检索结果-内蒙古大学图书馆

Comparative Study of Constrained Handling Techniques of Constrained Differential Evolution algorithms Applied to Constrained optimization Problems in Mechanical Engineering 3

Comparative Study of Constrained Handling Techniques of Cons...

引用

3rd Technology Innovation Management and Engineering Science International Conference (TIMES-iCON)

作者： Muangkote, Nipotepat Photong, Lersak Sukprasert, Anupong Mahasarakham Univ Mahasarakham Business Sch Dept Business Comp Maha Sarakham 44150 Thailand

ISBN: (纸本)9781538675731

Constrained optimization problems in mechanical engineering are very difficult for the optimization algorithm. In 2013, an improved version of constrained differential evolution, named ArATM-ICDE was proposed to optimize the constrained optimization problem. An archiving-based adaptive trade-off model (ArATM) was constructed to handle the constraints;resulting in an algorithm referred to as ArATM-ICDE. This paper applies ArATM-ICDE to solve constraint optimization problems in mechanical engineering. We also combine the penalty technique for constraint handling into the ICDE, named Penalty-ICDE;which compares the abilities of the constraint handling techniques. Our experiments were conducted on ten widely used constraint engineering optimization problems. The experiment results proved the ArATM-ICDE to be more reliable than the Penalty-ICDE. Additionally, ArATM-ICDE consumed a lesser number of function calls than Penalty-ICDE. This paper further compared the effectiveness of ArATM-ICDE and Penalty-ICDE with eight state-of-the-art algorithms, which revealed that ArATM-ICDE and Penalty-ICDE produced solutions of higher quality than those produced by the comparative algorithms. The ArATM-ICDE also consumed less effort in its process.

关键词： global optimization algorithm differential evolution algorithm mechanical engineering problem constrained handling techniques

来源：评论

学校读者我要写书评

暂无评论

ANN Characterization of Printed Reflectarray Elements

ANN Characterization of Printed Reflectarray Elements

引用

2010 IEEE International Symposium Antennas and Propagation/CNC-USNC/URSI Radio Science Meeting

作者： Mussetta, M. Pirinoli, P. Zich, R. E. Orefice, M. Politecn Torino Dip Elettron LACE I-10129 Turin Italy Politecn Milan Dept Engn I-20156 Milan Italy

ISBN: (纸本)9781424449682

The design of printed reflectarray antennas (RAs) could be quite complex and computationally expensive, since the need of providing high performances and satisfying requirements that could be also in contrast each other could require the use of a large number of re-radiating advanced element configurations. A possible strategy for the RA design could be therefore of carrying it out adopting an evolutionary optimization tool. In this work, an artificial neural network (ANN) model of the RA single element is presented as convenient interface between antenna design and global optimization algorithms. In order to prove the effectiveness of the model, it will be used in the design of a dual-band dual-layer reflectarray.

关键词： ANN characterization artificial neural network dual-band dual-layer reflectarray evolutionary computation evolutionary optimization tool global optimization algorithm microstrip antenna arrays neural nets printed reflectarray element reflector antennas

来源：评论

学校读者我要写书评

暂无评论

Two-layered High Gain and Wide Bandwidth Metamaterial Antenna for 5G mm-Wave Applications Using Multi-Trial Vector-Based Differential Evolution

Two-layered High Gain and Wide Bandwidth Metamaterial Antenn...

引用

International Workshop on Antenna Technology (iWAT)

作者： Hlias, Tzouras Griva, Aikaterini I. Korompilis, Georgios Boursianis, Achilles D. Goudos, Sotirios K. Stavros, Koulouridis Univ Patras Dept Elect & Comp Patras Greece Aristotle Univ Thessaloniki ELEDIA AUTH Sch Phys Thessaloniki Greece

ISBN: (纸本)9798350314762;9798350314755

A two-layered high gain and wide bandwidth metamaterial antenna working at 24 GHz - 30.5 GHz for mm-Wave applications is presented in this paper. To design the antenna we apply a novel evolutionary algorithm, namely the multi-trial vector-based differential evolution (MTDE). The metamaterial antenna has an overall compact size of 12.4 x 12.4 x 8.38 mm(3) including two substrates and the air gap. It is realized with a Rogers Duroid 5880 substrate 0.78 mm thick and a Rogers RO3010 as a superstrate 1.6 mm thick at an optimized distance above the radiation element. The radiation element is composed of a square-cut-at-the-four corners patch antenna. In addition, to enhance the antenna performance, both gain and bandwidth, a metasurface based on periodic metallic mushrooms which surround the radiation element is employed. Interelement distance between the metallic structures, their size and the distance between the two substrates are optimized. Simulated results show a significantly wide bandwidth ranging 24 GHz to 30.5 GHz and a high peak realized gain of 11.76 dB when the MTDE optimizer is applied. These features make the antenna a good candidate for 5G mm-Wave applications.

关键词： 5G Antennas Metasurfaces mm-Waves EBG Mushrooms global optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Water Quantity Prediction Based on Particle Swarm optimization and Evolutionary algorithm Using Recurrent Neural Networks

Water Quantity Prediction Based on Particle Swarm Optimizati...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhang, Nian Lai, Shuhua Univ Dist Columbia Dept Elect & Comp Engn Washington DC 20008 USA

ISBN: (纸本)9781424496365

Stormwater pollution is one of most important issues that the District of Columbia faces. Urban stormwater pollution can be a large contributor to the water quality problems of many receiving waters, as runoff transports a wide spectrum of pollutants to local receiving waters and their cumulative magnitude is large. Therefore, evaluations of stormwater runoff quantity are necessary to enhance the performance of an assessment operation and develop better water resources management and plan. However, some computational intelligence methods that have most successful applications on time series prediction have not yet been investigated on water quantity prediction. Only a limited number of neural networks models were applied to the water quantity monitoring. Therefore, we proposed an Elman style based recurrent neural network on the water quantity prediction. A hybrid learning algorithm incorporating particle swarm optimization and evolutional algorithm was presented, which takes the complementary advantages of the two global optimization algorithms. The neural networks model was trained by particle swarm optimization and evolutional algorithm to forecast the stormwater runoff discharge. The USGS real-time water data at Four Mile Run station at Alexandria, VA were used as time series input. The excellent experimental results demonstrated that the proposed method provides a suitable prediction tool for the stormwater runoff monitoring.

关键词： Elman style based recurrent neural network Neural networks Particle swarm optimization Prediction algorithms Rivers Time series analysis Water pollution Water resources computational intelligence method cumulative magnitude environmental science computing evolutionary algorithm evolutionary computation global optimization algorithm hybrid learning algorithm hydrology learning (artificial intelligence) particle swarm optimisation particle swarm optimization recurrent neural nets stormwater pollution stormwater runoff monitoring stormwater runoff quantity time series time series prediction water pollution water quality water quality water quantity monitoring water quantity prediction water resources water resources management

来源：评论

学校读者我要写书评

暂无评论

A Highly Parallel Approach for Solving Computationally Expensive Multicriteria optimization Problems 5th

A Highly Parallel Approach for Solving Computationally Expen...

引用

5th Russian Supercomputing Days Conference (RuSCDays)

作者： Gergel, Victor Kozinov, Evgeny Lobachevsky State Univ Nizhni Novgorod Nizhnii Novgorod Russia

ISBN: (纸本)9783030365929;9783030365912

In this paper, a highly parallel approach for solving multicriteria optimization problems is proposed. The considered approach is based on the reduction of the multicriterial problems to the global optimization ones using the minimax convolution of the partial criteria, the dimensionality reduction with the use of the Peano space-filling curves, and the application of the efficient parallel information-statistical global optimization methods. The required computations can be time-consuming since functions representing individual criteria can be multi-extremal and computationally expensive. The proposed approach comprises two different schemes for efficient parallel computations on high performance systems with shared and distributed memory and with a large number of computational units. The computational efficiency is achieved by storing all the computed criteria values and their intensive reuse for finding new solutions. The results of numerical experiments have demonstrated that this approach allows to reduce the computational costs of solving multicriteria optimization problems by a factor between 10 and 100.

关键词： Multicriteria optimization Parallel computing Dimensionality reduction Criteria convolution global optimization algorithm Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Parameter Search Method For Optimal Efficiency Design Of High Power Millimeter Wave Gyrotron TWT 22

A Parameter Search Method For Optimal Efficiency Design Of H...

引用

22nd International Vacuum Electronics Conference (IVEC)

作者： Zou, Fucheng Yan, Ran Luo, Yong Univ Elect Sci & Technol China Sch Elect Sci & Engn Chengdu 610054 Sichuan Peoples R China

ISBN: (纸本)9781665441056

This paper introduces a method for searching the optimal efficiency parameters of high-power millimeter wave gyrotron based on BP neural network prediction. This method can establish the prediction model through the actual design gyrotron test data, and optimize the prediction model through the global optimization algorithm to obtain the optimal efficiency design parameters. This method can effectively extract accurate and effective information from the test data and feed back to the designers.

关键词： Gyrotron BP neural network global optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

optimization for Hazardous Materials Road Transportation based on Multi-objective Method

Optimization for Hazardous Materials Road Transportation bas...

引用

3rd International Conference on Intelligent System Design and Engineering Applications (ISDEA)

作者： Li, Xiang Jiang, Huiyuan Wuhan Univ Technol Sch Transportat Wuhan 430063 Hubei Peoples R China

ISBN: (纸本)9780769549231

On the basis of the previous related work of hazardous materials road transportation and considered the real problem of hazardous materials management, this paper propose a model based on multi-objective optimization. Transportation risk, route and freight are weighted to get a similar generalized cost expression which makes the function of influencing factors more flexibility and applicability. global optimization algorithm is simple and easy to be calculated which will provide a more operable model for the optimization problem of hazardous material road transportation. Finally, the feasibility of the method is proved by the given example.

关键词： Hazardous Materials Route optimization Multi-objective global optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Fast On-line Calibration algorithm for a Two-Stroke Kerosene Engine 7

Research on Fast On-line Calibration Algorithm for a Two-Str...

引用

7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023

作者： Liang, Siqiang Wang, Jian Wang, Xu Huang, Ying School of Mechanical Engineering Beijing Institute of Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (纸本)9798350340488

Engine calibration poses a challenging multi-objective non-convex optimization problem due to its inherent complexity. In this study, we present a novel on-line engine calibration algorithm named Search Space Division-Momentum Gradient Descent (SSD-MGD), aimed at tackling this issue and reducing the calibration time. To commence, our investigation centers on a two-stroke kerosene engine, focusing on the calibration of spark timing and air-fuel ratio. We leverage experimental data to construct an engine response model utilizing support vector machines. This model serves as a virtual calibration test bench. The SSD-MGD methodology is then elaborated upon. It combines two key components: search space partitioning, which quickly identifies suitable initial points, and a momentum gradient descent algorithm, which solves for local optimal solutions from selected initial points. The two complement each other and we achieve a globally optimal solution. To evaluate the effectiveness of SSD-MGD, we performed a comparative analysis with traditional methods such as genetic algorithms in the context of virtual calibration tests. Our research results consistently show that SSD-MGD not only achieves the global optimal solution but also has significant efficiency. © 2023 IEEE.

关键词： global optimization algorithm non-convex optimization On-line model-free engine calibration

来源：评论

学校读者我要写书评

暂无评论

Simulation Exploration on Artificial Intelligence and Visual Communication Design in the Intelligent Era

Simulation Exploration on Artificial Intelligence and Visual...

引用

2023 International Conference on Evolutionary algorithms and Soft Computing Techniques, EASCT 2023

作者： Sun, Hongbo Zhang, Yingyu Changchun Humanities College Visual Communication Design Changchun China

ISBN: (纸本)9798350313413

With the continuous progress of society, the era of intelligence has arrived. Therefore, simulation of artificial intelligence (AI) and VCD is a hot topic of current research. Through research on intelligent algorithms, simulation of VCD can be achieved, which can better meet the growing needs of people. Currently, a large amount of research has been conducted on AI and VCD worldwide, and certain achievements have been achieved. Therefore, this paper proposed a VCD simulation method based on knowledge atlas through the analysis and processing of intelligent algorithms. The results showed that the proportion of experts and researchers who believed that the VCD effect of Group X system was above 80 points was 80% and 71.4%, while the proportion of people who believed that the VCD effect of Group Y system was above 80 points was 0% and 14.3%. The performance of Group X was far better than that of Group Y, indicating the positive relationship between AI and VCD in the intelligent era. © 2023 IEEE.

关键词： artificial intelligence global optimization algorithm satisfaction evaluation visual communication design

来源：评论

学校读者我要写书评

暂无评论

Direct generation of arbitrary complex fields from a ring laser resonator

引用

Chinese Optics Letters 2024年第11期22卷 93-97页

作者： Cong Hu Yu Xiao Hao Peng Xiahui Tang School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Research Institute of Huazhong University of Science and Technology in Shenzhen Shenzhen 518052China

On-demand and real-time generation of arbitrary complex fields directly from the laser source holds significant appeal for myriad applications. In this Letter, we demonstrate a ring laser configuration capable of dynamically generating arbitrary transverse fields. In a ring laser resonator, two cascaded phase modulations are utilized, which permits the control of two beams with high efficiency and high fidelity. The zeroth-order beam is a fundamental Gaussian field that self-reproduces itself in the resonator. The first-order beam serves as the desired output field, which is separated from the selfreproduction mode to facilitate the on-demand manipulation of amplitude and phase. In the verification experiments,a series of typical Hermite–Gaussian(HG) modes, Laguerre–Gaussian(LG) modes, flat-top mode, and amplitude-only pattern“A” are generated from the ring laser configuration. This innovative ring laser resonator may open up new perspectives for the design of structured-light lasers, with potential impacts in applications such as particle manipulation, advanced microscopy, and next-generation optical communication.

关键词： structured-light laser phase modulation intracavity light-field manipulation global optimization algorithm

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：