检索结果-内蒙古大学图书馆

Switching-type PD-PI controller design by HEA for AVR system

JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS 2014年第5期37卷 687-697页

作者： Wong, Ching-Chang Li, Shih-An Tamkang Univ Dept Elect Engn 151 Yingzhuan Rd New Taipei City 25137 Taiwan

In this paper, a switching-type PD-PI controller is proposed and a parameter selection method based on a hybrid evolution algorithm (HEA) is used to select the control parameters effectively for an automatic voltage regulator (AVR) system. The proposed switching-type PD-PI control structure combines improved transient response and reduction of steady state error to produce good global response. In the selections of parameters, HEA is applied to select an appropriate switching value and the control parameters in PD and PI controllers so that the controlled system may have good performance. In the selection of the fitness function, a new evaluation method for system performance is applied so that evolution algorithms can effectively find an appropriate parameter set. Finally, the proposed method is applied in the AVR system. From some simulation and comparison results, we can see that the proposed parameter selection method can effectively find a parameter set for the proposed switching-type PD-PI controller to yield better control performance.

关键词： PID PSO automatic voltage regulator (AVR) evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

A simulation optimization method for vehicles dispatching among multiple container terminals

引用

EXPERT SYSTEMS WITH APPLICATIONS 2015年第7期42卷 3742-3750页

作者： Tao, Jinghui Qiu, Yuzhuo Nanjing Univ Finance & Econ Sch Mkt & Logist Management Nanjing 210046 Jiangsu Peoples R China Nanjing Univ Finance & Econ Jiangsu Key Lab Modern Logist Nanjing 210046 Jiangsu Peoples R China

Container terminals, serving as the hubs between container ships and other transportations nodes, are of extreme importance in streamlining the ever increasing global trade. Many different factors affect the service efficiency in container terminals, which inspire great interest in both industrial and academic researches. This work focuses on vehicle dispatching problem which decides, for each internal vehicle in the port, where to go to find a new loading or unloading task in container terminals after finishing the previous one. A multi-factor online dispatching method, which takes both empty traveling and location balance into consideration, is proposed to fit the current condition of the physical and information infrastructure in most of the ports in mainland China. Such a method is established by using combined evolution searching function and discrete event simulation. Through comparing our dispatching method with the traditional dedicated vehicle dispatching methods in various simulation cases, together with theoretical analysis, we prove that our method delivers substantial efficiency improvement in terms of reducing ship serving time and vehicle empty traveling, regardless of changing environment we have examined in the study. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Container terminal Online dispatching Event-driven simulation evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

An immune chaotic adaptive evolutionary algorithm for energy-efficient clustering management in LPWSN

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第10期34卷 8297-8306页

作者： Zhang, Yao Xie, Jianpeng Liu, Yang Li, Chaoqun Xiao, Jing Ma, Hongliang Zhou, Jie Univ Cordilleras Baguio 2600 Philippines Shihezi Univ Coll informat Sci & Technol Shihezi Peoples R China

Recently, low power wireless sensor networks (LPWSNs) have been widely used in the military and edu-cation. However, the lifetime of LPWSN is affected by the energy of the sensor, so the clustering design has received a lot of attention. In this study, the problem of designing optimal clustering for LPWSN is formulated as a cluster head selection problem, considering energy, which is an NP-hard problem. Therefore, a new structural model of the clustering design problem is constructed. This model can repre-sent the process of sensor node clustering and information transfer. In this paper, a new immune chaotic adaptive evolutionary algorithm (ICAEA) is proposed and used in the clustering design of LPWSNs to obtain a better cluster head selection scheme. Then we design new advanced operators, such as immune operator and chaotic operator, which improve the convergence speed of the algorithm on the basis of evolutionary algorithm (EA). Moreover, ICAEA avoids local optima by introducing an adaptive operator, improves the convergence accuracy of the algorithm, and improves the performance of the optimization. Simulations are conducted to determine the performance improvements of ICAEA in terms of network lifetime and energy consumption compared to the latest clustering methods of R-LEACH, Q-LEACH, and ICCHR. The experimental results show that the proposed ICAEA algorithm outperforms RLEACH, Q -LEACH and ICCHR in terms of network lifetime under multiple identical experimental conditions. Moreover, ICAEA consumes less energy than R-LEACH, Q-LEACH and ICCHR in terms of system energy consumption.(c) 2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Wireless sensor network Clustering LPWSN evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

DNA Epidemic Model Construction and Dynamics Optimization

引用

INTERNATIONAL JOURNAL OF COGNITIVE INFORMATICS AND NATURAL INTELLIGENCE 2020年第3期14卷 97-117页

作者： Zhou, Yinglian Hunan Int Econ Univ Informat Sci & Technol Changsha Peoples R China

In order to solve some complex optimization problems, the SIR-DNA algorithm was constructed based on the DNA-based SIR (susceptible-infectious-recovered) infectious disease model. Since infectious diseases attack a very small part of the individual's genes, the number of variables per treatment is small;thus, the natural dimensionality reduction of the algorithm is achieved. Based on the DNA-SIR infectious disease model, different infections can be distinguished in the pathogenesis of viruses. The mechanisms of disease transmission are described by the SIR model, and these are used to construct operators such as SS, SI, II, IR, RR, and RS, so that individuals can naturally exchange information naturally through disease transmission. The test results show that the algorithm has the characteristics of strong search ability and has a high convergence speed for solving complex optimization problems.

关键词： Bionic Optimization Epidemic Dynamics evolution algorithm Immune Genes Meta-Heuristic Search Population Intelligent Optimization Random Search SIR Epidemic Model

来源：评论

学校读者我要写书评

暂无评论

MEAs-Filter: a novel filter framework utilizing evolutionary algorithms for cardiovascular diseases diagnosis

引用

HEALTH INFORMATION SCIENCE AND SYSTEMS 2024年第1期12卷 8页

作者： Zhu, Fangfang Ding, Ji Li, Xiang Lu, Yuer Liu, Xiao Jiang, Frank Zhao, Qi Su, Honghong Shuai, Jianwei Xiamen Univ Dept Phys Xiamen 361005 Peoples R China Xiamen Univ Fujian Prov Key Lab Soft Funct Mat Res Xiamen 361005 Peoples R China Xiamen Univ Natl Inst Data Sci Hlth & Med Innovat Ctr Cell Signaling Network Xiamen 361005 Peoples R China Xiamen Univ Innovat Ctr Cell Signaling Network State Key Lab Cellular Stress Biol Xiamen 361005 Peoples R China Tsinghua Univ Yangtze Delta Reg Inst Jiaxing 314006 Zhejiang Peoples R China Univ Chinese Acad Sci Wenzhou Inst Wenzhou 325001 Peoples R China Univ Chinese Acad Sci Wenzhou Key Lab Biophys Wenzhou 325001 Peoples R China Deakin Univ Fac Sci Engn & Built Environm Sch Informat Technol Geelong Vic Australia Univ Sci & Technol Liaoning Sch Comp Sci & Software Engn Anshan 114051 Peoples R China

Cardiovascular disease management often involves adjusting medication dosage based on changes in electrocardiogram (ECG) signals' waveform and rhythm. However, the diagnostic utility of ECG signals is often hindered by various types of noise interference. In this work, we propose a novel filter based on a multi-engine evolution framework named MEAs-Filter to address this issue. Our approach eliminates the need for predefined dimensions and allows adaptation to diverse ECG morphologies. By leveraging state-of-the-art optimization algorithms as evolution engine and incorporating prior information inputs from classical filters, MEAs-Filter achieves superior performance while minimizing order. We evaluate the effectiveness of MEAs-Filter on a real ECG database and compare it against commonly used filters such as the Butterworth, Chebyshev filters, and evolution algorithm-based (EA-based) filters. The experimental results indicate that MEAs-Filter outperforms other filters by achieving a reduction of approximately 30% to 60% in terms of the loss function compared to the other algorithms. In denoising experiments conducted on ECG waveforms across various scenarios, MEAs-Filter demonstrates an improvement of approximately 20% in signal-to-noise (SNR) ratio and a 9% improvement in correlation. Moreover, it does not exhibit higher losses of the R-wave compared to other filters. These findings highlight the potential of MEAs-Filter as a valuable tool for high-fidelity extraction of ECG signals, enabling accurate diagnosis in the field of cardiovascular diseases.

关键词： Electrocardiogram evolution algorithm Filter Noise interference Disease diagnosis

来源：评论

学校读者我要写书评

暂无评论

Geometric mean optimizer for achieving efficiency in truss structural design

引用

evolutionARY INTELLIGENCE 2024年第4期17卷 2453-2466页

作者： Pham, Vu Hong Son Dang, Nghiep Trinh Nguyen Nguyen, Van Nam Ho Chi Minh City Univ Technol HCMUT Vietnam Natl Univ VNU HCM Fac Civil Engn Ho Chi Minh City Vietnam

The objective of this study is to utilize the geometric mean optimizer (GMO) for mass optimization of structural trusses. By harnessing the GMO's mutation mechanism rooted in a Gaussian framework, the model effectively addresses the discrete nature of truss structure optimization. Through a comprehensive evaluation involving four distinct problem scenarios including 10, 15, 25, and 52-bar truss structures with both discrete and continuous variables, the effectiveness of the GMO technique is thoroughly demonstrated. The optimization findings underscore that the GMO consistently generates improved designs in comparison to conventional population-based techniques. Furthermore, the GMO model demonstrates remarkable computational efficiency in specific cases. This research emphasizes the potential of the GMO-based approach as a potent tool in the domain of truss structure optimization. It holds the capability to revolutionize the manner in which engineers approach the intricate balance between structural integrity, minimal weight, and cost-effectiveness.

关键词： Structural engineering Discrete optimization Truss design problems evolution algorithm Geometric mean optimizer

来源：评论

学校读者我要写书评

暂无评论

evolutionary Recurrent Neural Architecture Search

引用

IEEE EMBEDDED SYSTEMS LETTERS 2021年第3期13卷 110-113页

作者： Tian, Shuo Hu, Kai Guo, Shasha Li, Shiming Wang, Lei Xu, Weixia Natl Univ Def Technol Coll Comp Sci & Technol Changsha 410000 Peoples R China

Deep learning has promoted remarkable progress in various tasks while the effort devoted to these hand-crafting neural networks has motivated so-called neural architecture search (NAS) to discover them automatically. Recent aging evolution (AE) automatic search algorithm turns to discard the oldest model in population and finds image classifiers beyond manual design. However, it achieves a low speed of convergence. A nonaging evolution (NAE) algorithm tends to neglect the worst architecture in population to accelerate the search process whereas it obtains a lower performance compared with AE. To address this issue, in this letter, we propose to use an optimized evolution algorithm for recurrent NAS (EvoRNAS) by setting a probability epsilon to remove the worst or oldest model in population alternatively, which can balance the performance and time length. Besides, parameter sharing mechanism is introduced in our approach due to the heavy cost of evaluating the candidate models in both AE and NAE. Furthermore, we train the sharing parameters only once instead of many epochs like ENAS, which makes the evaluation of candidate models faster. On Penn Treebank, we first explore different epsilon in EvoRNAS and find the best value suited for the learning task, which is also better than AE and NAE. Second, the optimal cell found by EvoRNAS can achieve state-of-the-art performance within only 0.6 GPU hours, which is 20 x and 40 x faster than ENAS and DARTS. Moreover, the transferability of the learned architecture to WikiText-2 also shows strong performance compared with ENAS or DARTS.

关键词： Computer architecture Sociology Statistics Microprocessors Manuals Training Computational modeling Deep learning evolution algorithm neural architecture search (NAS) parameter sharing

来源：评论

学校读者我要写书评

暂无评论

Cubature Split Covariance Intersection Filter-Based Point Set Registration

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2018年第8期27卷 3942-3953页

作者： Li, Liang Yang, Ming Wang, Chunxiang Wang, Bing Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Minist Educ China Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China

Point set registration is a basic but still an open problem in numerous computer vision tasks. In general, there are more than one type of error sources for registration, for example, noise, outliers, and false initialization, may exist simultaneously. These errors could influence the registration independently and dependently. Previous works usually test performance under one of the two types of errors at one time, or they do not perform well under some extreme situations with both of the error sources. This paper presents a robust point set registration algorithm under a filtering framework, which aims to he robust under various types of errors simultaneously. The point set registration problem can he cast into a non-linear state space model. We use a split covariance intersection filter (SCIF) to capture the correlation between the state transition and the observation (moving point set). The two above-mentioned types of errors can be represented as dependent and independent parts in the SCIF. The covariance of the two types of errors will be updated every iteration. Meanwhile, the non-linearity of the observation model is approximated by a cubature transformation. First, the recursive cubature split covariance intersection filter is derived based on the non-linear state space model. Then, we use this algorithm to solve the point set registration problem. This algorithm can approximate non-linearity by a third-order term and consider correlations between the process model and the observation model. Compared with other filtering-based methods, this algorithm is more robust and precise. Tests on both public data sets and experiments validate the precision and robustness of this algorithm to outliers and noise. Comparison experiments show that this algorithm outperforms the state-of-the-art point set registration algorithms in certain respects.

关键词： Point set registration cubature split covariance intersection filter continuous simulated annealing evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Selection of optimal conditions in the surface grinding process using the quantum based optimisation method

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2019年第3期30卷 1469-1481页

作者： Alajmi, Mahdi S. Alfares, Fawzan S. Alfares, Mohamed S. Publ Author Appl Educ & Training Coll Technol Studies Dept Mfg Engn Technol Adailiyah Kuwait Publ Author Appl Educ & Training Coll Technol Studies Dept Elect Engn Technol Adailiyah Kuwait

A novel optimisation technique based on quantum computing principles, namely the quantum based optimisation method (QBOM), is proposed to solve the surface grinding process problem optimisation. In grinding process there is a trade-off between faster material removal rates, with a reduction in cutting time and its associated cost and shorter tool life or higher tool cost. The objective of the surface grinding optimisation problem is to determine the optimal machining conditions, which will minimize the unit production cost and unit production time with the finest possible surface finish but without violating any imposed constraints. The performance of QBOM is investigated against two test cases, one of a rough grinding process and the other of a finished grinding process and the computational results show that the proposed optimisation technique obtained better results than most of the methods presented in the literatures.

关键词： Optimisation Surface grinding Manufacturing evolution algorithm Quantum based optimisation method

来源：评论

学校读者我要写书评

暂无评论

An improved peak side lobe reduction method for linear array antenna for military applications

引用

International Journal of Intelligent Computing and Cybernetics 2021年第2期14卷 185-197页

作者： Ravi Tej D Sri Kavya Ch K Sarat K.Kotamraju Department of Electronics and Communication Engineering Koneru Lakshmaiah Education FoundationGunturIndia

Purpose-The purpose of this paper is to improve energy efficiency and further reduction of side lobe level the algorithm proposed is firework *** this paper,roused by the eminent swarm conduct of firecrackers,a novel multitude insight calculation called fireworks algorithm(FA)is proposed for work *** FA is introduced and actualized by mimicking the blast procedure of *** the FA,two blast(search)forms are utilized and systems for keeping decent variety of sparkles are likewise all around *** approve the presentation of the proposed FA,correlation tests were led on nine benchmark test capacities among the FA,the standard PSO(SPSO)and the clonal PSO(CPSO).Design/methodology/approach-The antenna arrays are used to improve the capacity and spectral efficiency of wireless communication *** latest communication systems use the antenna array technology to improve the spectral efficiency,fill rate and the energy efficiency of the communication system can be *** of the most important properties of antenna array is beam pattern.A directional main lobe with low side lobe level(SLL)of the beam pattern will reduce the interference and enhance the quality of *** classical methods for reducing the side lobe level are differential evolution algorithm and PSO *** this paper,roused by the eminent swarm conduct of firecrackers,a novel multitude insight calculation called fireworks algorithm(FA)is proposed for work *** FA is introduced and actualized by mimicking the blast procedure of *** the FA,two blast(search)forms are utilized and systems for keeping decent variety of sparkles are likewise all around *** approve the presentation of the proposed FA,correlation tests were led on nine benchmark test capacities among the FA,the standard PSO(SPSO)and the clonal PSO(CPSO).It is demonstrated that the FA plainly beats the SPSO and the CPSO in both enhancement exactness and combinat

关键词： Antenna arrays Spectral efficiency Fill rate Interference evolution algorithm Side lobe level Paper type Research paper

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：