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

loading pattern optimization of a PWR using newly developed Multi-Verse optimization algorithm

引用

NUCLEAR ENGINEERING AND DESIGN 2024年 426卷

作者： Safari, M. Aghaie, M. Salimi, K. Shahid Beheshti Univ Engn Dept GCPOB *** Tehran Iran

In the fuel management of nuclear reactors, which has a direct impact on power generation costs and environmental factors, it is essential to obtain an optimal arrangement of assemblies and core parameters. This complex task relies on both neutronics and thermal hydraulics. This research solves this by employing PARCS and COBRA-EN codes, alongside Multi-Verse optimization algorithm (MVO) as a novel algorithm. Findings demonstrate the MVO algorithm has reliability and favorable convergence rate. Moreover, integrating the nodal expansion technique with MVO notably decreases the computational time for optimization in the loading pattern optimizations (LPOs). The optimized loading pattern aligns well with the findings in the literature. Also, using multi objective fitness function leads to improving core flatness, cycle length and safety parameters.

关键词： loading pattern optimization WWER1000 reactor Neutronics Thermal -hydraulic Meta -heuristic algorithm COBRA -EN PARCS MVO MFO GSA HS

来源：评论

学校读者我要写书评

暂无评论

Multi-objective loading pattern optimization of a soluble boron free core using social spider algorithm

引用

NUCLEAR ENGINEERING AND DESIGN 2024年 420卷

作者： Hosseinllu, M. Abbasi, M. Safarzadeh, O. Dehghani, F. Shahid Beheshti Univ Fac Engn Tehran Iran Shahed Univ Fac Engn Tehran Iran

Shortly due to their favorable economic and safety characteristics, Small Modular Reactors (SMR) systems are expected to be in high demand. To ensure effective operation and the proper safety margins of SMRs, it is crucial to find the optimum loading pattern (LP). In this paper, we proposed a 300 MWth soluble boron free UO2 fueled core with 20 MWd/KgU discharge burnup. The Fuel Assemblies (FAs) and Burnable Poisons (BPs) configuration for LP of the Soluble Boron Free (SBF) SMR core must fulfill specific technical requirements. A new metaheuristic optimization algorithm, Social Spider Algorithm (SSA), is developed for implementation in the loading pattern optimization (LPO) of the SMR cores. The SSA provides results that are comparable with PSO solutions as a popular method that are used for LPO problems. A new multi -objective cost function is recommended for LPO of SBF SMRs, which have high through -life reactivity swing due to poison depletion. The objectives of a neutronic parameters such as assessing appropriate excess reactivity, reducing the radial PPF at Beginning Of Cycle (BOC), reducing the highest radial PPF entire the cycle, reducing the reactivity swing entire the cycle, and achieve to proper cycle length have been considered simultaneously. Apart from the newly proposed two -batch SBF core with a new metaheuristic algorithm, the control rod movement scheme is considered entire the irradiation cycle to reach the core criticality. The new method results in promising convergence rates and reliability;hence it can be used in various optimization applications in the field of nuclear engineering.

关键词： Social Spider Algorithm loading pattern optimization Small Modular Reactor Soluble Boron Free core

来源：评论

学校读者我要写书评

暂无评论

Fuel assemblies loading pattern optimization of pressurized water reactors using the trees social relations algorithm

引用

ANNALS OF NUCLEAR ENERGY 2023年第1期192卷

作者： Shams, Sajjad Azgomi, Hossein Asghari, Ali Shafagh Inst Higher Educ Dept Comp Engn Tonekabon Iran Islamic Azad Univ Dept Comp Engn Rasht Branch Rasht Iran

Pressurized water reactors (PWR) are a type of light water nuclear reactors that constitute most nuclear power plants in the world. In PWRs, the initial coolant is water that is pumped into the reactor core with high pressure where it is heated by the energy released from nuclear fission. Then, the high-pressure hot water flows into a steam generator where its thermal energy is transferred to the water with lower pressure, and steam is generated. The steam, then, spins turbines that rotate an electrical generator to generate power. It is crucial to increase the safety of PWRs in nuclear power plants. A measure to ensure the safety of these reactors is to optimize the fuel assemblies loading (FAL) pattern. This paper presents a method to optimize the FAL pattern of PWRs by the trees social relations (TSR) optimization algorithm. The TSR algorithm is a metaheuristic algorithm inspired by the hierarchical life of trees in the jungle. The proposed method models the problem of FAL pattern optimization by the TSR algorithm. This method is practically compared with other methods. Based on the results, it outperforms similar methods in terms of the multiplication factor, power flattening, and fitness of the final solution.

关键词： Fuel assemblies loading pattern optimization Pressurized water reactors (PWR) Reactors TSR algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuel loading pattern optimization of ALLEGRO fast reactor using genetic algorithms

引用

ANNALS OF NUCLEAR ENERGY 2023年 180卷

作者： Lima-Reinaldo, Yrobel Francois, Juan-Luis Univ Nacl Autonoma Mexico Fac Ingn Dept Sistemas Energet Paseo Cuauhnahuac 8532 Jiutepec 62550 Morelos Mexico

In this work the genetic algorithmic (GA) optimization technique is used to find the optimal fuel loading pattern in the experimental fast reactor ALLEGRO. The penalty function method is used to solve this multi-objective combinatorial optimization problem. To evaluate each loading pattern, an interface between the genetic algo-rithm code and the ERANOS 2.3 deterministic neutronic simulation code was developed. For the simulation of the fuel cycle in ERANOS, the diffusion approach and a 7-group energy structure are used to reduce the computational cost. An integer variable encoding scheme was defined to represent the fuel loading patterns. Two crossover operators, the partially mapped crossover (PMX) and the order crossover (OX), combined with the random mutation operator were implemented as an alternative to the classical operators used in GA. To evaluate the performance of the code the results are compared using two objective functions and two crossover operators. In the first case the operating cycle length is maximized by maximizing the k-eff value at the EOC by satisfying the constraints on the power peaking factor over the cycle, the excess reactivity at the BOC, and the linear heat generation rate constraints. In addition, a condition was imposed that there should be no more than two contiguous positions in the pattern to preserve the power distribution uniformity and to avoid high power peaking factors. The code works very well, and a good solution was found in a reasonable computation time. The best solution corresponds to the PMX operator, and the running time is twice as short compared to the OX operator. In the second case study, a power distribution flatness term is included in the objective function. In this case, a more uniform radial power distribution is obtained but associated with a decrease in cycle length due to the penalty of the flatness term.

关键词： loading pattern optimization Genetic algorithms Gas-cooled fast reactor ALLEGRO reactor ERANOS code

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

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

PWR core loading pattern optimization with adaptive genetic algorithm

引用

ANNALS OF NUCLEAR ENERGY 2021年 159卷 108331-108331页

作者： So, Chol Ho, Il-Mun Chae, Jong-Suk Hong, Kwang-Hak Kim Il Sung Univ Fac Energy Sci Pyongyang North Korea

Y In this paper, a new adaptive genetic algorithm (AGA) is proposed for the loading pattern optimization (LPO) of the pressurized water reactor (PWR) core. The tournament selection, the two-point crossover and the mutation based on randomly swapping positions between two fuel assemblies (FAs) are applied. New calculation formulae are introduced to adjust effectively the crossover and mutation probabilities according to the fitness value of the individual. The proposed algorithm is implemented in the LPO for the first core of the 1000 MWe PWR. The objective function is to minimize the maximum radial power peaking factor (RPPF) at the equilibrium of Xe under the constraint condition for the cycle length. The maximum RPPF of the obtained LP is decreased than that of the loading pattern (LP) by the designer. The results show that the proposed AGA is effective to improve the convergence rate of genetic algorithms (GAs) in the LPO. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Fuel management loading pattern optimization Adaptive genetic algorithm PWR

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

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：