检索结果-内蒙古大学图书馆

IEEE-Industry-Applications-Society Annual Meeting

作者： Zhang, Dong Zhou, Lijun Huang, Lin Wu, Tongshuai Hu, Chen Liu, Xintong Chen, Sixiang Southwest Jiaotong Univ Coll Elect Engn Chengdu Peoples R China Guangdong Power Grid Co Ltd Foshan Power Supply Bur Foshan Peoples R China

ISBN: (纸本)9781728171920

In transmission lines tower earthing device assessment and reconstruction, the existing tower earthing device will lead to inversion error of soil electric parameters. As a result, the inversion data can't represent the real electric parameters of soil. In order to obtain the accurate soil structure around the tower earthing device, this paper proposes an inversion strategy combining finite element method (FEM) with differential evolution (DE) algorithm. Firstly, FEM is used to calculate the theoretical value of soil apparent resistivity without earthing device, and the effectiveness of FEM is verified by complex image method (CIM). Then, DE algorithm is used to optimize the parameters of soil with earthing device and the optimal values of soil parameters are obtained, the validity of the inversion method is verified by comparing it with the set model. The method has been applied to the reconstruction of earthing device of tower in Foshan city, Guangdong province. The test results show that the reconstruction plan guided by the soil structure obtained by the inversion method can effectively reduce the impulse grounding resistance of the tower in power transmission networks.

关键词： Multi-layer soil parameters inversion earthing device reconstruction finite element method differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Objective Resource Beamforming in Broadband SWIPT System by evolution algorithms 2

Objective Resource Beamforming in Broadband SWIPT System by ...

引用

2nd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (IEEE ECBIOS) - Biomedical Engineering, Healthcare and Sustainability

作者： Chien, Wei Hsieh, Tzong-Tyng Chiu, Chien-Ching Cheng, Yu-Ting Huang, Chun-Lian Beibu Gulf Univ Dept Sch Elect & Informat Engn Qinzhou Guangxi Peoples R China Ningde Qianwei Ind Technol Co Ltd Ningde Fujian Peoples R China Tamkang Univ Dept Elect & Comp & Engn Dept New Taipei Taiwan

ISBN: (纸本)9781728187129

The evolutionary algorithm beamforming technology of multi-user resource allocation in wireless information and power transmission (SWIPT) system is studied. In large-capacity broadband communication systems, there are many users with wearable devices. The transmitter provides wireless information and power to a specific receiver at the same time, while other receivers can obtain energy from the radio frequency when idle. Under the constraint of bit error rate (BER), by adjusting the length of the feed line of the transmitting antenna and the excitation current, the energy capture efficiency is maximized. Asynchronous particle swarm optimization (APSO) and adaptive dynamic differential evolution algorithm (SADDE) are used to synthesize the optimal radiation pattern. Both APSO and SADDE can form a good pattern to receive energy. However, APSO has a faster convergence rate than SADDE.

关键词： beamforming wireless information and power transfer broadband asynchronous particle swarm optimization differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Handwritten Recognition Based on Extreme Learning Machine Optimized by Difference evolutionary algorithm

World Scientific Research Journal

引用

World Scientific Research Journal 2021年第1期7卷 302-312页

作者： Yuhang Zhang Yuan Chang Chenwen Dong Zai Cai

With the development of science and technology, the phenomenon of paperless has gradually become common in daily life, and people's requirements for the accuracy of handwritten font recognition have gradually increased. MNIST is the most basic and important data set for studying handwritten font recognition. In this paper, a finite difference evolutionary algorithm is proposed to optimize the extreme learning machine (ELM) model, which referred as DE-ELM hereafter. The DE-ELM model is applied to handwritten numeral recognition. Extreme learning machine is one of the single hidden layer feedforward neural (SLFN) network, its superior performance as the neural network and the rise of artificial intelligence, compared with other traditional neural network such as deep learning, extreme learning machine has higher precision and shorter training time. However, since in the extreme learning machine, the number of hidden nodes is allocated a priori, the hidden node parameters are randomly selected in the initial stage of the model and remain unchanged during the training process, so there may be many non-optimal nodes in the model, and the minimization function contributes less. differential evolution algorithm is a simple but powerful group-based random direct search technology. This article uses differential evolution algorithm to select the hidden node parameters in the extreme learning machine model to make the extreme learning machine achieve better results. The optimized model is classified on the handwritten data set MNIST, and compared with other neural network classification effects, the accuracy of DE-ELM model classification has been improved.

关键词： differential evolution algorithm Estimate learning machine Handwritten recognition

来源：评论

学校读者我要写书评

暂无评论

Study and Simulation of Combined Cooling Heating and Power System in an Industrial Park

Study and Simulation of Combined Cooling Heating and Power S...

引用

3rd IEEE Student Conference on Electrical Machines and Systems (SCEMS)

作者： Xu, Peng Bu, Qiangsheng Li, Yuezhu Geng, Jian Zhang, Junfang Ying, Qin China Elect Power Res Inst Co Ltd Nanjing Peoples R China State Grid Jiangsu Elect Power Co Ltd Res Inst Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Automat Nanjing Peoples R China

ISBN: (纸本)9781728156224

In view of the large demand of energy in the industrial park and the collection of multiple loads such as cooling, heating and power, although the energy supply method of traditional industrial parks can ensure the stability of the park's energy supply, it cannot achieve more reasonable and effective use of energy. This paper applied the risk-return model in the condition value at risk to the power purchase and sale decision of industrial parks, and obtained the comprehensive electricity price for the electricity market. According to the industrial park's load curve, a mathematical model of the Combined Cooling, Heating and Power system was established. The improved particle swarm algorithm was adopted to solve the comprehensive electricity price fluctuations and energy price uncertainty. Through the simulation and analysis, the park equipment capacity configuration was optimized, the simulation accuracy was improved, and the environmental protection, economy and efficiency of the cooling, heating and power cogeneration system was verified. The simulation of energy utilization efficiency with or without energy storage devices showed that the configuration of energy storage in industrial parks can effectively reduce energy waste and improve the stable operation of industrial parks.

关键词： combined cooling heating and power industrial park comprehensive electricity price capacity configuration particle swarm optimization differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

A general control strategy of planar multi-link underactuated manipulator with passive last joint based on nilpotent approximation and intelligent optimization

A general control strategy of planar multi-link underactuate...

引用

Chinese Automation Congress (CAC)

作者： Huang, Zixin Qin, Xiangyu Wang, Lejun Zhang, Pan Wuhan Text Univ Sch Elect & Informat Engn Wuhan Inst Technol Hubei K Lab DigitalText Equipment Wuhan Peoples R China Wuhan Inst Technol Sch Elect & Informat Engn Wuhan Peoples R China China Univ Geosci Sch Automat Wuhan Peoples R China

ISBN: (纸本)9781728176871

We design a control strategy via the differential evolution algorithm (DEA) to solve the position control problem of a planar multi-link underactuated manipulator (PMLUM) with a passive last joint. According to the structure of the PMLUM, which can be regarded as a planar virtual Pendubot by the model reduction method. Considering the existence of the nilpotent approximation (NA) characteristic in the planar virtual Pendubot (PVP), the iterative steering method (ISM) is employed to make the PVP to its target angle. Simulation results show the effectiveness of the proposed strategy.

关键词： Planar multi-link underactuated manipulator position control model reduction nilpotent approximation iterative steering differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of DE-GWO-SVM algorithm in Business Order Prediction Model 11

Application of DE-GWO-SVM Algorithm in Business Order Predic...

引用

11th IEEE International Conference on Software Engineering and Service Science (IEEE ICSESS)

作者： Liu, Jing Zhu, Xiaojun Zhang, Yanfeng Minist Publ Secur Res Inst 3 Dept Cyber Secur Beijing Peoples R China Govt Affairs Serv Adm Xicheng Beijing Peoples R China Lanzhou Univ Sch Informat Sci & Engn Lanzhou Peoples R China

ISBN: (数字)9781728165790

ISBN: (纸本)9781728165790

To judge whether customers will choose the time deposit business launched by the bank is a problem of prediction classification, and it is also a problem that bankers want to know and urgently need to solve. This paper constructs a prediction model of banking business order based on DE-GWO-SVM *** model uses differential evolution algorithm and Grey Wolf algorithm to optimize the Support Vector Machine, and then applies the model to the prediction of bank marketing business order, which can effectively classify and identify whether bank customers will buy the time deposit business. Finally through the model experiment and comparing the Grey Wolf algorithm for without optimization, it is concluded that the model of banking business order based on DE-GWO-SVM algorithm, at an effective prediction accuracy of 96.8%, will help Banks identify the target customer groups, carry on the accurate marketing, improve the success rate of business marketing.

关键词： component differential evolution algorithm Grey Wolf algorithm Support Vector Machine business order prediction classification

来源：评论

学校读者我要写书评

暂无评论

Aiming at QoS: A Modified DE algorithm for Task Allocation in Cloud Computing

Aiming at QoS: A Modified DE Algorithm for Task Allocation i...

引用

IEEE International Conference on Communications (IEEE ICC) / Workshop on NOMA for 5G and Beyond

作者： Ma, Kun Bagula, Antoine Ajayi, Olasupo Nyirenda, Clement Univ Western Cape Dept Comp Sci Bellville South Africa

ISBN: (纸本)9781728150895

The Cloud computing system is characterized by large scale servers being utilized by an even larger number of users. It is a system where there is the need to frequently and efficiently schedule and manage different application tasks, with varied service requirements. One of the challenges of Cloud computing is managing the quality of service (QoS) rendered to users, specifically scheduling tasks between users and Cloud resources in a timely manner. Cloud users usually have widely diverse QoS requirements and meeting these simultaneously is also a challenge. In this paper, in order to improve on Cloud resource allocation and specifically to tailor it towards meeting varied QoS requirements of users, we proposed a new algorithm which combines differential evolution with the Shapley Value economic mode. This combination allows us measure the contribution of each virtual machine (VM), so as to improve the probability of obtaining a better tasks-to-resource allocation thereby improving user satisfaction. From results of conducted experiments, when compared with the traditional DE (differential evolution) algorithm and the conventional task-VM binding policy in CloudSim, both for allocations where special QoS requirements are required and in instances of multiple QoS requirements;the modified Shapley value based DE algorithm (SVBDA) shows significant improvement.

关键词： Cloud computing differential evolution algorithm Execution time/cost minimizing NP hard problem Quality of service (QoS) Shapley value Tasks scheduling Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Optimal Planning of Distributed Generation in Distribution Networks using the differential evolutionary algorithm

Optimal Planning of Distributed Generation in Distribution N...

引用

IEEE-Industry-Applications-Society Annual Meeting

作者： Norouzizad, Ali Bahramara, Salah Divian, Abbas Osorio, Gerardo J. Shafie-khah, Miadreza Wang, Fei Catalao, Joao P. S. Islamic Azad Univ Sanandaj Branch Dept Elect Engn Sanandaj Iran Iran Univ Sci & Technol Dept Elect Engn Tehran Iran Univ Beira Interior C MAST Covilha Portugal Univ Vaasa Sch Technol & Innovat Vaasa 65200 Finland North China Elect Power Univ Dept Elect Engn Baoding 071003 Peoples R China Univ Porto Fac Engn Porto Portugal INESC TEC Porto Portugal

ISBN: (纸本)9781728171920

The use of distributed generators (DGs) in the distribution networks has many economic and technical advantages. In order to achieve these advantages, DGs should have the proper size and be installed in suitable locations. In this work, a differential evolution algorithm is proposed to find the best location and capacity of DGs in the distribution network with the aim of getting to the minimum losses and optimal voltage profile. The important loads need continuity of power supply when the network is in islanding mode due to various events such as short circuit faults. The existence of at least one DG in these networks is necessary. In this paper, the proposed method is applied to the IEEE 33-bus distribution network in two connection modes. First, it is connected with the power grid and then it works in the islanding operation mode. The results show the effectiveness of the proposed algorithm.

关键词： differential evolution algorithm Distributed generation Islanding Power loss Voltage profile

来源：评论

学校读者我要写书评

暂无评论

An evolutionary algorithm-Based Damage Detection in Structural Elements 1st

An Evolutionary Algorithm-Based Damage Detection in Structur...

引用

1st International Conference on Innovative Product Design and Intelligent Manufacturing System, ICIPDIMS 2019

作者： Sahu, Sasmita Parhi, D.R. Nayak, B.B. KIIT University Bhubaneswar India NIT Rourkela Rourkela India

ISBN: (纸本)9789811526954

Damage in structural and rotating machine elements causes the local changes in the dynamical parameters of the system. To find the damage present in a system is becoming one of the important research topics in today’s civil and mechanical engineering field. This topic of research can mainly be used in bridges, offshore platforms, plates, shells, beams, aerospace and composite structures and other large civil structures to detect structural damages by analyzing the dynamic features of the system. It has been observed due to any slight physical change, the stiffness of the system changes which changes the modal responses of the system. The aim of this research work is to derive a simple method for estimating the failure parameters (crack depth and crack location) in structures based on a data-driven subspace identification technique. These changes in the modal parameters can be used as the input variables to find out the damage severity. The responses (natural frequencies) were obtained using finite element analysis, and then, the differential evolution algorithm (a type of evolutionary algorithm) is used to detect and characterize these defects. This work proposes a robust computational application of the differential evolution algorithm that more accurately takes into account the natural evolution with initial point and produces a good converging result. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Damage differential evolution algorithm Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Sidelobe minimization in Orthogonal Frequency Division Multiplexing Using efficient Generalize Sidelobe Canceler 17

Sidelobe minimization in Orthogonal Frequency Division Multi...

引用

17th International Bhurban Conference on Applied Sciences and Technology (IBCAST)

作者： Ahmed, R. Elahi, A. Ahmad, G. Ahmed, A. Gull, N. Univ Peshawar Dept Elect Peshawar Pakistan Int Islamic Univ Islamabad Dept Elect Engn Islamabad Pakistan

ISBN: (纸本)9781728146768

The optimal choice for the organized utilization of the radio spectrum is Cognitive Radio Network (CRN). To permit data of Secondary Users (SUs) opportunistically, in the absence of Primary Users (PUs) is the main objective of CRN. Due to its efficiency and easy implementation Orthogonal Frequency Division Multiplexing (OFDM) is employed in CRN for signaling. The drawback in using OFDM is its sidelobes that causes Out of Band (OOB) radiations, which results interference to the PU's. In order to reduce OOB radiations the signal pass through Modified Generalize Sidelobe Canceller (MGSC) in which optimization part of the adaptive weight vector of conventional Generalize Sidelobe Canceller (GSC) is done using differential evolution (DE). Furthermore, proposed work reduces time wastage and memory by calculating the weight of one sample point from left and right side of OFDM symbol using DE while applying the formula of sidelobe decay to calculate remaining weights of sidelobe. The effectiveness and consistency of our proposed technique can be seen in simulation. Better results has been achieved in comparison to the existing techniques by our proposed technique.

关键词： Cognitive Radio Orthogonal Frequency Division Multiplexing Generalize Sidelobe Canceller differential evolution 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：