检索结果-内蒙古大学图书馆

SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING 2024年第6期51卷 598-608页

作者： Bobrovskaya, O. P. Gavrilenko, T. V. Galkin, V. A. Surgut State Univ Surgut 628400 Khanty Mansi Au Russia Russian Acad Sci Surgut Branch Fed State Inst Sci Res Inst Syst Anal Surgut 628426 Russia

This article considers a problem of route simulation of autonomous vehicles in a collision-free traffic. A new swarm algorithm is proposed, based on a microscopic traffic model, which ensures the collision-free motion of agents. The change in the several optimality criteria is considered in the process of the algorithm operation, such as: average speed of agents, throughput, and the number of lane changes. The boundaries of the effective values of the algorithm hyperparameters are estimated. Free flow and an improvement in the optimization criteria are observed for certain density parameters and attraction-repulsion factors in the traffic.

关键词： swarm intelligence swarm algorithm microscopic traffic model agent fish school algorithm

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC TRAJECTORY AND CONVERGENCE ANALYSIS OF swarm algorithm

引用

COMPUTING AND INFORMATICS 2012年第2期31卷 371-392页

作者： Yue, Benxian Liu, Hongbo Abraham, Ajith Dalian Univ Technol Sch Elect & Informat Engn Dalian 116023 Peoples R China MIR Labs Machine Intelligence Res Labs Auburn WA 98071 USA

swarm intelligence (SI) is an innovative distributed intelligent paradigm whereby the collective behaviors of unsophisticated individuals interacting locally with their environment cause coherent functional global patterns to emerge. Although the swarm algorithms have exhibited good performance across a wide range of application problems, it is difficult to analyze the convergence. In this paper, we discuss the dynamic trajectory and convergence of the swarm intelligent model, namely the particle swarm algorithm. We explore the tradeoff between exploration and exploitation using differential analysis and Laplace transform. The trajectories are parsed into first-order inertial element and second-order oscillation element. Their transfer functions are derived, and the trajectories are described in explicit time functions. The first-order inertial element is helpful to maintain the trajectory's stability and algorithm convergence, while the second-order oscillation element trends to explore some new search spaces for the better solutions. The convergence regions of the swarm system are analyzed using the spectral radius and Lyapunov second theorem on stability.

关键词： swarm intelligence swarm algorithm convergence stability

来源：评论

学校读者我要写书评

暂无评论

Maximizing energy tracking in photovoltaic grid-connected system through modified tunicate swarm algorithm - control on environmental effect of irradiance conditions

引用

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS 2022年第1期44卷 1620-1639页

作者： Reddy, K. Harinadha Lakireddy Bali Reddy Coll Engn Autonomous Dept Elect & Elect Engn Mylavaram India Jawaharlal Nehru Technol Univ Kakinada Kakinada India

Photovoltaic (PV) systems are mostly utilized in all fields of applications, especially for remote electrification purpose. Irradiance change during the day, and the conditions are more dynamic at cloudy days. Environmental conditions are a challenge/dynamic task and require individual control methods for maximum tracking of the available power. Maximum Power Point Tracking (MPPT) methods are designed through power electronic converters, which supply the PV systems to the load. Maximum Power Point (MPP) conditions of PV system with proposed Modified Tunicate swarm algorithm (md-TSA) effectively tunes the controller parameters by the help of voltage and current control. Power control with I/V control is almost improved up to 3.2% as compared with existing methods. Testing of md-TSA has been validated during uniform irradiance and different partial shading conditions. Proposed md-TSA tracking control vector is validated with Positive Conductance Region (PCR) and Negative Conductance Region (NCR) in all maximum energy tracking cases. In a propped work, Gravity force of will be modified and determined modified gravity force. Hence control of md-TSA will to meet dP/dV and (I + dI/dV ) on both PCR and NCR for validating MPP. Proposed md-TSA has been validated for 50% loading and 100% loading conditions with the control vector. Quantitative data according to variations of loading, the voltage control vector can able improves the performance up to 6-8%. Also quantitative data according to variations of irradiance levels, the control vector of module current will improve the performance 5-10% and explored in test condition-1, 2 of results. By the proposed md-TSA, islanding has been tested with added control to voltage thresholds and hence proper switching pulses of converter are initiated. Here islanding switching t(sw) has been considered either '0' or '1' for test event validation. Switching time signal t(sw) have determined for switching instants S >= 0 , S < 0 and valida

关键词： Irradiance swarm algorithm positive conductance region negative conductance region and MPPT control

来源：评论

学校读者我要写书评

暂无评论

Numerical optimization and feed-forward neural networks training using an improved optimization algorithm: multiple leader salp swarm algorithm

引用

EVOLUTIONARY INTELLIGENCE 2021年第3期14卷 1233-1249页

作者： Bairathi, Divya Gopalani, Dinesh Malaviya Natl Inst Technol Jaipur Jaipur Rajasthan India

Metaheuristics are one of the most promising techniques for solving optimization problems. Salp swarm algorithm (SSA) is a new swarm intelligence based metaheuristic. To improve the performance of SSA, this paper introduces multiple leader salp swarm algorithm (MLSSA), which has more exploratory power than SSA. The algorithm is tested on several mathematical optimization benchmark functions. Results are compared with some well known metaheuristics. The results represents the capability of MLSSA to converge towards the optimum. In recent studies many metaheuristic techniques are applied to train feed-forward neural networks. In this paper MLSSA is also applied for neural network training and is analysed for thirteen different datasets. Performance is compared with SSA, particle swarm optimization, differential evolution, genetic algorithm, ant colony optimization and evolution strategy.

关键词： Optimization Metaheuristics Multiple leader salp swarm algorithm swarm algorithm Feedforward neural networks-training Classification Regression

来源：评论

学校读者我要写书评

暂无评论

Evolutionary swarm algorithm Based on Evolutionary swarm Model

Evolutionary Swarm Algorithm Based on Evolutionary Swarm Mod...

引用

1st WRI Global Congress on Intelligent Systems (GCIS 2009)

作者： Quan, Haiyan Shi, Xinling Kunming Univ Sci & Technol Fac Informat & Automat Kunming 650051 Peoples R China Yunnan Univ Informat Coll Kunming 650091 Peoples R China

ISBN: (纸本)9780769535715

The paper introduces an evolution swarm model that clearly demonstrates many intelligent algorithms. Based on the model, an evolutionary swarm algorithm is designed In this work, the evolutionary swarm algorithm is tested with 5 multivariable benchmark functions. The simulation results show that the algorithm possesses an excellent performance in the global optimization, and can be efficiently employed to solve the multimodal function optimization for the multimodal function with high dimensionality

关键词： swarm algorithm evolution algorithm evolutionary swarm model evolutionary swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent car platform for swarm algorithm verification 13

Intelligent car platform for swarm algorithm verification

引用

2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI)

作者： Tong Baojun Hou Ligang Wang Zhongchao Wang Jinhui Wang Wensi VLSI and System Lab Beijing University of Technology Department of Electrical and Computer Engineering North Dakota State University

ISBN: (纸本)9781509050369;9781509050352

As an important part of artificial intelligence, swarmalgorithm is mostly verified by theoretical simulation. In this paper, such swarm behavior is verified by intelligent cars. The hardware design includes intelligent car network module, speed measurement module, electronic compass module and motor module, etc. The software part includescontrol program of each module and swarm algorithm. Based on the intelligent car's swarm algorithm, this paper designs a suitable platform of intelligent car for verification. Finally completes the design and algorithm verification of the intelligent car successfully.

关键词： intelligent car verification swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Early Warning Method for Distribution Network Operation Risk Based on Improved Particle swarm algorithm 1

Intelligent Early Warning Method for Distribution Network Op...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Liu, Lulu Simayi, Xuelati Xiaokaiti, Maihebubai Jia, Junqiang Yang, Lina State Grid Xinjiang Electric Power Co. Information and Telecommunication Company Urumqi China

ISBN: (纸本)9798350316469

The reliable operation of distribution networks is crucial for ensuring the uninterrupted supply of electricity to consumers. However, these networks face various risks that can lead to disruptions and pose significant challenges for network operators. To address this issue, an intelligent early warning method for distribution network operation risk based on an improved particle swarm algorithm is proposed in this study. The findings indicate that the proposed intelligent early warning method outperforms existing approaches in terms of accuracy, computational efficiency, and early warning timeliness. The method's ability to accurately identify risks and provide real-time warnings empowers network operators to take proactive measures, ensuring the stability, reliability, and resilience of distribution networks. The research contributes to the advancement of intelligent decision support systems for power system operation and opens avenues for further research in risk management and optimization techniques. © 2023 IEEE.

关键词： distribution networks intelligent decision real-time warnings swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Phase transition in a swarm algorithm for self-organized construction

引用

Physical Review E 2003年第4期68卷 046111-046111页

作者： Henri Leung Ravi Kothari Ali A. Minai Complex Adaptive Systems Laboratory ECECS Department University of Cincinnati Cincinnati Ohio 45221-0030 USA

This paper reports on a system where very simple, noncommunicating mobile agents in a cellular (lattice) environment use purely local rules to construct connected structures from initially randomly distributed building blocks. We study the effect of block density on the final structure, demonstrating a percolationlike phase transition: Low block densities lead to the formation of small, disconnected structures but a single connected structure emerges abruptly beyond a critical density. The empirical study of the structure at the transition point shows scaling behavior, providing strong evidence for criticality. We also demonstrate that a simple change of rules can completely change the phase-transition effect. The results have implications for the self-organized construction of complex structures by swarms.

关键词： .colonies emergent structures critical density simple agents swarm algorithm block density Low block

来源：评论

学校读者我要写书评

暂无评论

Parametric estimation for AWJ cutting of Ti-6Al-4V alloy using Rat swarm optimization algorithm

引用

MATERIALS AND MANUFACTURING PROCESSES 2022年第16期37卷 1871-1881页

作者： Tamilarasan, A. Renugambal, A. Vijayan, D. Sri Chandrasekharendra Saraswathi Viswa Mahavidya Dept Mech Engn Kanchipuram 631561 Tamil Nadu India Univ Coll Engn Kancheepuram Dept Math Kanchipuram India

The kerf taper angle is one of the most significant parameters for AWJ cutting. Choosing the best cutting parameters is critical to reducing the kerf taper. Therefore, the aim of this work is to demonstrate on to implement RSM in conjunction with the Rat swarm optimizer algorithm to optimize the kerf taper angle of a Titanium alloy. Thirty-two number of experiments were conducted according to CCD considering five process parameters namely jet traverse rate, water jet pressure, abrasive flow rate, stand-off distance and diameter of focusing nozzle to achieve kerf taper angle. A second-order full quadratic model is used for mathematical modeling. The result demonstrates that the model is sufficiently adequate and acceptable. A recent Rat swarm Optimization (RSO) algorithm is considered for finding out the global optimal solution. It is observed that after optimizing the process that the jet traverse rate of 1.952 mm/sec, water jet pressure of 250.548 MPa, abrasive flow rate of 0.554 kg/min, stand-off distance of 3.75 mm and diameter of focusing nozzle of 2.0 mm gives minimized with 0.754 degree of kerf taper angle. A series of verification tests are carried out to ensure that the optimization technique is accurate in determining the best levels of process.

关键词： Parameters AWJ cutting RSM CCD ANOVA graphical analysis Rat swarm algorithm optimization Ti-6Al-4V alloy kerf taper angle

来源：评论

学校读者我要写书评

暂无评论

An improved grey wolf algorithm and its localization research in complex indoor environments

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-23页

作者： Li, Bing Hao, Yanxin Cui, Yiyang Chai, Xingshao Zhou, Jingmei Liu, Chungang Hebei Normal Univ Coll Combust Engn Shijiazhuang 050024 Peoples R China Hebei Prov Key Lab Informat Fus & Intelligent Cont Shijiazhuang 050024 Peoples R China Hebei Prov Innovat Ctr Wireless Sensor Network Dat Shijiazhuang 050024 Peoples R China

In complex indoor environments, traditional localization methods often suffer from non-line-of-sight (NLOS) and multipath problems, which lead to unsolvable or incorrectly solved mathematical localization models, thereby limiting localization accuracy. A localization method based on swarm intelligence optimization has been proposed to address this issue. The swarm intelligence optimization algorithm does not require solving matrix inversions and transforms the localization problem into a function optimization problem, which can obtain approximate optimal solutions. Nevertheless, optimization algorithms are beset with issues like sluggish convergence speed and proneness to getting trapped in local optima, thereby failing to satisfy the current practical requirements for localization. This paper proposes a new method that applies the grey wolf optimization (GWO) algorithm to ultra-wideband (UWB) indoor localization to enhance localization accuracy. It improves the GWO algorithm with four strategies. Firstly, a small-area optimization strategy near the target point is proposed. The Chan algorithm is adopted for initial tag localization, and the initial localization result is taken as a constraint to construct the search area of the GWO algorithm, thereby reducing the large space region to a small space region and enhancing optimization efficiency. Secondly, an improved Tent mapping, a nonlinear convergence factor, a fitness-weighted location update strategy, and an out-of-bounds reflection mechanism are designed to improve the GWO algorithm, referred to as the TIGWO algorithm. Finally, apply the TIGWO algorithm to determine the optimal location of the tag. The experimental results indicate that the proposed algorithm significantly enhances indoor localization accuracy. Compared to the Chan, Chan-Taylor, PSO, WOA, and GWO algorithms, the average localization accuracy has been enhanced by 59.65%, 63.41%, 40.97%, 45.97%, and 35.44%, respectively. In an equipment warehouse

关键词： Ultra-wideband technology 3D indoor localization swarm algorithm Grey wolf optimization algorithm Localization accuracy

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：