检索结果-内蒙古大学图书馆

Inverse design of electromagnetic metamaterials: from iterative to deep learning-based methods

JOURNAL OF MICROMECHANICS AND MICROENGINEERING 2024年第5期34卷 053001-053001页

作者： Ma, Chen Wang, Zhenyu Zhang, Hui Yang, Fengyuan Chen, Jianlin Ren, Qinghua Ma, Yiming Wang, Nan Shanghai Univ Sch Microelect Shanghai 201800 Peoples R China Shanghai Univ Shanghai Collaborat Innovat Ctr Intelligent Sensin Shanghai 201800 Peoples R China Harbin Inst Technol Weihai Dept Math Weihai 264209 Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong 999077 Peoples R China

In recent years, considerable research advancements have emerged in the application of inverse design methods to enhance the performance of electromagnetic (EM) metamaterials. Notably, the integration of deep learning (DL) technologies, with their robust capabilities in data analysis, categorization, and interpretation, has demonstrated revolutionary potential in optimization algorithms for improved efficiency. In this review, current inverse design methods for EM metamaterials are presented, including topology optimization (TO), evolutionary algorithms (EAs), and DL-based methods. Their application scopes, advantages and limitations, as well as the latest research developments are respectively discussed. The classical iterative inverse design methods categorized TO and EAs are discussed separately, for their fundamental role in solving inverse design problems. Also, attention is given on categories of DL-based inverse design methods, i.e. classifying into DL-assisted, direct DL, and physics-informed neural network methods. A variety of neural network architectures together accompanied by relevant application examples are highlighted, as well as the practical utility of these overviewed methods. Finally, this review provides perspectives on potential future research directions of EM metamaterials inverse design and integrated artificial intelligence methodologies.

关键词： inverse design electromagnetic metamaterials topology optimization evolutionary algorithms surrogate modeling inverse networks physics-informed neural networks

来源：评论

学校读者我要写书评

暂无评论

A multi-hybrid algorithm with shrinking population adaptation for constraint engineering design problems

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2024年 421卷

作者： Salgotra, Rohit Sharma, Pankaj Raju, Saravanakumar AGH Univ Krakow Fac Phys & Appl Comp Sci Krakow Poland Middle East Univ MEU Res Unit Amman Jordan Vellore Inst Technol Sch Elect Engn Vellore Tamil Nadu India

A multi -hybrid algorithm is proposed in this paper based on the Kepler Optimization algorithm (KOA), Red Panda Optimization (RPO), Meerkat Optimization (MO), and Grey Wolf Optimizer (GWO). The proposed multi -hybrid algorithm, known as the Kepler Red Meerkat Grey (KRMG) algorithm, incorporates the concepts of iterative division and mutation operators for enhanced operation. The KRMG algorithm utilizes a new population shrinking mechanism to reduce the population size over subsequent iterations for reducing the computational burden. To evaluate the efficiency of the KRMG algorithm in solving global optimization challenges, it has been tested on IEEE CEC 2014, CEC 2017, CEC 2019, as well as CEC 2022 benchmark test challenges. Also, the performance of the KRMG algorithm has been evaluated for six constraint engineering design optimization problems. Furthermore, the KRMG algorithm has also been evaluated for the parameter identification of proton exchange membrane fuel cells (PEMFC) on three distinct PEMFC modules, including the BCS 500 W, Ballard Mark V, as well as 250 W stack. Experimental and statistical comparison with respect to jDE100, FROBL-GJO, LX-TLA, RW-GWO, LSHADE-EpSin, EBOwithCMAR, jSO, SHADE, SaDE, JADE and others, prove that the proposed KRMG is statistically significant with respect to other algorithms under comparison, and can be considered as a potential candidate for future research.

关键词： evolutionary algorithms CEC benchmarks Engineering design optimization KRMG algorithm Proton-exchange membrane fuel cells

来源：评论

学校读者我要写书评

暂无评论

Taper design and optimization by evolutionary algorithms

Taper design and optimization by evolutionary algorithms

引用

Latin America Optics and Photonics Conference, LAOP 2014

作者： Dourado-Sisnando, A. Vieira, Luana da França Rodríguez-Esquerre, V.F. Rubio-Mercedes, C.E. Department of Electrical Engineering Federal University of Bahia University of Bahia UFBA Brazil State University of Mato Grosso do Sul UEMS Brazil

Power coupling between different size waveguides has been successfully and efficiently designed and optimized by using evolutionary algorithms based on the artificial immune system and differential evolution in conjun... 详细信息

ISBN: (纸本)9781557528254

关键词： evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysing Equilibrium States for Population Diversity

引用

ALGORITHMICA 2024年第7期86卷 1-35页

作者： Lengler, Johannes Opris, Andre Sudholt, Dirk Swiss Fed Inst Technol Inst Theoret Comp Sci Zurich Switzerland Univ Passau Fac Comp Sci & Math Passau Germany

Population diversity is crucial in evolutionary algorithms as it helps with global exploration and facilitates the use of crossover. Despite many runtime analyses showing advantages of population diversity, we have no clear picture of how diversity evolves over time. We study how the population diversity of (mu+1)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\mu +1)$$\end{document} algorithms, measured by the sum of pairwise Hamming distances, evolves in a fitness-neutral environment. We give an exact formula for the drift of population diversity and show that it is driven towards an equilibrium state. Moreover, we bound the expected time for getting close to the equilibrium state. We find that these dynamics, including the location of the equilibrium, are unaffected by surprisingly many algorithmic choices. All unbiased mutation operators with the same expected number of bit flips have the same effect on the expected diversity. Many crossover operators have no effect at all, including all binary unbiased, respectful operators. We review crossover operators from the literature and identify crossovers that are neutral towards the evolution of diversity and crossovers that are not.

关键词： evolutionary algorithms Runtime analysis Diversity Population dynamics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on the Role of Artificial Intelligence in Power System Stability, Control, and Protection: Insights and Future Directions

引用

APPLIED SCIENCES-BASEL 2024年第14期14卷 6214页

作者： Alhamrouni, Ibrahim Abdul Kahar, Nor Hidayah Salem, Mohaned Swadi, Mahmood Zahroui, Younes Kadhim, Dheyaa Jasim Mohamed, Faisal A. Alhuyi Nazari, Mohammad Univ Kuala Lumpur British Malaysian Inst Bt 8Jalan Sungai Pusu Gombak 53100 Selangor Malaysia Univ Sains Malaysia USM Sch Elect & Elect Engn Nibong Tebal 14300 Penang Malaysia Libyan Author Sci Res POB 80045 Tripoli Libya Univ Baghdad Coll Engn Dept Elect Engn Baghdad 10001 Iraq Norwegian Univ Sci & Technol NTNU Dept Engn Cybernet N-7034 Trondheim Norway Univ Tehran Fac New Sci & Technol Tehran *** Iran Duy Tan Univ Sch Engn & Technol Da Nang 550000 Vietnam Lovely Profess Univ Res & Dev Cell Phagwara 144411 India

This review comprehensively examines the burgeoning field of intelligent techniques to enhance power systems' stability, control, and protection. As global energy demands increase and renewable energy sources become more integrated, maintaining the stability and reliability of both conventional power systems and smart grids is crucial. Traditional methods are increasingly insufficient for handling today's power grids' complex, dynamic nature. This paper discusses the adoption of advanced intelligence methods, including artificial intelligence (AI), deep learning (DL), machine learning (ML), metaheuristic optimization algorithms, and other AI techniques such as fuzzy logic, reinforcement learning, and model predictive control to address these challenges. It underscores the critical importance of power system stability and the new challenges of integrating diverse energy sources. The paper reviews various intelligent methods used in power system analysis, emphasizing their roles in predictive maintenance, fault detection, real-time control, and monitoring. It details extensive research on the capabilities of AI and ML algorithms to enhance the precision and efficiency of protection systems, showing their effectiveness in accurately identifying and resolving faults. Additionally, it explores the potential of fuzzy logic in decision-making under uncertainty, reinforcement learning for dynamic stability control, and the integration of IoT and big data analytics for real-time system monitoring and optimization. Case studies from the literature are presented, offering valuable insights into practical applications. The review concludes by identifying current limitations and suggesting areas for future research, highlighting the need for more robust, flexible, and scalable intelligent systems in the power sector. This paper is a valuable resource for researchers, engineers, and policymakers, providing a detailed understanding of the current and future potential of intelligen

关键词： smart grid artificial intelligence power system stability power system protection wavelet transformation neural network evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Large-Scale evolutionary Optimization Approach Based on Decision Space Decomposition

引用

FRONTIERS IN ENERGY RESEARCH 2022年 10卷

作者： Ma, Jia Chang, Fengrong Yu, Xinxin Shenyang Aerosp Univ Coll Econ & Management Shenyang Peoples R China East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai Peoples R China Northeastern Univ Coll Software Shenyang Peoples R China

The identification of decision variable interactions has a crucial role in the final outcome of the algorithm in the large-scale optimization domain. It is a prerequisite for decomposition-based algorithms to achieve grouping. In this paper, we design a recognition method with higher efficiency and grouping accuracy. It is based on the decomposition strategy of min hash to solve large-scale global optimization (LSGO) problems, called MHD. Our proposed method focuses on discovering the interactions of decision variables through min hash and forming subcomponents with a principle that the interdependencies between these subcomponents are maintained at a minimal level. This is described as follows: first, the min hash performs several permutations of the vector composed of decision variables. Second, the index value of the first non-zero row of the vector after rearrangement is found to obtain the new feature vector. Third, the probability of identical data at each position is calculated based on the new feature vector to decide whether there are some certain interactions between the decision variables. The advantages of min hash are: simpler computation and greater efficiency improvement than comparison between two or two decision variables;ability to find similar decision variables very quickly;and ability to cluster decision variables in a simple way. Therefore, the efficiency as well as the reliability of MHD is guaranteed. On the accuracy aspect, the proposed algorithm performs well in various types of the large-scale global optimization benchmark test function. Finally, the experimental results analysis and summarize the performance competitiveness of our proposed MHD algorithm from several aspects when it is used within a co-evolutionary framework.

关键词： min hash evolutionary algorithms cooperation co-evolution decision space decomposition large-scale global optimization

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Intrusion Detection via evolutionary Cost-Sensitive Learning and Fog Computing

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第22期9卷 23260-23271页

作者： Telikani, Akbar Shen, Jun Yang, Jie Wang, Peng Univ Wollongong Sch Comp & Informat Technol Wollongong NSW 2522 Australia

Cyber attacks and intrusions have become the major obstacles to the adoption of the Industrial Internet of Things (HoT) in critical industries. Imbalanced data distribution is a common problem in HoT environments that negatively influence machine learning-based intrusion detection systems (IDSs). To address this issue, we introduce EvolCostDeep, a hybrid model of stacked autoencoders (SAE) and convolutional neural networks (CNNs) with a new cost-dependent loss function. The loss function aims to optimize the model's parameters, where the costs are determined using an evolutionary algorithm. The combination of evolutionary algorithms and deep learning (DL) on Big data hinders the scalability of HoT IDSs. In this regard, a fog computing-enabled framework, called DeepIDSFog, is designed at the data level, where the master node shares the EvolCostDeep model with worker nodes. In each fog worker node, the EvolCostDeep is parallelized through one task-level and two model-level mechanisms. After aggregating detection outputs from worker nodes to the master, the result is passed to the cloud platform for mitigating attacks. A series of experiments is conducted on the ToN-IoT and UNSW-NB15 data sets to evaluate the performance of EvolCostDeep and DeepIDSFog. The results show that our frameworks can effectively handle both class imbalance problem and scalability of big HoT traffic data compared with the other models. The averaged values of the EvolCostDeep for recall, precision, and Fl-score on the data sets are of 93.3%, 97.6%, and 95.2%, respectively, which are higher than the compared methods. Also, the DeepIDSFog provides an average speedup of 38.7x over other comparing models.

关键词： Class imbalance cost-sensitive learning deep learning (DL) evolutionary algorithms fog computing Industrial Internet of Things (IIoT) intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Multi-UAVs delivery task decision based on Quint-Domain Interactive Multi-Objective evolutionary Algorithm 7

Multi-UAVs delivery task decision based on Quint-Domain Inte...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Jinglin He, Chang Ouyang, Haibin Guangzhou University School of Mechanical and Electric Engineering Guangzhou510006 China

ISBN: (纸本)9798350363173

This paper proposes a delivery task allocation model based on m-UAVs, aimed at maximizing the number of delivery tasks and minimizing the average and longest delivery times underling a fixed number of UAVs. A new discrete non- dominated sorting algorithm - the Quint-Domain Interactive Multi-Objective evolutionary Algorithm (QDI-NSGA-II) is introduced to address the delivery task allocation problem. This algorithm is designed with a unique interactive mechanism of multi-population knowledge sharing based on the characteristics of the delivery task allocation model and improves upon the original mutation operations of GA-MTSP. Through comparison with NSGA-II and MOEA/D algorithms under different delivery task settings, the results show that QDI-NSGA-II offers a superior Pareto solution set for solving this problem. © 2024 IEEE.

关键词： evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Two new single/multi-objective multi-strategy algorithms for the parametric estimation of dual band-notched ultra wideband antennas

引用

KNOWLEDGE-BASED SYSTEMS 2024年 286卷

作者： Salgotra, Rohit Singh, Gurdeep Kaur, Sandeep Singh, Urvinder AGH Univ Sci & Technol Fac Phys & Appl Comp Sci Krakow Poland Middle East Univ MEU Res Unit Amman 11813 Jordan Thapar Inst Engn & Technol Dept ECE Patiala India Guru Nanak Dev Univ Dept CET Amritsar India

This article introduces a novel single objective and a multi-objective multi-hybrid naked mole-rat (moIGDN) algorithm optimization techniques for solving numerical benchmarks and electromagnetic engineering problems. The hybridization was introduced to overcome the basic naked mole-rat algorithm's (NMRA's) local optima stagnation and poor exploration problems. The global exploration search equations of INFO, gazelle optimization algorithm (GOA), and dwarf mongoose optimization algorithm (DMO) have been added into the NMRA's worker phase. Additionally, five mutation operators have been introduced for parametric enhancements and adaptations. For single-objective performance evaluation, three benchmark datasets namely classical benchmark, CEC 2014, CEC 2017, and CEC 2022 have been analysed. A comparison with JADE, SaDE, CMA-ES, success history based DE (SHADE), fractional-order calculus-based FPA (FA-FPO), LSHADE-SPACMA, NL-SHADE-LBC, evolutionary algorithms with eigen crossover (EA4eig), S-LSHADE-DP, L-SHADE-RSP-MID, EBOwithCMAR, LSHADE-EpSin among others. Apart from that, the proposed moIGDN algorithm was utilized to optimize the design of two electromagnetic multi-objective printed monopole antennas categorized as basic ultra-wideband (B-UWB) and dual band-notched ultra-wideband (DBN-UWB) antennas. Simulations have been performed by using the EM-MATLAB optimization interface with two objective functions: trying to minimize pass-band signal reflection and maximizing antenna gain, by mapping solutions to the Pareto-front boundary in the objective space. The best obtained antenna structure had an impedance bandwidth of 2.92-11.96 GHz (fractional bandwidth of 122%), efficient band-rejection characteristics for the WI-MAX (3.3 GHz-3.7 GHz) and WLAN (5.15 GHz-5.85 GHz) bands, and a compact geometry. Based on simulation results, moIGDN is found to be effective and can be utilized to solve complex wireless communication and advanced engineering optimization problems.

关键词： Multi-objective optimization Hybridization evolutionary algorithms Dual band-notch Ultra wideband (UWB) Real-world antenna application

来源：评论

学校读者我要写书评

暂无评论

Lotus effect optimization algorithm (LEA): a lotus nature-inspired algorithm for engineering design optimization

引用

JOURNAL OF SUPERCOMPUTING 2024年第1期80卷 761-799页

作者： Dalirinia, Elham Jalali, Mehrdad Yaghoobi, Mahdi Tabatabaee, Hamid Islamic Azad Univ Dept Comp Engn Mashhad Branch Mashhad Iran Karlsruhe Inst Technol KIT Inst Funct Interfaces Eggenstein Leopoldshafen Germany Islamic Azad Univ Dept Elect Engn Mashhad Branch Mashhad Iran

Here we introduce a new evolutionary algorithm called the Lotus Effect Algorithm, which combines efficient operators from the dragonfly algorithm, such as the movement of dragonflies in flower pollination for exploration, with the self-cleaning feature of water on flower leaves known as the lotus effect, for extraction and local search operations. The authors compared this method to other improved versions of the dragonfly algorithm using standard benchmark functions, and it outperformed all other methods according to Fredman's test on 29 benchmark functions. The article also highlights the practical application of LEA in reducing energy consumption in IoT nodes through clustering, resulting in increased packet delivery ratio and network lifetime. Additionally, the performance of the proposed method was tested on real-world problems with multiple constraints, such as the welded beam design optimization problem and the speed-reducer problem applied in a gearbox, and the results showed that LEA performs better than other methods in terms of accuracy.

关键词： Optimization evolutionary algorithms Lotus effect Dragonfly algorithm Network clustering Internet of Things (IoT)

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：