检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and automation (ICRA)

作者： Zhendong Xiao Changhao Chen Shan Yang Wu Wei Control Science and Engineering School of Automation Science and Engineering South China University of Technology Guangzhou China Colloge of Intelligence Science and Technology National University of Defense Technology Changsha China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Camera relocalization is pivotal in computer vision, with applications in AR, drones, robotics, and autonomous driving. It estimates 3D camera position and orientation (6-DoF) from images. Unlike traditional methods like SLAM, recent strides use deep learning for direct end-to-end pose estimation. We propose EffLoc, a novel efficient Vision Transformer for single-image camera relocalization. EffLoc’s hierarchical layout, memory-bound self-attention, and feed-forward layers boost memory efficiency and inter-channel communication. Our introduced sequential group attention (SGA) module enhances computational efficiency by diversifying input features, reducing redundancy, and expanding model capacity. EffLoc excels in efficiency and accuracy, outperforming prior methods, such as AtLoc and MapNet. It thrives on large-scale outdoor car-driving scenario, ensuring simplicity, end-to-end trainability, and eliminating handcrafted loss functions.

关键词： Computer vision Accuracy Three-dimensional displays Simultaneous localization and mapping Computational modeling Robot vision systems Cameras

来源：评论

学校读者我要写书评

暂无评论

Contrastive Conditional Adversarial Autoencoder with Class-specific Forces for Imbalanced Open-set Fault Detection

引用

IEEE Transactions on automation science and engineering 2025年 22卷 15757-15767页

作者： Zuo, Zhonglin Meng, Tao Li, Zheng Zhang, Hao Liu, Tong Chen, Zhansheng Pang, Zhibo Zhejiang University College of Control Science and Engineering Hangzhou310027 China Zhejiang University School of Aeronautics and Astronautics Hangzhou310027 China Hainan Institute of Zhejiang University Sanya572025 China Chongqing University School of Automation Chongqing400044 China University of Sheffield Department of Computer Science SheffieldS1 4DP United Kingdom Shanghai Aerospace Space Technology Co. Ltd Shanghai201109 China ABB Corporate Research Sweden Department of Automation Technology Vasteras Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm Sweden

In real-world industrial scenarios, fault detection faces the widely recognized challenge of data imbalance, which not only refers to the scarcity of fault data but also includes the imbalance in healthy data. This article is concerned with imbalanced open-set fault detection (IOSFD), a practical yet challenging scenario in industrial applications where multiple healthy operating conditions and multiple fault types are imbalanced. In this article, we propose a new contrastive conditional adversarial autoencoder for IOSFD. It constructs an end-to-end unified model based on multi-class known healthy and faulty data to address the reliance of traditional methods on fault samples, while optimizing with class-specific weighted forces to ensure equal attention to imbalanced known classes. Input and feature reconstruction conditioned on operating modes are utilized to learn a compact decision plane and achieve both unknown fault detection and known data classification. Significantly, we formulate the optimization objective of conditional reconstruction based on contrastive learning and introduce adversarial training to further enhance the model’s performance. The effectiveness of the proposed method is validated through real-world pipeline leak detection and Tennessee-Eastman multi-fault detection. © 2004-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

SoftNB: A Fully Functional NB-IoT PHY for Various SDR Platforms

SoftNB: A Fully Functional NB-IoT PHY for Various SDR Platfo...

引用

International Conference on Network Protocols

作者： Jingze Zheng Chaojie Gu Yuanchao Shu Xiuzhen Guo Shibo He Zhiguo Shi Jiming Chen College of Information Science & Electronic Engineering Zhejiang University China College of Control Science and Engineering Zhejiang University China School of Automation Hangzhou Dianzi University China

ISBN: (数字)9798350351712

ISBN: (纸本)9798350351729

The design of Low Power Wide Area Network (LPWAN) protocols has attracted increasing attention in recent years, particularly within the LoRa research community. However, NB-IoT, another critical LPWAN technology, has not seen similar growth in its research community due to the lack of a functional and flexible software-defined radio (SDR) implementation. To address this gap, we present SoftNB, the first fully functional physical layer SDR implementation for NB-IoT. SoftNB conforms to the latest 3GPP standards and features an efficient and effective signal processing pipeline to mitigate time, frequency, and phase offsets during transmission and reception. Additionally, SoftNB is compatible with various SDR platforms, including USRP, HackRF One, and RTL-SDR Dongle. Extensive evaluations of SoftNB demonstrate its superior performance. Compared to the state-of-the-art baseline, SoftNB achieves an $8\times$ reduction in Block Error Rate (BLER) when the number of repetitions is set to 4 at a distance of 450 meters.

关键词： Meters Time-frequency analysis Protocols Computer peripherals Pipelines LoRa Signal processing Physical layer Low-power wide area networks Software radio

来源：评论

学校读者我要写书评

暂无评论

Model Reduction of Cooperative Systems Using Separable Energy Functions

引用

IFAC-PapersOnLine 2024年第5期58卷 96-101页

作者： Arijit Sarkar Yu Kawano Jacquelien M.A. Scherpen Jan C Willems Center for Systems and Control Discrete Technology and Production Automation ENTEG Faculty of Science and Engineering University of Groningen Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima 739-8527 Japan

In this paper, we develop a model reduction method for cooperative nonlinear systems via their variational systems. Inspired by scalable stability analysis of cooperative systems based on separable functions, we provide novel L1 differential observability and L∞ differential reachability functions and study them by using vector-valued functions. These vector-valued functions characterize not-so-important state variables. By truncating them, model reduction is performed, which preserves cooperativity and stability properties.

关键词： Nonlinear systems monotone systems model reduction balanced realization contraction

来源：评论

学校读者我要写书评

暂无评论

Dual contrastive learning for incomplete multi-view clustering on enhanced liver tumor CT diagnosis 3

Dual contrastive learning for incomplete multi-view clusteri...

引用

3rd International Conference on Biomedical and Intelligent Systems, IC-BIS 2024

作者： Li, Siyuan Li, Xinde School of Cyber Science and Engineering Southeast University Jiangsu Nanjing211100 China Key Laboratory of Measurement and Control of CSE School of Automation Southeast University Jiangsu Nanjing210018 China Southeast University Shenzhen Research Institute Shenzhen518063 China Nanjing Center for Applied Mathematics Nanjing211135 China

ISBN: (纸本)9781510681279

Incomplete multi-view clustering (IMVC) for liver tumor CT images provide common and complementary information, that essential to support liver tumor diagnosis of without labeling. These IMVC techniques still have two problems, though: 1) they only heed the following to the resemblance between the same samples of different views, ignoring the resemblance between different samples of the same view, which can provide more information for liver tumor diagnose;2) most of the existing diagnostic processes are staged, greatly increasing the cost of time. We suggest a solution to these problems by a dual contrastive learning framework to learning mutual information from cross-view contrast learning and intra-view contrast learning at the same time. On this basis, the cosine similarity between views is constructed using positive and negative samples from these dual contrastive learning, and the whole process is carried out synchronously. In this paper, two multi-view liver tumor data sets are compared with 4 methods in recent years, indicating that this method is the most advanced. © 2024 SPIE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Weak-Model Based Reinforcement Learning control Strategy of Aircraft Attitude System

Weak-Model Based Reinforcement Learning Control Strategy of ...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Huang, Dingcui Hu, Jiangping Peng, Zhinan Hao, Mingrui School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789811581540

Intelligent aircraft control is an important strategic development trend. Traditional aircraft control algorithms have a strong dependence on the system models, and it is difficult to cope with the increasingly complex battlefield environment for intelligent aircrafts. In this paper, an online intelligent controller design based on a weak-model reinforcement learning technology is proposed to solve stabilization problem of an aircraft. The control problem is firstly converted to an optimal control problem, then an adaptive dynamic programming (ADP) technology is applied for computing the corresponding nonlinear Hamilton-Jacobi-Bellman equation (HJB) equation. Then, actor-critic neural networks structures are established to learn the optimal controller online where only partial information of the aircraft dynamics is required. The proposed control strategy enables the aircraft to adjust and update its control strategy on-line according to the actual mission targets and environments, such that the requirements of autonomous learning and intelligent operation can be realized. Finally, simulation example is offered to validate the effectiveness of the proposed weak-model based controller design. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fractal Converters with Boundless Current and Voltage Ratings

Fractal Converters with Boundless Current and Voltage Rating...

引用

Power Systems and Electrical Technology (PSET), IEEE International Conference on

作者： Jingyang Fang Qin Jiang Hanqing Yang School of Control Science and Engineering Shandong University Jinan China College of Electrical Engineering Sichuan University Chengdu China School of Automation University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350353204

ISBN: (纸本)9798350353211

Extremely high current/voltage stresses challenge power electronics. This paper proposes a novel series of power converters, collectively referred to as Fractal (F) converters. F converters consist of several identical layers, which further comprise many identical cells or submodules. Salient benefits of F converters include but not limited to 1) modularity and scalability; 2) boundless current and voltage ratings; 3) high power quality; 4) unified control applied to various layers; 5) high reliability; 6) control flexibility, e.g., for efficiency optimization. F converters will quickly find their applications in 1) high-voltage dc/ac transmissions; 2) renewable energy generation; 3) power quality enhancement equipment; 4) electric vehicles; 5) marine and aircraft propulsion; 6) medical applications such as noninvasive magnetic stimulators; 7) high-frequency high-power power supplies; 8) plasma applications; 9) future distributed power grids. For validations, simulation results are presented, demonstrating that F converters operate well as high-voltage and high-current inverters as well as arbitrary pulse generators.

关键词： Pulse generation Renewable energy sources Simulation Scalability Power quality High-voltage techniques Fractals Reliability Voltage control Stress

来源：评论

学校读者我要写书评

暂无评论

Low-Carbon Economic Operation Optimization of Mine Integrated Energy System Considering Energy Supply Uncertainty

引用

Complex System Modeling and Simulation 2024年第3期4卷 258-273页

作者： Xiaokang Wu Yong Zhang Xiaotian Fei Hejuan Hu Xiaoyan Sun Dunwei Gong Xianfang Song North Automatic Control Technology Institute Taiyuan 030006China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China College of Automation and Electronic Engineering Qingdao University of Science and TechnologyQingdao 266061China

Mine integrated energy system(MIES)can promote the uilliation of derived energy and achieve multi-energy complementation and ecological *** it gradually becomes an important focus for scientific carbon reduction and carbon *** reduce the impact of uncertain prediction differences on the system during the process of using mine derived energy,a low-carbon economic operation strategy of MIES considering energy supply uncertainty is developed in this ***,based on the basic structure of energy flow in MIES,the energy-carbon flow framework of MIES is established for the low-carbon operation ***,considering carbon emission constraints,the low-carbon economic operation optimization model(LEOOM)is bullt for MIES to minimize operation cost and carbon ***,multiple uncertainties of the system are modeled and analyzed by using the robust model under the risk aversion strategy of information gap decision theory(IGDT),and a model conversion method is designed to optimize the low-carbon economic operation *** simulation results under three scenarios demonstrate that compared to the existed economic dispatching models,the proposed model achieves a 30%reduction in carbon emission while the operational cost of MIES only is increased by 2.1%.The model ffiently mitigates the carbon emission of the system,and the proposed uncertain treatment strategy can significantly improve the robustness of obtained operation plans.

关键词： mine integrated energy system uncertainty information gap decision theory(IGDT) low-carbon economic dispatch

来源：评论

学校读者我要写书评

暂无评论

Fault Prognostics for Machinery with Multi-Degradation Stage Based on Deep Residual Network and Multi-Task Learning

Fault Prognostics for Machinery with Multi-Degradation Stage...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Wang, Mingxian Cui, Langfu Jiang, Jiahe Wang, Junle Jin, Yang Xiang, Gang Yang, Jianbing Lin, Ruishi Beihang University School of Automation Science and Electrical Engineering Beijing China Shanghai Zhenhua Heavy Industries Co. Ltd Shanghai China Shanghai Electro-Mechanical Engineering Institute Shanghai China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9798350337754

Fault prognostics is critical for complex machines. Deep learning has achieved success in fault prognostics. However, existing methods do not consider the following factors: 1) Machines always take through multi-degradation stages and do not begin to degrade during health stage. 2) Fault prognostics is composed of remaining useful life (RUL) prediction, health stage (HS) prediction and fault category prediction, but previous researches focus more on RUL prediction. This paper proposed a novel prognostics framework to predict both HS and RUL for machines through multi-task learning (MTL). Fuzzy clustering is used for HS labeling and segmented RUL representation. MTL based on hard parameter sharing is used to learn from sensor data. Deep residual network (ResNet) is employed to extract degradation feature as shared layers. Different network towers are designed for two prediction tasks based on shared layers. The proposed framework is verified on XJTU-SY Bearing Datasets. The results demonstrate the superiority of the framework. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Open-loop and closed-loop D^(α)-type iterative learning control for fractional-order linear multi-agent systems with state-delays

引用

Journal of Systems engineering and Electronics 2021年第1期32卷 197-208页

作者： LI Bingqiang LAN Tianyi ZHAO Yiyun LYU Shuaishuai School of Automation Northwestern Polytechnical UniversityXi’an 710129China School of Electrical and Control Engineering Shaanxi University of Science and TechnologyXi’an 710021China College of Electronics and Information Hangzhou Dianzi UniversityHangzhou 310018China

This study focuses on implementing consensus tracking using both open-loop and closed-loop Dα-type iterative learning control(ILC)schemes,for fractional-order multi-agent systems(FOMASs)with *** desired trajectory is constructed by introducing a virtual leader,and the fixed communication topology is considered and only a subset of followers can access the desired *** each control scheme,one controller is designed for one agent *** to the tracking error between the agent and the virtual leader,and the tracking errors between the agent and neighboring agents during the last iteration(for open-loop scheme)or the current running(for closed-loop scheme),each controller continuously corrects the last control law by a combination of communication weights in the topology to obtain the ideal control *** the rigorous analysis,sufficient conditions for both control schemes are established to ensure that all agents can achieve the asymptotically consistent output along the iteration axis within a finite-time *** numerical simulation results demonstrate the effectiveness of the control schemes,and provide some meaningful comparison results.

关键词： multi-agent system fractional-order consensus control iterative learning control virtual leader state-delay

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：