检索结果-内蒙古大学图书馆

International Conference on control and automation (ICCA)

作者： Yulong Zhang Zhongxian Zhou Lingxia Mu Xianghong Xue Jing Xin Youmin Zhang School of Automation and Information Engineering Xi'an University of Technology Xi'an Shaanxi China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Quebec Canada

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

In this paper, an insulator missing defect detection method is proposed based on unmanned aerial vehicles to solve the problem of glass insulator burst fault detection in high-voltage transmission lines. Firstly, the proposed method utilizes the improved Mask R-CNN (region-based convolutional neural network) algorithm to segment insulator strings in aerial images. Then, the constructed encoder-decoder network is used to extract and reconstruct features of the insulators, resulting in residual images. Finally, the residual images preserve the location information of the fault and obtains the result of missing insulators. The experiment shows that the proposed algorithm has high segmentation accuracy for insulators and high recognition accuracy for insulator missing faults.

关键词： Image segmentation Accuracy Power transmission lines Fault detection High-voltage techniques Insulators Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode-based Two-Dimensional Iterative Learning control for Systems with Uncertainties and External Disturbances

Sliding Mode-based Two-Dimensional Iterative Learning Contro...

引用

International Conference on control and automation (ICCA)

作者： Y. Yaru L. Dewei M. Aoyun Furong Gao Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai Department of Chemical and Biological Engineering Hong Kong University of Science and Technology HongKong

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This paper proposes a sliding mode-based two-dimensional (2D) iterative learning control (ILC) strategy for discrete- time batch process systems challenged by uncertainties and external disturbances. Considering the repetitive nature of batch process systems, the ILC method shows significant advantages. Given the presence of non-repetitive uncertainties and external disturbances in practical systems, this paper integrates the sliding mode control (SMC) scheme into the ILC design framework to ensure system robustness. A novel aspect of this study is the development of an augmented 2D model that captures the dynamic evolution in both batch and sampling time directions. Based on this 2D model, a corresponding 2D sliding mode surface and a 2D iterative learning sliding mode controller are designed, preserving the learning capabilities of ILC and the robustness of SMC against uncertainties and external disturbances. The method proposed in this paper enables the controlled system to maintain a high tracking capability in the face of non-repetitive uncertainties and external disturbances. Particularly, the stability conditions derived from this 2D model provide a broad feasible solution space, which improves the applicability. Furthermore, the correctness of the proposed method is proven and its effectiveness is validated through a simulation example.

关键词： Uncertainty System dynamics Two-dimensional displays Simulation Batch production systems Robustness Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Real-time Framework of Multi-Camera Vehicle Tracking System

A Real-time Framework of Multi-Camera Vehicle Tracking Syste...

引用

2024 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2024

作者： Zhuang, Hanyang Chen, Xingyuan Lan, Jianglin Wang, Ying Lu, Zhaoxuan Wang, Chunxiang Yang, Ming University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom Shanghai Jiao Tong University School of Mechanical Engineering Shanghai200040 China Shanghai Intelligent and Connected Vehicle R and D Center Co. LTD Shanghai201400 China Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9798350372601

Multi-camera vehicle tracking (MCVT) system is a key technology to build an intelligent city and intelligent transportation system. The MCVT system utilizes roadside monitoring devices and computing platforms to achieve city-level road traffic perception at a finer scale by tracking each vehicle on the road to obtain the trajectory. The existing MCVT system mainly focuses on dealing with the algorithm modules separately, without studying the real-time performance and system architecture of the entire pipeline. However, in real-world applications, many of the tricks in improving evaluation metrics are not applicable since there is endless traffic flow running all the time. Therefore, this paper proposes a real-time framework of the MCVT system to streamline all the algorithm modules with proper data flow. Firstly, a multi-threaded multi-vehicle tracking (MVT) module is developed to detect vehicles in each camera. Re-identification is implemented during MVT to provide the feature for tracking in the same camera and across different cameras. Then, after the vehicle leaves the camera field of view, the feature of vehicle trajectory is calculated by averaging the feature at each frame. Meanwhile, a background thread runs continuously to match the incoming feature of vehicle trajectory with past features by conducting a topology searching method. In the end, the vehicle trajectories with well-matched features are considered to be the same vehicle. The entire pipeline has been validated on two different datasets, the precision is 0.64 in the CityFlow dataset which uses 6 cameras simultaneously. In the customized dataset, the same method can still reach real-time when using 16 cameras at the same time with smaller network modules. © 2024 IEEE.

关键词： Vehicle locating systems

来源：评论

学校读者我要写书评

暂无评论

Improved ELBO-assisted Transformer for Skeleton-Based Action Recognition

Improved ELBO-assisted Transformer for Skeleton-Based Action...

引用

International Conference on Intelligent Transportation

作者： Arnab Bhattacharjee Wen-Hui Chen Yu-Chen Lin Kuan-Ting Lai Graduate Institute of Automation Technology National Taipei University of Technology Taipei Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan

Recognizing human actions accurately from video data is a difficult task because of the variability in human motion, appearance, and context. A new approach to human action recognition is proposed in this study, which uses a combination of Variational Autoencoder (VAE) and Transformer models. The VAE with IWGECO optimization is utilized for acquiring a compact and discriminative representation of the input 2D skeletons from video frames along with its spatial relations. This encoded representation of 2D poses is then fed into a Transformer model for sequence modeling and classification, resulting in effective recognition of human actions. The proposed approach is evaluated on the MPOSE2021 benchmark dataset, outperforming existing methods (90.6%) with an average classification accuracy of 92.0%. The model performs well on real-life data too showcasing its generalizing potential. The study also addresses the domain shift problem occurring in real-world situations by using a pre-trained VAE and subsequently training the Transformer on the MPOSE2021 dataset. The results demonstrate the effectiveness of combining VAE and Transformer models for human action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization based Trajectory Propagation for RLV Approach and Landing Phase

Particle Swarm Optimization based Trajectory Propagation for...

引用

2022 Chinese automation Congress, CAC 2022

作者： Yan, Han Shen, Xiaxin Wang, Xinghu Beijing Institute of Control Engineering Beijing100094 China Science and Technology on Space Intelligent Control Laboratory Beijing100094 China Beijing Sun Wise Space Technology Ltd. Beijing100094 China University of Science & Technology of China Department of Automation Hefei230027 China

ISBN: (纸本)9781665465335

The trajectory propagation is used to estimate the flight states of the RLV when landing with a designed trajectory, so as to verify that whether the trajectory is suitable or not. Most of existing results are developed based on Euler numerical integration technique, and due to the implementation of the method, the efficiency of propagation may be low if a small integration step is used for high accuracy. To handle such issue, the paper propose a particle swarm optimization (PSO) based trajectory propagation method. With the proposed method, the efficiency of propagation can be significantly improved without losing accuracy. Simulations are done to show the advantages of our method. © 2022 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Heat Transport Modeling And Model-Based Temperature control Of A Residential Building, A Case Study

Heat Transport Modeling And Model-Based Temperature Control ...

引用

International Carpathian control Conference (ICCC)

作者： Krisztián Szilveszter Gál Dénes Nimród Kutasi Automation Engineer Thermo Control Srl. Sfantu Gheorghe Romania Department of Electrical Engineering Sapientia Hungarian University of Transylvania Tirgu Mures Romania

The paper proposes a case study on modeling, model validation, model-based temperature control of a building to demonstrate the effectiveness of a modern control technique versus a classical control used in a residential building. Energy efficiency is a key topic today, thus it is important to study the methods of temperature control in buildings to achieve the desired control with minimum energy usage. The paper presents the heat transport modeling using the R-C model technique, the model validation (parameter tuning) based on long-term measurements, classical control and model-based predictive (MPC) distributed temperature control in the rooms of the building and the comparison of the energy consumption for each case. Moreover, there are two MPC algorithms discussed, with and without external temperature forecast as disturbance variable. The simulation results and real-time measurements are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art Shaped Profile Windings and Their Integrated Cooling Configurations Enabled by Additive Manufacturing Technology

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Zhao, Han Li, Haoran Zhang, Xiaochen Li, Jing Xiong, Bin Yuan, Yixiang Ruan, Yixiao Zheng, Fuyuan Zhang, Rong Zhang, Wei Zhang, He Yongjiang Laboratory Advanced Electric Drive Centre Ningbo315202 China Chinese Academy of Sciences Institute of Electrical Engineering Beijing100080 China University of Nottingham Ningbo China Department of Electrical and Electronic Engineering Ningbo315100 China AVIC Xi’an Flight Automation Control Research Institute Xi’an710076 China

The ongoing development of transportation electrification is driving an increasing demand for higher motor power density. Improved thermal design of electrical machines, including both heat generation and dissipation aspects, could be beneficial for enhancing motor power density beyond current state of the art. As the main heat source, motor windings are being increasingly required with reduced loss generation and enhanced cooling capability. Owing to the considerable manufacturing flexibility offered by additive manufacturing (AM) technologies, shaped profile windings with unconventional geometries are extensively explored with the aim of AC loss suppression and slot utilization enhancement. Furthermore, these tailored winding profiles enable the integration of direct cooling configurations such as liquid channels or heat pipes, thereby improving their thermal behavior. However, a more intensive summary and comparison are necessary to further extend their investigations and applications based on a deeper understanding. Therefore, this paper aims to provide a comprehensive review of state-of-the-art shaped profile windings and their integrated direct cooling configurations enabled by AM technologies. Further to this, this article also discusses the merits and restrictions associated with additively manufactured windings and their direct cooling methods at the current stage. © 2015 IEEE.

关键词： AC machinery

来源：评论

学校读者我要写书评

暂无评论

A Modified Data-driven Distributed Information-Weighted Kalman Consensus Filtering with Switching Topology and Packet Loss

A Modified Data-driven Distributed Information-Weighted Kalm...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Honghai Ji Yuxin Wu Shida Liu Li Wang Lingling Fan Shuangshuang Xiong Department of Electrical and Control Engineering North China University of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

This paper is concerned with distributed state estimation problem over sensor networks with uncertainty in communication networks. Because of the instability of communication in real systems, it is meaningful to consider packet loss and topology change. Thus, based on Kalman consensus filtering algorithm and Data-driven filtering technique, we proposed a modified Data-driven Distributed information-weighted Kalman Consensus Filter to estimate the state. Finally, the effectiveness of the designed algorithm is validated by a simulation example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leader-Following Entrapping control of AUVs Using Bearing Measurements in Local Coordinate Frames

引用

Guidance, Navigation and control 2022年第4期2卷 85-121页

作者： Yingbo Fu Ziwen Yang Shanying Zhu Cailian Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240P.R.China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240P.R.China Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240P.R.China

In this paper,the entrapping control problem of discrete-time AUVs with local coordinate frames is *** achieve entrapment in arbitrarily shaped orbits and formations,we design a bearingbased leader-following framework fully in the discrete-time domain with four parts:the orientation estimation unit,estimator unit,controller unit and parameters tuning *** bearing measurements and communication information,the orientation estimation unit can estimate orientations of local coordinate frames infinite time,and the estimator unit can achieve local *** on estimation,the controller unit can drive each AUV to track the desired orbit or formation with an arbitrary *** present su±cient conditions under which stability of the overall system is proved using the theorem offinite-time stability and LaSalle's theorem for the discrete-time ***,the parameters tuning unit can calculate optimal parameters to improve overall ***,we extend our schemes to nonholonomic AUVs with unicycle ***,simulation results demonstrate the effectiveness of the proposed scheme.

关键词： Entrapping control discrete-time AUVs bearing measurements local coordinate frames

来源：评论

学校读者我要写书评

暂无评论

Smith predictor-based nonlinear internal model control for water temperature regulation of combi-boiler systems

Smith predictor-based nonlinear internal model control for w...

引用

2023 Jiangsu Annual Conference on automation, JACA 2023

作者： Liu, Ruihao Cao, Mengying Li, Shihua Yang, Jun The Key Laboratory of Measurement and Control of CSE Ministry of Education School of Automation Southeast University Nanjing210096 China BDR THERMEA HVAC Co. Ltd Jiaxing314000 China The Department of Aeronautical and Automotive Engineering Loughborough University LoughboroughLE11 3TU United Kingdom

ISBN: (纸本)9781839539848

This paper proposes a reliable and practical water temperature control scheme for combi-boiler systems working in domestic hot water mode. In practice, the water temperature regulation process of a combi-boiler is strongly affected by the nonlinearities of actuators, the variation of system parameters caused by the fluctuation of water flow rate, external disturbances, and large, variable time delays. Although there are some results that can address one or two of these factors, a comprehensive and concise control scheme with consideration of all these factors is lacking. This paper aims to change this situation. First, based on the modeling and identification of real combi-boiler systems, the feedback linearization method is adopted in the controller synthesis to solve the effects of actuator nonlinearity. Next, a Smith predictor-based control structure is designed to eliminate system time delays. Finally, based on the internal model control (IMC) theory, an IMC-based parameter tuning method is proposed for the parameter selection of feedback controllers, in which the model parameters used in the controller synthesis are calculated in real-Time based on the system identification results. As a result, the influence of model uncertainties and external disturbances can be effectively attenuated, and only one parameter is required to be tuned for the desired performance. The feasibility and effectiveness of the proposed control scheme are verified by simulations. © The Institution of engineering & Technology 2023.

关键词： Water temperature

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：