检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Chenglin Yang Zihao Chai Xiaoxiao Yang Hanyang Zhuang Ming Yang Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China Key Laboratory of Automobile Components and Vehicle Technology Guangxi University of Science and Technology Liuzhou China

ISBN: (纸本)9781665481106

The SLAM system, which uses 3D LiDAR as the only sensor, is prone to degradation when facing a scenario with sparse structure and fewer constraints. It cannot solve the robot pose based on limited LiDAR constraint information, which leads to the localization failure and mapping failure of the SLAM system. Due to the limitations of LiDAR, it is difficult to only rely on the point cloud data provided by LiDAR to solve the problem of localization and mapping of degraded scenarios. Currently, the mainstream is to provide additional information through multi-sensor fusion and other schemes to restrict and correct the system's attitude. In the multi-source fusion system, it is still essential to determine the information reliability of each sensor source in different directions. Hence, the recognition of the degradation scenario has significant research value. In this paper, three schemes, geometric information, constraint distur-bance, and residual disturbance, are designed to quantitatively identify the degradation state of the system and estimate the degradation direction. Through experimental verification, the proposed schemes have a favorable recognition effect in the degradation scenario of the simulation environment and real environment.

关键词： Degradation Location awareness Point cloud compression Bridges Simultaneous localization and mapping Laser radar Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

A Real-time Fire Segmentation Method Based on A Deep Learning Approach

引用

IFAC-PapersOnLine 2022年第6期55卷 145-150页

作者： Mengna Li Youmin Zhang Lingxia Mu Jing Xin Ziquan Yu Shangbin Jiao Han Liu Guo Xie Yi Yingmin Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an Shaanxi 710048 China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Quebec H3G 1M8 Canada College of Automation Engineering Nanjing University of Aeronautics and Astronautics (NUAA) Nanjing Jiangsu China

As a kind of the forest “fault”, fire is highly destructive and difficult to rescue. Fire segmentation is helpful for firefighters to understand the fire scale and formulate a reasonable fire-fighting plan. Therefore, this paper proposes a real-time fire segmentation method based on deep learning. This method is an improved version of deeplbav3+, which is an encoder-decoder structure network. Encoder network is composed of deep convolutional neural network and atrous spatial pyramid pooling. Different from deeplabv3+, in order to improve the segmentation speed, this paper uses the lightweight network mobilenetv3 to build a new deep convolutional neural network and does not use atrous convolution, but it will affect the segmentation accuracy. Therefore, in order to compensate for the loss of segmentation accuracy, on the basis of the original decoder network, this paper adds two different shallow features to make the network contain rich fire feature information. Experimental results show that the comprehensive performance of this method is better than the original deeplabv3+, especially the segmentation speed of the network is greatly improved, which is about 59 FPS.

关键词： Forest fire Fire segmentation Atrous spatial pyramid pooling Mobilenetv3 Deeplabv3+

来源：评论

学校读者我要写书评

暂无评论

$H_{\infty}$ Model Reduction for Fractional-Order Linear systems

$H_{\infty}$ Model Reduction for Fractional-Order Linear Sys...

引用

Chinese control and Decision Conference, CCDC

作者： Guanyou Mo Junguo Lu Dong Yang Yanlong Wu Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China China Academy of Space Technology Beijing China

ISBN: (纸本)9781665431293

This paper focuses on the $H_{\infty}$ model reduction problem of fractional-order Linear systems with commensurate fractional order $0 < \alpha < 1$ . Firstly, resorting to the $H_{\infty}$ bounded real lemma, a design method based on the linear matrix inequalities is proposed to construct an asymptotically stable reduced-order model for the given stable fractional-order linear system, such that the $H_{\infty}$ norm of the error between the transfer function of the reduced-order model and the transfer function of the given stable fractional-order system is less than the prescribed $H_{\infty}$ performance. Secondly, by introducing a free-weighting matrix and congruent transformation, the system parameters of the reduced-order model are decoupled with the complex matrix variable and parameterized by another free-weighting matrix variable. Finally, one numerical example are given to illustrate the effectiveness of the proposed theoretical results.

关键词： Linear systems Uncertainty Design methodology Transfer functions Reduced order systems Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Consensus with Event-Triggered Communication and Relative Output Sensing

Multi-Agent Consensus with Event-Triggered Communication and...

引用

第40届中国控制会议

作者： Xianwei Li Shaoyuan Li Wei Xing Zheng Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China School of Computer Data and Mathematical Sciences Western Sydney University

This paper investigates the consensus problem of linear multi-agent systems with event-triggered(ET) communication on undirected graphs. More practically, it is assumed that each agent can only access the relative output about its ***, the existing event-triggered(ET) protocols based on relative state sensing or absolute output sensing are not *** by this, an ET output-feedback protocol based on relative output sensing is developed. By a new Lyapunov function with more augmented states, it is proved that the resulting closed-loop system can reach consensus and the protocol states converge to zero. It is also shown that Zeno behavior is excluded from the triggering process. Furthermore, a method for reconstructing the continuous-time relative output from sampled data is formulated, based on which, the protocol can be implemented without continuous monitoring of neighbors. Finally, the effectiveness of the theoretic developments is illustrated by a numerical example.

关键词： Multi-agent system(MAS) Consensus Relative information Output feedback Event-triggered(ET) communication

来源：评论

学校读者我要写书评

暂无评论

Early Forest Fire Segmentation Based on Deep Learning

Early Forest Fire Segmentation Based on Deep Learning

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Li, Mengna Zhang, Youmin Xin, Jing Mu, Lingxia Yu, Ziquan Liu, Han Xie, Guo Jiao, Shangbin Yi, Yingmin Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Shaanxi Xi'an710048 China Concordia University Department of Mechanical Industrial and Aerospace Engineering MontrealQCH3G 1M8 Canada Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing211106 China

ISBN: (纸本)9781665401159

Fire segmentation is very important for fire rescue. It can make firefighters get the information on fire area, spread direction and so on, and then help them make quick and effective fire-fighting plan. Therefore, this paper proposes an early forest fire segmentation algorithm based on a deep learning model, named F-Unet, which mainly uses the architecture idea of Unet for reference. F-Unet consists of contraction path, feature fusion layer and expansion path. The contraction path is composed of the first 13 layers of VGG16, which is used to obtain feature maps with different scales. In order to improve the segmentation accuracy of the model, the feature fusion network proposed in this paper is added to the Unet architecture to fuse these feature maps with different scales. The expansion path is used for upsampling these feature maps to restore the size of the original input image and obtain the fire segmentation results. The experimental testing results on the FLAME dataset show that F-Unet can significantly improve the fire segmentation precision, and also prove that the proposed feature fusion network is effective to improve the performance of fire segmentation. © 2021 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Application of attention mechanism for multi-time series in fault diagnosis

Application of attention mechanism for multi-time series in ...

引用

第33届中国控制与决策会议

作者： Yang Yu Nan Xia Jianxun Li Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China China Shipbuilding Industry Corporation 708th Institute

A large amount of time series data obtained by sensors in industry can be used for fault ***,multivariate time series data is very complicated,and different features are related to each *** article proposes an improved CNN-LSTM network for attention mechanism of multivariate time *** adding the attention mechanism for multi-time series,the model can focus on the useful time series,so as to better extract the temporal characteristics of multi-time series ***,through the experimental analysis of the fan blade icing problem,the results are compared with the traditional CNN-LSTM model,and the Fl-score of the model is improved by 6.7%.The method presented in this paper is more accurate in solving the problem of multi-variable sequence classification.

关键词： Fault diagnosis Convolutional neural network LSTM Attention multi variate time series classification

来源：评论

学校读者我要写书评

暂无评论

$H_{\infty}$ Performance Robustness Analysis of Fractional-Order systems with Structured Perturbations

$H_{\infty}$ Performance Robustness Analysis of Fractional-O...

引用

Chinese control and Decision Conference, CCDC

作者： Qing-Hao Zhang Dong Yang Yan-Long Wu Jun-Guo Lu Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China China Academy of Space Technology Beijing China

ISBN: (纸本)9781665431293

This paper considers the $H_{\infty}$ performance robustness analysis of fractional-order systems with structured perturbations. Based on the assumption that the nominal fractional-order systems satisfies $H_{\infty}$ performance, innovative conditions for checking whether the fractional-order systems with structured perturbations preserve the $H_{\infty}$ performance are given. Then, the explicit robustness bounds of preserving the $H_{\infty}$ performance of fractional-order systems with structured perturbations are established. The results are derived by using $\mu$ -analysis. The final two numerical examples are provided to illustrate the obtained methods.

关键词： Perturbation methods Robustness

来源：评论

学校读者我要写书评

暂无评论

Energy Management for Zones-Based Isolated DC Multi-microgrids 3rd

Energy Management for Zones-Based Isolated DC Multi-microgri...

引用

3rd EAI International Conference on Smart Grid and Internet of Things, SGIoT 2019

作者： Nawaz, Arshad Wu, Jing Long, Chengnian Lin, Yi Bing Department of Automation School of Electronic Information and Electrical Engineering Key Laboratory of System Control and Information Processing Ministry of China Shanghai Jiao Tong University Shanghai China Department of Computer Science and Information Engineering National Chiao Tung University Hsinchu300 Taiwan

ISBN: (纸本)9783030496098

In this paper, zones based distributed energy management for isolated multi-microgrids is proposed. Loads are categorized into different zones to form zonal multi-microgrids. Each microgrid has own energy management system which can locally manages the supply and demand of its zonal load and minimize the operational cost. Distributed Network Operator (DNO) act as central controller to facilitate the energy exchange between zonal microgrids and balancing the overall system-wide supply and demand in economic way. Demand Response Program (DRP) is also utilized for peak load shifting within the scheduling horizon. In addition to minimization of operation cost, the utilization of DR will also assure the reliability of supply. In the proposed distributed energy management, each microgrid balances its supply and demand locally and exchange surplus and deficit power with other microgrids through DNO. The performance of proposed scheme is demonstrated through case study simulation of radial multi-microgrid structure. © 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Based on Deep Learning and Collaborative Cloud-edge Computation

Surface Defect Detection Based on Deep Learning and Collabor...

引用

International Conference on Computer and Communications (ICCC)

作者： Shunjie He Bo Yang Dafeng Zhu Cheng Li Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai China

ISBN: (纸本)9781665409513

Surface defect detection is a fundamental step of quality management. Nowadays, surface defect detection system based on machine vision technology has made great progress which can gradually replace the human inspector. With the help of convolutional neural networks, the accuracy and stability of the surface defect detection algorithm are improving rapidly. However, it is difficult to process the images which have small defect areas and complex backgrounds. Furthermore, lacking defective samples and limited computation resources are also tough problems. To deal with these problems, a two-stage algorithm combined with object detection and classification networks is proposed. Transform learning and data augmentation are used to deal with the problem of lacking defect samples. Besides, a detection system based on collaborative cloud-edge computation is designed to improve the performance of the algorithm. The result shows that the proposed method has high performance and low requirements of computation resources.

关键词： Training Collaboration Transforms Object detection Classification algorithms Convolutional neural networks Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Pneumatic Electrode Gripper for Robotic Cochlear Implant Surgery

A Miniaturized Pneumatic Electrode Gripper for Robotic Cochl...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Hongyan Gao Yun Zou Shaoping Huang Weidong Chen Anzhu Gao Institute of Medical Robotics and Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai P. R. China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai P. R. China

ISBN: (纸本)9781665481106

Cochlear implant surgery is one of the most challenging surgeries due to the limited workspace and delicate inner structure. A traditional electrode implant instrument is a passive elastic forceps, which needs another forceps to help grip or release the electrode. It is not convenient to achieve delicate operations in a confined space. This paper develops a miniaturized pneumatic electrode gripper at the tip of forceps to achieve active gripping. It transmits the pressurized air through 3D-printed inner lumens to form two inflated soft bubbles to push the electrode to the rigid shell for accurate positioning. The finite element analysis is carried out to evaluate the shape of inflated soft bubbles with variable soft films. A prototype of a gripper with inner tortuous airways is fabricated using micro 3D printing technique, and experiments are carried out to validate its accuracy and demonstrate its ability to grip and release. Finally, robotic teleoperation using a robotic arm and a joystick is implemented for cochlear implant surgery. Results demonstrate that the developed miniaturized pneumatic gripper has successfully achieved electrode implantation in a 3D-printed cochlear phantom.

关键词： Electrodes Cochlear implants Shape Surgery Prototypes Phantoms Pneumatic systems

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：