检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Liufu, Ying Liu, Mei Jin, Long Wang, Feiyue School of Information Science and Engineering Lanzhou University Lanzhou China College of Computer Qinghai Normal University Xining China Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350337020

In recent years, quadratic optimizations have become increasingly popular in engineering. However, conventional methods that investigate this problem from the perspective of a canonical form with linear constraints are not effective in dealing with the significant challenges posed by quadratic constraints in practice. This paper proposes a solution framework for the quadratic optimization with quadratic constraints (QOQC) based on innovative artificial societies, computational experiments, and parallel execution (ACP) framework. Then, a gradient projection differential neural solution (GPDNS) is proposed to address this. To illustrate the effectiveness of the GPDNS model in solving the QOQC system, numerical simulations are provided. Overall, this paper presents the potential of innovative approaches like the ACP framework to enhance our capabilities in addressing challenging optimization systems. © 2023 IEEE.

关键词： ACP constraints differential neural solution numerical simulation Quadratic optimization with quadratic

来源：评论

学校读者我要写书评

暂无评论

Modulation of marine heatwaves by salinity effect in the Northeast Pacific Ocean in 2013-2014

引用

Acta Oceanologica Sinica 2025年第1期44卷 17-27页

作者： Xiaokun Wang Hai Zhi Ronghua Zhang Jiaxiang Gao Pengfei Lin School of Atmospheric Sciences Nanjing University of Information Science and TechnologyNanjing 210044China Henan Meteorological Disaster Prevention Technology Center Zhengzhou 450003China School of Marine Sciences Nanjing University of Information Science and TechnologyNanjing 210044China Laoshan Laboratory Qingdao 266237China Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment TechnologySchool of Environmental Science and EngineeringNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China

Marine heatwaves(MHWs)are extreme ocean events characterized by anomalously warm upper-ocean temperatures,posing significant threats to marine *** various factors driving MHWs have been extensively studied,the role of ocean salinity remains poorly *** study investigates the influence of salinity on the major 2013-2014 MHW event in the Northeast Pacific using reanalysis data and climate model *** results show that salinity variabilities are crucial for the development of the MHW ***,a significant negative correlation exists between sea surface temperature anomalies(SSTAs)and sea surface salinity anomalies(SSSAs)during the MHW,with the SSSAs emerging simultaneously with SSTAs in the same *** salinity anomalies(SAs)result in a shallower mixed layer,which suppresses vertical mixing and thus sustains the upper-ocean ***,salinity has a greater impact on mixed layer depth anomalies than *** sensitivity experiments further demonstrate that negative SAs during MHWs amplify positive SSTAs by enhancing upper-ocean stratification,intensifying the ***,our analysis indicates that the SAs are predominantly driven by local freshwater flux anomalies,which are mainly induced by positive precipitation anomalies during the MHW event.

关键词： marine heatwave salinity effect ocean stratification and mixing sea surface temperature Northeast Pacific Ocean

来源：评论

学校读者我要写书评

暂无评论

Coverage control for Multi-Agent Systems via Curve Arc Length

Coverage Control for Multi-Agent Systems via Curve Arc Lengt...

引用

Chinese Automation Congress (CAC)

作者： Kaiqi Yang Xiaoli Wang Hengyu Yang Wei Xie Department of Control Science and Engineering Harbin Institute of Technology Harbin China School of Information Science and Engineering Harbin Institute of Technology at Weihai Weihai China School of Aeronautics and Astronautics Tiangong University Tianjin China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

In complex environments, effective and comprehensive information gathering necessitates the strategic deployment of multi-agent systems. Corridor-type regions, characterized as non-convex areas, present substantial challenges in formulating coverage control strategies. To tackle this issue, this paper proposes a novel coverage control methodology for multi-agent systems based on partitioning the coverage area using curve arc lengths. Firstly, the coverage areas for each team is segmented into sequentially arranged subregions based on curve arc lengths. Through adjustments in the virtual leading agent's position, the range of curve arc lengths for each team's coverage areas is dynamically managed. Then, a distributed coverage controller is developed for agents, which integrates the movement status of virtual leading agents to guide agents towards the centroid positions of their respective coverage areas. Finally, numerical simulations affirm the efficacy of the proposed coverage control approach.

关键词： Automation control systems Numerical simulation Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of Factors Influencing Driver Lane-Changing Intentions Based on a Naturalistic Trajectory Data Set on Highways 24

Analysis of Factors Influencing Driver Lane-Changing Intenti...

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Wang, Guangchen Lu, Guangquan Wang, Jinghua Liu, Miaomiao School of Transportation Science and Engineering Beihang Univ. Beijing China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Beijing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

Accurately analyzing and predicting driver lane-changing intentions is of paramount importance, as it significantly enhances the safety of self-driving vehicles in their decision-making processes, holding great promise for the future of intelligent transportation systems. This study extracts fundamental lane-changing characteristic parameters from the Next Generation Simulation (NGSIM) trajectory data set and employs Structural Equation Modeling (SEM) to construct a model that elucidates the factors influencing drivers’ lane-changing intentions. Furthermore, it provides insight into how lane-changing intentions are influenced by lane-changing behavior and explores the intricate connection between intention and associated risks. The results emphasize the substantial negative impact of the longitudinal speed difference between the self-vehicle and the preceding vehicle on lane-changing intentions. Additionally, the consideration of lane-changing risk plays a pivotal role in drivers’ decisions to engage in lane-changing behavior. These findings have significant implications for a deeper comprehension of lane-changing intentions, guiding lane-changing decisions, and enhancing overall traffic safety. © ASCE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Decomposition Based MOEA with Unique Subregions and Stable Matching

Decomposition Based MOEA with Unique Subregions and Stable M...

引用

2021 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2021

作者： Wang, Zhixue Chen, Hanning Liang, Xiaodan He, Maowei Tiangong University School of Control Science and Engineering Tianjin China Tiangong University School of Computer Science and Technology Tianjin China

ISBN: (纸本)9781665441308

The Multiobjective Evolutionary Optimization algorithms (MOEAs) have attracted lots of attention and have been used for resolving engineering problems, such as production scheduling, logistics planning, and intelligent storage. This paper focuses on the modification of the Stable Matching-based Selection (STM) in Evolutionary Multiobjective Optimization (MOEA/D-STM). Generally speaking, the mechanism would strike an equilibrium between the preferences among scalar problems and solutions. Nevertheless, the initial stable matching model may have a high weakness of mismatching with a certain solution. To address the drawback, this paper proposes the Decomposition Based MOEA with Unique Subregions and Stable Matching (MOEA/D-RM). MOEA/D-RM decomposes the multiobjective optimization problem into a number of various subregions for remedying the loss of diversity and introduces the incomplete preference lists into the STM model for repairing the loss of convergence. The effectiveness and competitiveness of MOEA/D-RM are corroborated and compared with several evolutionary multiobjective optimization algorithms. © 2021 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Decentralized Dynamic Disturbance Compensation control Strategy for Multiple Parallel Inverters in Microgrid 1

Decentralized Dynamic Disturbance Compensation Control Strat...

引用

1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

作者： Luo, Shanna Peng, Kaixiang Hu, Changbin Shi, Xiangyi Lu, Heng School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China School of Electrical and Control Engineering North China University of Technology Beijing China Tianjin Electric Power Design Institute Co. Ltd China Energy Engineering Group Tianjin China Institute for Automatic Control and Complex Systems University of Duisburg-Essen Duisburg47057 Germany

ISBN: (纸本)9798350398069

In order to enhance the anti-disturbance capability of voltage fluctuation during microgrid island operation, a decentralized dynamic disturbance compensation control strategy for multiple inverters in parallel based on robust residual generator is proposed. First, a parallel state space model of multiple inverters with line parameters under quasi-stationary line conditions is established. Secondly, for the double closed loop control structure of the inverter, a dynamic compensation controller Q(s) is designed from the perspective of disturbance cancellation, and its control signal is applied to the input terminal of the current loop to realize superposition with the original system current given signal. Then, a residual generator and a dynamic compensation controller Qi(s) are added to each parallel inverter to realize mutual influence among multiple inverters further decoupling. Finally, hardware-in-the-loop experiment on three inverters in parallel are designed on the RTDS platform to verify the effectiveness of the proposed strategy. © 2022 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Tensorized Timeline Alignment for Neural Dynamical Systems in Irregularly Sampled Time Series Prediction

Tensorized Timeline Alignment for Neural Dynamical Systems i...

引用

Chinese control Conference (CCC)

作者： Linxiao Qin Tao Sun Shuo Zhang Xi-Ming Sun School of Control Science and Engineering Dalian University of Technology Dalian Department of Automation Tsinghua University Beijing

For many real-world scenarios, time series prediction needs to be performed on irregularly sampled data. Neural ordinary differential equations have successfully introduced neural dynamical system (NDS) methods into such tasks. However, these models suffer from a large computational cost, and cannot effectively utilize the temporal information in mini-batches, due to mismatched timestamps of samples. In this work, a unified architecture for NDS is developed, with two novel implementations on discrete input sequences (named TDINDS) and continuous sequences (named TCINDS). The reuse of network modules effectively reduces the scale of parameters and time consumption, while maintaining accuracy. In addition, a tensorized timeline alignment method is proposed, which preserves the temporal information of each training sample via reversible mappings, improving prediction performance and reducing time complexity by at least one order of magnitude. Experiments are conducted on the GoogleStock dataset, where we evaluate model accuracy and computational cost by predicting irregular future sequences. The model robustness is tested using incomplete inputs. The results demonstrate the superior performance of TDINDS and TCINDS, with mean square error reduced by 44% and 50% respectively. Robustness evaluation shows that tensorized timeline alignment is also a key factor to enhance irregular time series prediction ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Compound Fault Diagnosis of Planetary Gearbox Using Capsule Network with Multi-Scale Convolutional Neural Network

Compound Fault Diagnosis of Planetary Gearbox Using Capsule ...

引用

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Li, Guoyan Zhang, Jingbin Lu, Guoliang School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu61173 China Taiyuan University of Technology Key Laboratory of Advance Transducers and Intelligent Control System Ministry of Education Taiyuan030024 China School of Mechanical Engineering Key Laboratory of High-efficiency and Clean Mechanical Manufacture of MOE Shandong University National Demonstration Center for Experimental Mechanical Engineering Education Jinan250061 China

ISBN: (纸本)9798350360585

Capsule network is an innovative deep learning-based model that uses neuron vectors as inputs and outputs of the network. It can achieve independent output of multiple classification labels, and solve the problem of decoupling recognition of compound fault components in planetary gearboxes. However, the single-scale feature extraction cannot fully explore multi-scale feature information in compound fault signals. This study proposes a capsule network combined with multi-scale convolutional feature fusion to diagnose the compound fault of planetary gearbox. The multi-scale features are extracted from STFT images of vibration signals using convolutional layers with different kernel sizes;secondly, a capsule network is designed to classify and identify the fault components by using the dynamic routing algorithm. The experiments are conducted to assess the performance of the proposed method, and the results indicates that it can effectively decoupling identify the compound faults with strong anti-interference and stability. © 2024 IEEE.

关键词： Dynamic routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Bearing-Based Formation control Simultaneously Involving Several Heterogeneous Multi-Agent Systems with Nonlinear Uncertainties

Bearing-Based Formation Control Simultaneously Involving Sev...

引用

IEEE Conference on Decision and control

作者： Yujie Wang Shuai Liu School of Control Science and Engineering Shandong University Ji'nan Shandong P.R. China

For a large-scale multi-agent system consisting of agents that have different types of dynamics, employing bearing rigidity theory to handle formation problems is unrealistic since the bearing-based rigid graph is extremely complicated and heterogeneous agents are hard to analyze as a whole. Therefore, we inventively propose to separate the large-scale system into smaller subsystems, and each subsystem is generated by agents which share the same dynamics. In such sense, formation control turns to focus on several systems with milder conditions rather than a system with complex analysis. The control objectives are to drive all systems to acquire the desired formation shapes, and make all systems simultaneously maneuver along with the desired velocities and maintain the formation shapes. To reduce communication cost, the leader-follower strategy is applied. To make formation control suitable for general environments, nonlinear uncertainties are considered, and the desired maneuvering velocities are time-varying. Adaptive nonsmooth distributed controllers are appropriately designed for all agents.

关键词：

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：