factor of the Watts Bar Nuclear 1 reactor under the constraint of the criticality state of the reactor. The results showed the discrete differential evolution to be reliable and effective in LP optimization. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Discrete differential evolution loading pattern optimization WBN1

来源：评论

学校读者我要写书评

暂无评论

PWR loading pattern optimization using Harmony Search algorithm

引用

ANNALS OF NUCLEAR ENERGY 2013年 53卷 288-298页

作者： Poursalehi, N. Zolfaghari, A. Minuchehr, A. Shahid Beheshti Univ Dept Engn GC Tehran Iran

In this paper a core reloading technique using Harmony Search, HS, is presented in the context of finding an optimal configuration of fuel assemblies, FA, in pressurized water reactors. To implement and evaluate the proposed technique a Harmony Search along Nodal Expansion Code for 2-D geometry, HSNEC2D, is developed to obtain nearly optimal arrangement of fuel assemblies in PWR cores. This code consists of two sections including Harmony Search algorithm and Nodal Expansion modules using fourth degree flux expansion which solves two dimensional-multi group diffusion equations with one node per fuel assembly. Two optimization test problems are investigated to demonstrate the HS algorithm capability in converging to near optimal loading pattern in the fuel management field and other subjects. Results, convergence rate and reliability of the method are quite promising and show the HS algorithm performs very well and is comparable to other competitive algorithms such as Genetic Algorithm and Particle Swarm Intelligence. Furthermore, implementation of nodal expansion technique along HS causes considerable reduction of computational time to process and analysis optimization in the core fuel management problems. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Harmony Search algorithm Nodal expansion method Fitness function loading pattern optimization

来源：评论

学校读者我要写书评

暂无评论

Application of Cuckoo Search algorithm to loading pattern optimization problems

引用

ANNALS OF NUCLEAR ENERGY 2020年 139卷 107214-107214页

作者： de Moura Meneses, Anderson Alvarenga da Silva, Patrick Vasconcelos Nast, Fernando Nogueira Araujo, Lenilson Moreira Schirru, Roberto Fed Univ Western Para Lab Computat Intelligence Av Vera Paz S-N BR-68035110 Santarem PA Brazil Univ Fed Rio de Janeiro COPPE Nucl Engn Program Rio De Janeiro Brazil

The loading pattern optimization (LPO) is related to important goals in a Nuclear Power Plant (NPP) operation such as the extension of the cycle according to safety margins. The LPO is a combinatorial problem of relevance and interest for Nuclear Engineering. optimization metaheuristics have been efficient in solving the LPO. The recent metaheuristic Cuckoo Search (CS) is based on the brood parasitism of some cuckoo species, combined with the behavior of the Levy flight of some birds. In the present work the results of the application of CS to the LPO using IAEA-3D and BIBLIS-2D benchmarks are presented, as well as the application of CS in the optimization of 7th cycle of Angra 1 NPP, in Brazil. The results are compared to the metaheuristics Artificial Bee Colony and Population-Based Incremental Learning. Statistical analyses show that CS is the most robust algorithm for the set of instances selected for tests. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： loading pattern optimization Nuclear Power Plant optimization metaheuristics Pressurized water reactor Cuckoo Search Nuclear fuel

来源：评论

学校读者我要写书评

暂无评论

An Improved Inverse Analysis Model for Fuel loading pattern optimization

引用

JOURNAL OF NUCLEAR SCIENCE AND TECHNOLOGY 2009年第12期46卷 1162-1169页

作者： Tran, Hoai Nam Yamamoto, Akio Yamane, Yoshihiro Nagoya Univ Dept Mat Phys & Energy Engn Chikusa Ku Nagoya Aichi 4648603 Japan

An improved inverse analysis model for fuel loading pattern (LP) optimization is proposed to reproduce a desired in-core power distribution from available fuel assemblies based on the inverse analysis of diffusion equations. In the present approach, the inverse analysis is simplified as a fixed-source problem rather than an eigenvalue problem in a previous work. By using the one-to-one correspondence between the power distribution and reactivity distribution, a target reactivity distribution is solved from a desired power distribution through the inverse analysis. The reactivity of available assemblies is evaluated using a modified effective fast-group model with a higher order correction of leakage effect. A candidate LP is determined by individually matching the reactivity of available assemblies to the target in-core reactivity distribution using a stable matching algorithm. The process of predicting the reactivity of available assemblies and matching them to the target reactivity distribution is repeated until the convergence condition is satisfied. Validation of the model has been confirmed with a reference PWR core. The model is expected to be applicable to a problem of multicycle loading pattern optimization.

关键词： inverse analysis power distribution loading pattern optimization modified effective fast-group model stable matching algorithm

来源：评论

学校读者我要写书评

暂无评论

Core loading pattern optimization of a typical two-loop 300 MWe PWR using Simulated Annealing (SA), novel crossover Genetic Algorithms (GA) and hybrid GA(SA) schemes

引用

ANNALS OF NUCLEAR ENERGY 2014年 65卷 122-131页

作者： Zameer, Aneela Mirza, Sikander M. Mirza, Nasir M. Pakistan Inst Engn & Appl Sci Dept Comp & Informat Sci Islamabad 45650 Pakistan Pakistan Inst Engn & Appl Sci Dept Phys & Appl Math Islamabad 45650 Pakistan

A comparative study of the Simulated Annealing and Genetic Algorithms based optimization of loading pattern with power profile flattening as the goal, has been carried out using the LEOPARD and MCRAC neutronic codes, for a typical 300 MWe PWR. At high annealing rates, Simulated Annealing exhibited tendency towards premature convergence while at low annealing rates, it failed to converge to global minimum. The new 'batch composition preserving' Genetic Algorithms with novel crossover and mutation operators are proposed in this work which, consistent with the earlier findings (Yamamoto, 1997), for small population size, require comparable computational effort to Simulated Annealing with medium annealing rates. However, Genetic Algorithms exhibit stagnation for small population size. A hybrid Genetic Algorithms (Simulated Annealing) scheme is proposed that utilizes inner Simulated Annealing layer for further evolution of population at stagnation point. The hybrid scheme has been found to escape stagnation in bcp Genetic Algorithms and converge to the global minima with about 51% more computational effort for small population sizes. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Simulated Annealing Genetic Algorithms loading pattern optimization Pressurized Water Reactors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：