检索结果-内蒙古大学图书馆

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

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

Threshold image segmentation based on improved sparrow search algorithm (Apr, 10.1007/s11042-022-13073-x, 2022)

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第23期81卷 33547-33547页

作者： Wu, Dongmei Yuan, Chengzhi Nanjing Univ Posts & Telecommun Sch Automat & Artificial Intelligence Jiangsu Engn Lab IOT Intelligent Robots Nanjing Peoples R China

Threshold segmentation based on swarm intelligence optimization algorithm is a research hotspot in image processing, because of its good segmentation effect and easy implementation. This paper proposes an image threshold segmentation method based on an improved sparrow search algorithm and 2-D maximum entropy method. In the proposed algorithm, the nonlinear inertia weight is introduced into the entrants’ update formula to improve the local exploration ability of the algorithm, and Levy flight is introduced into the vigilant sparrows’ update formula to prevent the algorithm from falling into the local optimal solution in the later stage of iteration. In addition, improved sparrow search algorithm is tested on fifteen benchmark functions. The results represent the merit of the proposed algorithm with respect to other algorithms. Finally, the proposed algorithm is applied to entropy based image segmentation. Experiment results on classical images and medical images show that the proposed method improves the segmentation effect in terms of peak signal-to-noise ratio and feature similarity.

关键词： 2-D histogram Levy flight Maximum entropy Nonlinear weight Swarm optimization algorithm Threshold image segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust cooperative tracking of multiagent systems with asymmetric saturation actuator via output feedback

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2024年第1期34卷 506-529页

作者： Qian, Juan Wang, Xiaoling Su, Housheng Jiang, Guo-Ping Nanjing Univ Posts & Telecommun Coll Automat & AI Nanjing Peoples R China Jiangsu Engn Lab IOT Intelligent Robots IOTRobot Nanjing Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan Peoples R China

The robust tracking control problem of the leader-follower multiagent systems affected by asymmetric input saturation and external disturbances is addressed in this article, by following three steps. First, an radial basis function neural network (RBFNN) is developed to estimate the external disturbances and supersaturation, where the supersaturation is induced by asymmetric saturation actuator. Second, combining with the developed radial basis function neural network, a reduced-order observer-based static protocol and a reduced-order observer-based adaptive one are designed for leader-follower systems with un-directed communication topology as well as those with directed communication topology, respectively. Third, some mild premises are given to guarantee the semiglobal robust leader-follower consensus for the above mentioned two kinds of multiagent systems. Finally, the theoretical results are verified by several numerical simulations.

关键词： adaptive radial basis function asymmetric input saturation external disturbances multiagent system

来源：评论

学校读者我要写书评

暂无评论

Error compensation and path planning for sheet metal bending process based on improved modeling algorithms

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第7-8期135卷 3363-3377页

作者： Ding, Da-Wei Xu, Feng-Yu Huang, Zhuo-Ran Jiang, Guo-Ping Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China Jiangsu Engn Lab IOT Intelligent Robots Nanjing 210023 Peoples R China

Sheet metal bending, an essential part of manufacturing, is increasingly used in transportation, aerospace, and related fields. Challenges related to forming accuracy and path generation have always been major concerns in industrial applications. A prediction model based on GA-BPNN (Genetic Algorithm-Backpropagation Neural Network) was developed, determined, and optimized to mitigate the impact of springback on the forming angle. A 9-input model, considering material classification, was adopted to further enhance prediction accuracy. An artificial potential field (APF) method based on discrete geometric calculations of main and auxiliary (DMA) points was introduced to improve the reliability of a collision-free bending path for the shape characteristics of sheet metal parts, and further optimized using the rapidly exploring random tree (RRT) method. The results indicated that the maximum errors in forming angles were reduced from 2.45 to 0.4 degrees, and 0.15 degrees, respectively, when applying different models. The experimental collision-free path maintained a safe distance of 2 mm, ensuring that the robotic arm operated smoothly to the target position. Additionally, this study could advance the development of a more accurate and efficient bending process in industrial settings.

关键词： Sheet metal bending Error compensation of bending angle Robot's path planning Springback Improved modeling algorithm

来源：评论

学校读者我要写书评

暂无评论

Quasi-bipartite synchronization of heterogeneous memristive neural networks via pinning control

引用

NEURAL COMPUTING & APPLICATIONS 2023年第10期35卷 7801-7815页

作者： Yang, Jiuyu Wang, Zhengxin Feng, Yuanzhen Lu, Yanling Xiao, Min Zheng, Cong Nanjing Univ Posts & Telecommun Sch Sci Nanjing 210023 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Jiangsu Engn Lab IOT Intelligent Robots IOTRobot Nanjing 210023 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Sch Automat Nanjing 210023 Jiangsu Peoples R China

This paper focuses on quasi-bipartite synchronization of heterogeneous memristive neural networks (MNNs) with cooperative-competitive interactions. Firstly, MNNs with nonidentical uncertain parameters are investigated. A pinning control is adopted to study robust quasi-bipartite synchronization of uncertain MNNs over the signed graph. A sufficient condition is derived for robust quasi-bipartite synchronization. Secondly, a more general heterogeneous MNNs is further discussed over the signed graph. Due to the heterogeneities of the MNNs, quasi-bipartite synchronization is studied and the corresponding sufficient condition is obtained. Additionally, the upper bounds of quasi-bipartite synchronization for two kinds of MNNs are given. Finally, two examples are given to illustrate theoretical results.

关键词： Memrisitive neural networks Quasi-bipartite synchronization Pinning control Leader-following Heterogeneous

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

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

Distributed observer design of discrete-time complex dynamical systems with long-range interactions

引用

JOURNAL OF THE FRANKLIN INSTITUTE 2023年第12期360卷 8806-8820页

作者： Wang, Xiaoling Fan, Zhen Zhou, Yingjiang Wan, Youhong Nanjing Univ Posts & Telecommun Coll Automat & AI Nanjing 210023 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Jiangsu Engn Lab IOT Intelligent Robots IOTRobot Nanjing 210023 Peoples R China

This paper focuses on the distributed observer design problem of a discrete-time complex dynamical system with long-rang interactions, where the outputs of the system are measured by a group of agents communicating through a directed graph and each agent can access only a part of ones. By introducing the variant d-path Laplacian matrix to describe the long-rang interactions among the multiple agents, a simple full-order distributed observer is first designed. Then, in order to reduce to the number of integrators in the distributed observer, a reduced-order distributed observer is constructed. Finally, some numerical simulations are presented to verify the theoretical results. & COPY;2022 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.

关键词： Directed graphs

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：