检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Yangzheng Li Dongmei Wu College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Engineering Lab for IoT Intelligent Robots Nanjing University of Posts and Telecommunications Nanjing China

Aquila Optimizer(AO) is a recently proposed metaheuristic optimization algorithm. Although AO has significant global exploration capabilities, its local exploitation capabilities are weak. To address the problem of AO's tendency to experience sluggish convergence and local optimum, a Multi-Strategy Co-ordination Aquila Optimizer (MCAO) algorithm is proposed in this paper. The population is initially initialized using Bernoulli's chaotic map. Gaussian difference variation is applied for updating the population during iteration. The adaptive weight strategy based on Tent chaotic sequence is used to speed up the convergence speed of the algorithm. Finally, the parabolic foraging strategy is applied to escape from the local optimum. The proposed MCAO algorithm was tested using part of the CEC2021 test function. The findings demonstrate that MCAO outperforms AO in terms of convergence accuracy and convergence rate. Finally, MCAO is used in two industrial engineering problems, through experimental results, It has been proven that the MCAO is very applicable to solving real-world problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cascaded fault model of power grid with active defense strategy

Cascaded fault model of power grid with active defense strat...

引用

第34届中国控制与决策会议

作者： Gang Liu Yurong Song Ruqi Li School of computer science Nanjing University of Posts and telecommunications School of automation Nanjing University of Posts and telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots (IOT Robot)

With the rapid development of power system,its potential hazards are also *** attention to grid cascading faults and building a robust smart grid have become a hot topic in current *** on the complex network theory system and the existing electrical betweenness model,a cascading failure model with active defense strategy has been proposed and its robustness has been *** the node is attacked and fails,the distribution principle of "the capable nodes are always busy" is adopted to distribute the failure *** is,the larger the residual load capacity of adjacent nodes,the more load will be *** active defense strategy has been proposed to artificially remove a small number of nodes with a large "removal ratio",reduce the electrical betweenness of other nodes,and prevent the propagation of cascading faults and power grid *** IEEE118 and IEEE300 power grid system simulation,the effects of key factors such as attack mode,allocation strategy and tolerance parameters on network robustness have been *** experimental simulation shows that the power grid cascade failure model with active defense strategy can better inhibit the further spread of power grid cascade faults.

关键词： Power system Cascade failure Active defense strategy Remove ratio Network robustness

来源：评论

学校读者我要写书评

暂无评论

Event-triggered impulsive synchronization of heterogeneous neural networks

引用

Science China(Information Sciences) 2024年第2期67卷 331-332页

作者： Zhengxin WANG Chongfang JIN Wangli HE Min XIAO Guo-Ping JIANG Jinde CAO College of Science Nanjing University of Posts and Telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) Nanjing University of Posts and Telecommunications Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology School of Automation Nanjing University of Posts and Telecommunications School of Mathematics Southeast University Yonsei Frontier Lab Yonsei University

Synchronization is one of the most important dynamics in neural networks. Several scholars have studied the quasi-synchronization of heterogeneous neural networks [1],wherein external controllers play a significant role. Impulsive control, a kind of energy-saving control, is activated instantaneously only at specific discrete moments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weighted Graph Convolutional Network for Collaborative Filtering Considering Entity Similarity

Weighted Graph Convolutional Network for Collaborative Filte...

引用

Chinese Control and Decision Conference, CCDC

作者： Yutao Shi Yurong Song Saisai Qu College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing Jiangsu Engineering Lab for IOT Intelligent Robots(IOTRobot) Nanjing

ISBN: (纸本)9781665478977

The core idea of collaborative filtering is to use historical interaction data of users and items to find similar users or items for recommendation. Most of the recommendation work based on the graph field is to directly use the Graph Convolutional Network (GCN) on the user-item bipartite graph. This kind of graph cannot reflect the similarity of information between the homogenous nodes of the users (items). To solve this problem, a Weighted Graph Convolutional Collaborative Filtering recommendation model (WGCCF) considering entity similarity is proposed. In this work, the user-item bipartite graph will be transformed into two homogeneous graphs. Firstly, the user-item scoring matrix is decomposed by singular value decomposition, and the vector representation of users(items) is obtained to calculate the similarity between users (items). Then the similarity is used as the edge weight of nodes in user(item) homogeneous networks and a weighted network based on node similarity is constructed. Finally, graph convolution operation is performed on the user (item) graph to extract the hidden layer representation of the user (item), and the vector inner product combination method is used to predict the score. Experimental results show that compared with the existing recommendation algorithms for matrix factorization and graph convolution, the index performance of RMSE and MAE can be improved up to 12.72% and 15.99%.

关键词： Analytical models Convolution Collaborative filtering Prediction algorithms Feature extraction Heterogeneous networks Bipartite graph

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Inverse Kinematics of Offset Wrist Manipulators Using Improved Differential Evolution Algorithm With Quaternion

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 6840-6847页

作者： Shutao Wu Shikun Wen Zhikang Yang Xuefei Liu Qingfei Han Kai Cao Lu Li Huan Shen Aihong Ji Lab of Locomotion Bioinspiration and Intelligent Robots College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei China Lab of Locomotion Bioinspiration and Intelligent Robots the College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Jiangsu Key Laboratory of Bionic Materials and Equipment Nanjing China State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing China

Inverse kinematics (IK) is at the core of manipulator control theory, with its solution accuracy directly impacting the robot's performance in executing tasks. This is particularly true for complex offset wrist manipulators (OWM), where existing evolutionary computation methods often face limitations in solution efficiency. Additionally, traditional modeling approaches may introduce inherent errors during the solution process, which are amplified through the iterative steps of evolutionary computation, resulting in deviations between the theoretically optimal solution and the actual implementation on robotic platforms. To address these challenges, this letter proposes a novel IK algorithm, TPEDE-IK, which integrates an improved differential evolution algorithm with quaternion-based modeling. The algorithm is designed to handle OWMs with various configurations and degrees of freedom. Experimental results demonstrate that the TPEDE-IK algorithm achieves superior performance on real robotic platforms, significantly improving solution accuracy and providing a robust foundation for future research in robotic control.

关键词： Wrist Quaternions Manipulators Kinematics Linear programming Optimization Evolutionary computation Accuracy Vectors Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Cascaded fault model of power grid with active defense strategy

Cascaded fault model of power grid with active defense strat...

引用

Chinese Control and Decision Conference, CCDC

作者： Gang Liu Yurong Song Ruqi Li School of Computer Science Nanjing University of Posts and Telecommunications Nanjing School of Automation Nanjing University of Posts and Telecommunications Nanjing Jiangsu Engineering Lab for IOT Intelligent Robots (IOT Robot) Nanjing China

ISBN: (纸本)9781665478977

With the rapid development of power system, its potential hazards are also increasing. Paying attention to grid cascading faults and building a robust smart grid have become a hot topic in current research. Based on the complex network theory system and the existing electrical betweenness model, a cascading failure model with active defense strategy has been proposed and its robustness has been analyzed. When the node is attacked and fails, the distribution principle of "the capable nodes are always busy" is adopted to distribute the failure load. That is, the larger the residual load capacity of adjacent nodes, the more load will be distributed. An active defense strategy has been proposed to artificially remove a small number of nodes with a large "removal ratio", reduce the electrical betweenness of other nodes, and prevent the propagation of cascading faults and power grid collapse. Through IEEE118 and IEEE300 power grid system simulation, the effects of key factors such as attack mode, allocation strategy and tolerance parameters on network robustness have been studied. The experimental simulation shows that the power grid cascade failure model with active defense strategy can better inhibit the further spread of power grid cascade faults.

关键词： Analytical models Power system protection Complex networks Power grids Robustness Systems simulation Smart grids

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Stochastic Multiplex Networks With Impulsive Effects

Synchronization of Stochastic Multiplex Networks With Impuls...

引用

第33届中国控制与决策会议

作者： Zhengxin Wang Xin Jin Yanling Lu Yuanzhen Feng School of Science Nanjing University of Posts and Telecommunications Jiangsu Engineering Laboratory for IoT Intelligent Robots Nanjing University of Posts and Telecommunications

This paper investigates synchronization of the stochastic multiplex networks with impulsive ***,compared with the single-layer networks,multiplex networks can express more ***,stochastic perturbations and impulses are ubiquitous and both can affect ***,a multiplex network with stochastic perturbations and impulses is ***,in order to solve the effect of impulses,the average impulsive interval method is *** on the Lyapunov function method,Ito's formula and exponential martingale inequality,the sufficient conditions for the multiplex networks to achieve almost sure exponential synchronization are ***,a numerical example of a two-layer multiplex network is given to illustrate the effectiveness of the theoretical results.

关键词： Multiplex networks stochastic perturbations impulsive effects average impulsive interval Ito's formula exponential martingale inequality

来源：评论

学校读者我要写书评

暂无评论

Effect of Thermal and Mechanical Training in Twisted and Coiled Polymer Fiber (TCPF) Artificial Muscle for Improved Actuation Consistency 23rd

Effect of Thermal and Mechanical Training in Twisted and Coi...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and engineering, IFToMM CCMMS 2022

作者： Li, Bo Zhang, Yakun Zhang, Yu Wang, Yanjie Formin, Alexey Chen, Guimin Zhang, Yong Shaanxi Key Lab of Intelligent Robots School of Mechanical Engineering Xi’an Jiaotong University Xi’an710049 China Key Laboratory of Shaanxi Province for Craniofacial Precision Medicine Research College of Stomatology Xi’an Jiaotong University Xi’an710049 China Jiangsu Provincial Key Laboratory of Special Robot Technology Hohai University Changzhou Campus Jiangsu Changzhou213022 China Moscow101000 Russia Department of Thoracic Surgery The First Affiliated Hospital of Xi’an Jiaotong University Xi’an710061 China

ISBN: (纸本)9789811993978

Twisted and coiled polymer fiber (TCPF) is a new type of artificial muscles featuring large stroke and high loading capacity that can be benefited in soft robotic actuation. However, due to the multi-step fabrication process with various parameter, the existed TCPF suffers from an inconsistent actuation performance, which hinders its further application. The current paper studies the mechanics of TCPF actuation, revealing the significance of coiling and annealing procedure. Effect of twisting weight, annealing temperature and pre-stretch as mechanical and thermal training, are experimentally investigated, and the contraction forces are characterized. With these mechanical and thermal training, consistent and hysteresis-free contraction force is attain. The findings offer a guidance for the high-performance artificial muscle in compliant structures and tensegrity robot. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

A Soft Robotic Glove for Hand Rehabilitation using Pneumatic Actuators with Jamming Structure

A Soft Robotic Glove for Hand Rehabilitation using Pneumatic...

引用

第40届中国控制会议

作者： Xudong Cao Kaiwei Ma Zhenjiang Jiang Fengyu Xu College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot)

In order to solve the problem that the current soft robotic glove for hand rehabilitation can only assist the movement of the fingers in a single direction and the output force is insufficient under lower air pressure,a soft pneumatic actuator coupled with a granular jamming system is *** of all,based on the analysis of the hand movement requirements,the design requirements of the soft robotic glove are proposed,and the structure design is carried ***,the deformation analysis of the pneumatic structure is performed based on the Yeoh model,and the actuator is simulated by ***,the manufacturing method of the actuator and the soft robotic glove is given,experiments of actuator performance and grasping experiments of the soft robotic glove are carried *** results show that the maximum bending angle of the driver can reach 138°,the side swing angle can reach 60°,and the maximum output force can reach 5.7 N under the pressure of 200 kPa,which meets the requirements of hand rehabilitation and can assist in grasping objects.

关键词： Soft Actuator Hand Rehabilitation Pneumatic Structure Granular Jamming System

来源：评论

学校读者我要写书评

暂无评论

Switched High-Gain Based Interval Observer Design for Harmonic Oscillator System

Switched High-Gain Based Interval Observer Design for Harmon...

引用

Chinese Control Conference (CCC)

作者： Tianhang Ming Xiaoling Wang Bo Liu Housheng Su College of Automation & AI Nanjing University of Posts and Telecommunications Nanjing P. R. China Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) Nanjing China College of Information Engineering Minzu University of China Beijing P. R. China Key Laboratory of Image Processing and Intelligence Control of Ministry of Education Huazhong University of Science and Technology Wuhan P. R. China

In this paper, we revisit the interval observer design problem of harmonic oscillator system with unknown but bounded external disturbance and measurement noise. With the bounding information of the external disturbance and measurement noise, a high-gain interval observer is firstly defined and constructed for the harmonic oscillator system to realize the interval estimation on the state and the robust control of the system. Then, a switched high-gain interval observer is proposed to reduce the influence of the measurement noise for a tighter interval width on the state estimation. Finally, some numerical simulations are given to verify the theoretical results.

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：