检索结果-内蒙古大学图书馆

Target layer state estimation in multi-layer complex dynamical networks considering nonlinear node dynamics

Chinese Physics B 2024年第4期33卷 245-252页

作者：吴亚勇王欣伟蒋国平 College of Automation and College of Artificial Intelligence Nanjing University of Posts and TelecommunicationsNanjing 210023China Jiangsu Engineering Laboratory for IOT Intelligent Robots Nanjing 210023China

In many engineering networks, only a part of target state variables are required to be *** the other hand,multi-layer complex network exists widely in practical *** this paper, the state estimation of target state variables in multi-layer complex dynamical networks with nonlinear node dynamics is studied.A suitable functional state observer is constructed with the limited *** parameters of the designed functional observer are obtained from the algebraic method and the stability of the functional observer is proven by the Lyapunov *** necessary conditions that need to be satisfied for the design of the functional state observer are *** from previous studies, in the multi-layer complex dynamical network with nonlinear node dynamics, the proposed method can estimate the state of target variables on some layers directly instead of estimating all the individual ***, it can greatly reduce the placement of observers and computational *** simulations with the three-layer complex dynamical network composed of three-dimensional nonlinear dynamical nodes are developed to verify the effectiveness of the method.

关键词： multi-layer complex dynamical network nonlinear node dynamics target state estimation functional state observer

来源：评论

学校读者我要写书评

暂无评论

Nondestructive Testing of Bridge Stay Cable Surface Defects Based on Computer Vision

引用

Computers, Materials & Continua 2023年第4期75卷 2209-2226页

作者： Fengyu Xu Masoud Kalantari Bangjian Li Xingsong Wang Jiangsu Engineering Lab for IOT Intelligent Robots(IOTRobot) College of AutomationNanjing University of Posts and TelecommunicationsNanjing210023China School of Mechanical Engineering Southeast University Nanjing210096China Rubic Robotics Company AlbertaCanada

The automatically defect detection method using vision inspectionis a promising direction. In this paper, an efficient defect detection method fordetecting surface damage to cables on a cable-stayed bridge automatically isdeveloped. A mechanism design method for the protective layer of cables of abridge based on vision inspection and diameter measurement is proposed bycombining computer vision and diameter measurement techniques. A detectionsystem for the surface damages of cables is de-signed. Images of cablesurfaces are then enhanced and subjected to threshold segmentation by utilizingthe improved local grey contrast enhancement method and the improvedmaximum correlation method. Afterwards, the data obtained through diametermeasurement are mined by employing the moving average method. Imageenhancement, threshold segmentation, and diameter measurement methodsare separately validated experimentally. The experimental test results showthat the system delivers recall ratios for type-I and II surface defects of cablesreaching 80.4% and 85.2% respectively, which accurately detects bulges oncable surfaces.

关键词： Defect detection computer vision bridge cable image enhancement

来源：评论

学校读者我要写书评

暂无评论

Design of cable detection robot and image detection method 41

Design of cable detection robot and image detection method

引用

第41届中国控制会议

作者： Julong Song Fengyu Xu Jinlong Hu Xingsong Wang Jiangsu Engineering Lab for IOT Intelligent Robots(IOTRobot) College of AutomationNanjing University of Posts and Telecommunications Southease University Yangli group

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

To detect surface damage to cables on a cable-stayed bridge automatically,a mechanism design method based on vision inspection and diameter measurement is proposed by combining computer vision and diameter measurement ***,a detection system for the surface damages of cables is *** overall scheme for the defect detection system based on vision inspection and diameter measurement is *** improved local gray contrast enhancement method is used to enhance the contrast of cable defect area,which effectively overcomes the problem of light reflection characteristics and makes the collected cable surface features not *** improved maximum correlation method is used for threshold segmentation of the damaged image to better segment the parts related to defects in the ***,the data obtained through diameter measurement are mined by employing the moving average *** enhancement,threshold segmentation,and diameter measurement methods are separately validated experimentally The structure of the robot is optimized to improve the vibration damping performance of the machine and improve the image acquisition *** results show that the system delivers recall ratios for type-Ⅰ and Ⅱ surface defects of cables reaching 80.4% and 85.2%,respectively and can accurately detect bulges on cable surfaces.

关键词： defect detection computer vision bridge cable diameter measurement image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-Strategy Co-Ordination Aquila Optimizer For Optimization of Mechanical Structure

Multi-Strategy Co-Ordination Aquila Optimizer For Optimizati...

引用

2023 China Automation Congress, CAC 2023

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

ISBN: (纸本)9798350303759

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. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

An improved sparrow search algorithm for mobile robot path planning 41

An improved sparrow search algorithm for mobile robot path p...

引用

第41届中国控制会议

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

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper proposes an improved sparrow search algorithm for robot path *** improved heuristic algorithm introduces Tent map and opposition-based learning scheme into sparrow search *** Tent map is applied to initialize population for greater diversity,and opposition-based learning enhances the diversity of the population in evolution process,so as to avoid the premature convergence of the *** proposed algorithm is adopted to mobile robot path *** results show that the improved algorithm can guide the mobile robot to find the optimal path quickly,and also prove the superiority and effectiveness of the proposed algorithm over the original algorithm.

关键词： Sparrow search algorithm robot path planning opposition-based learning optimization

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

第42届中国控制会议

作者： Tianhang Ming Xiaoling Wang Bo Liu Housheng Su Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) College of Information Engineering Minzu University of China

In this paper,we revisit the interval observer design problem of harmonic oscillator system with unknown but bounded external disturbance and measurement *** 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 ***,a switched high-gain interval observer is proposed to reduce the influence of the measurement noise for a tighter interval width on the state ***,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

Planning strategy for intruder agent based on game theory and artificial potential field

Planning strategy for intruder agent based on game theory an...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Xu, Jiahong Liu, Xiaofeng Zhou, Xu Wang, Huan Lin, Qiguang Jiangsu Key Laboratory of Special Cloud Robots Changzhou213022 China Changzhou Key Laboratory of Cloud Robots and Intelligent Technology Changzhou213022 China College of IoT Engineering Hohai University Changzhou213022 China

ISBN: (纸本)9781665436786

In our work, we propose a planner based on game theory and artificial potential field (APF) that enables intruder to confront defender in 2-D environment. The intruder would compute the mixed strategy approximate Nash equilibrium in the space of agent APF trajectory to maximally approach the target region while evading the pursuit of defender. First, according to the improved APF, the finite pure strategy matrix of agents is obtained by considering the opponent's response to the agents' actions iteratively. Then, Particle Swarm optimization (PSO) is taken to compute the mixed strategy approximate Nash equilibrium based on the expected profit composed of pure strategy matrix. Final, extensive simulation tests on agents are conducted to measure the performance of the planner we proposed. The simulation results show that our method not only has great advantages in the face of greedy defenders, but also is superior to the traditional APF planning algorithm. © 2021 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Climbing and Forward Flight Mechanism of Dragonflies 2nd

Analysis of the Climbing and Forward Flight Mechanism of Dra...

引用

2nd International Conference on the Frontiers of Robotics and Software engineering, FRSE 2024

作者： Zhi, Yi Shen, Huan Ji, Aihong Lab of Locomotion Bioinspiration and Intelligent Robots The College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China Jiangsu Key Laboratory of Bionic Materials and Equipment Nanjing210016 China State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing210016 China

ISBN: (纸本)9789819630127

In recent years, bionic micro air vehicles have garnered significant attention. Compared to other insects and birds, dragonflies exhibit unique flight capabilities, making them one of the best bionic prototypes. To better understand the flight characteristics of dragonflies and to delve into their flapping aerodynamics, this study investigates the kinematic parameters of dragonflies during escape flight (climbing) and normal flight (forward flight). Using four synchronously triggered high-speed cameras, the motion of the dragonflies was tracked and captured, followed by system calibration, feature point matching, and 3D reconstruction. Analysis revealed that dragonflies utilize a figure-8 wingtip trajectory during both climbing and forward flight. The intersection of the trajectory occurs near the pronation phase, which helps generate higher lift and thrust. During forward flight, the phase difference between the forewings and hindwings is smaller compared to climbing, with the downstroke occupying approximately 24% more of the flapping cycle during forward flight than climbing. Additionally, the results indicate that dragonflies do not maintain a fixed linear flight path in either state but exhibit periodic changes in the pitch angle. Climbing requires greater pitch angles and variations in pitch angle compared to forward flight to achieve higher lift. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： High speed cameras

来源：评论

学校读者我要写书评

暂无评论

Fault Detection Based on FIR Filters with Variable Discount Factors for Industrial Robot Drive Systems

引用

Wuhan University Journal of Natural Sciences 2021年第2期26卷 165-173页

作者： WANG Tao ZHANG Le FANG Guanghui BAI Yawen School of Intelligent Equipment Engineering Wuxi Taihu UniversityWuxi 214064JiangsuChina Jiangsu Key Construction Laboratory of IoT Application Technology Wuxi 214064JiangsuChina

To enhance dynamic tracking performance and anti-disturbance capacity of finite impulse response(FIR) filters, variable discount factors are introduced to the recursive least squares(RLS) algorithm. By employing improved FIR filters to conduct modelling of industrial robot drive systems, dynamic characteristics of the target systems are identified. Then the fault detection for a target system can be utilized by analyzing the coefficients of the FIR filter. Finally, an application of the fault detection scheme to a kind of brushless DC motor drive system is described. Compared with reference methods, the proposed scheme achieves effective fault detection and performs better in dynamic tracking and robustness according to the final simulation results.

关键词： fault detection variable discount factor industrial robot FIR(finite impulse response)filter

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

第34届中国控制与决策会议

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

The core idea of collaborative filtering is to use historical interaction data of users and items to find similar users or items for *** of the recommendation work based on the graph field is to directly use the Graph Convolutional Network(GCN) on the user-item bipartite *** 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 *** this work,the user-item bipartite graph will be transformed into two homogeneous ***,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 ***,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 *** 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： Collaborative filtering Graph convolutional network Weighted network Matrix decomposition Similarity

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：