检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON control OF NETWORK systems 2025年第1期12卷 461-473页

作者： Huang, Yunchang Dai, Shi-Lu South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Minist Guangzhou 510641 Peoples R China Southern Marine Sci & Engn Guangdong Lab Zhuhai Zhuhai 519000 Peoples R China

This article develops a formation maneuver control strategy for a group of underactuated unmanned surface vehicles (USVs) under similarity rigidity framework over directed graphs. The control objective is to achieve similar formation transformations (translation, rotation, and scaling) while maintaining the desired formation shape. The desired formation shape is determined by a set of similarity constraints on the signed angle and the distance ratio of a pair of edges joining a common vertex. Instead of the error variables with respect to the angle or distance ratio usually used in traditional similarity-rigidity control methods, the relative position errors are obtained by the constant rigidity matrix. Once the position of each USV overlaps with the configuration of the target formation, the desired formation maneuver can be achieved. The proposed control strategy can be implemented in a local coordinate system and directed graphs without intervehicle communication. Simulation results demonstrate the effectiveness of the proposed control strategy.

关键词： Rigidity Directed graphs Formation control Shape Network systems autonomous vehicles Underactuated surface vessels control design Convergence Vectors Directed graph formation maneuver similarity rigidity unmanned surface vehicles (USVs)

来源：评论

学校读者我要写书评

暂无评论

Singularity-free predefined time tracking control for quadrotor UAV with input saturation and error constraints

引用

NONLINEAR DYNAMICS 2025年第11期113卷 13225-13242页

作者： Li, Shuo Duan, Na Pei, Hailong South China Univ Technol Key Lab Autonomous Syst & Networked Control Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Minist EducSch Automat Sci & Engn Guangzhou 510640 Peoples R China Jiangsu Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Peoples R China

This paper investigates the predefined time tracking control of a quadrotor UAV in the presence of input saturation, external disturbances and tracking error constraints. In order to realize the predefined time bounded of position and attitude tracking errors, a tan-type barrier Lyapunov function is introduced, and the continuous piecewise function is used to avoid the singularity of power exponents. Considering the saturation limit of the control input, the auxiliary system is proposed to compensate the influence of input saturation. Moreover, a predefined time disturbance observer is utilized to accurately estimate the uncertainty caused by external disturbances. Using the presented observer, the observation error converges within a predefined time. The theorem analysis shows that the controller ensures the tracking error converges to a specified interval in a predefined time without violating the tracking error constraints. Simulation comparison results verify the effectiveness of the proposed control scheme.

关键词： Input saturation Predefined time disturbance observer Error constraint Predefined time control

来源：评论

学校读者我要写书评

暂无评论

Gaitts: indoor gait recognition with multi-scale temporal-spatial information aggregation

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-12页

作者： Zhang, Langwen Men, Zihan Xie, Wei South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Guangdong Peoples R China South China Univ Technol Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Guangdong Prov Key Lab Tech & Equipment Macromol A Guangzhou 510641 Guangdong Peoples R China South China Univ Technol Key Lab Autonomous Syst & Networked Control Minist Educ Guangzhou 510641 Guangdong Peoples R China

This paper addresses the issue of insufficient attention to multi-scale spatiotemporal features in gait recognition algorithms for indoor scenes by designing a GaitTS (Gait Temporal-Spatial) algorithm that fuses multi-scale temporal and spatial dimension features. The proposed GaitTS algorithm processes temporal features by aggregating multiple frames of temporal information. Enhancing attention is paid to spatial features of different human body parts by partitioning feature maps into different scales. The dual focus equips the network with stronger capabilities for recognizing global and multi-scale local features, thereby improving the recognition performance of the model. Experimental results are implemented on CASIA-B, CCPG and occCASIA-B datasets. The results demonstrate that the proposed GaitTS algorithm achieves average Rank-1 accuracies of 97.9%, 95.4%, and 85.7% under normal (NM), walking with a bag (BG), and wearing a coat or jacket (CL) conditions for CASIA-B dataset, respectively, outperforming the state-of-the-art methods.

关键词： Gait recognition Multi-scale features Identity recognition

来源：评论

学校读者我要写书评

暂无评论

Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 4213-4226页

作者： He, Lin Liang, Wenrui Plaza, Antonio South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China South China Univ Technol Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Guangzhou 510640 Peoples R China Minist Educ PRC Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Univ Extremadura Hyperspectral Comp Lab Caceres 10003 Spain

Over recent years, denoising diffusion probabilistic models (DDPMs) have received many attentions due to their powerful ability to infer data distribution. However, most of existing DDPM-based hyperspectral (HS) pansharpening methods over rely on local processing to perform recovery, which usually fails to reconcile global contextual semantics and local details in data. To address the issue, we propose a two-level semantic-driven diffusion method for HS pansharpening. In our method, we first extract semantics in two levels, where the low-level semantic not only leads the extraction of conditional details, but also supports the further semantic extraction while the high-level semantic is related to scene cognition. Then, the features from both the low-level and high-level semantics are conditionally injected to the denoising network to guide the high-resolution HS recovery. Experiments on multiple datasets verify the effectiveness of our method.

关键词： Semantics Pansharpening Noise reduction Feature extraction Noise Diffusion models Image restoration Decoding Cognition Training Diffusion model hyperspectral (HS) images pansharpening two-level semantics

来源：评论

学校读者我要写书评

暂无评论

Swift and Accurate Point Cloud Registration Using SGUformer

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Luo, Jiaxiang Dong, Duoqin Liu, Haiming South China Univ Technol Engn Res Ctr Minist Educ Precis Mfg Equipment Sch Automat Sci & Engn Guangzhou 510641 Peoples R China South China Univ Technol Key Lab Autonomous Syst & Networked Control Minist Educ Guangzhou 510641 Peoples R China South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China

Point cloud registration aims to find a rigid transformation that aligns two point clouds. Applications such as augmented reality (AR) and robot navigation often require real-time performance for point cloud registration algorithms. In this article, we propose SGUformer, a novel point cloud registration method that achieves fast alignment by redesigning the feature extraction pipeline and employing a lightweight global feature extraction framework. The gating mechanism is utilized, and local coordinates are embedded to enhance the representation of point-level features. To facilitate the extraction of global features, a Transformer with 3-D rotary position embedding (RoPE) is implemented, circumventing the need to compute relative position information, thereby improving computational efficiency. Furthermore, a part attention mechanism is designed to tackle outlier pollution issues. In the final registration stage, the registration results obtained from each patch pair, weighted by their respective confidence scores, are combined to vote and acquire a more robust final result. In the conducted experiment, the superior quality of features derived from the novel structure's feature extractor enabled our method to attain a better feature matching recall (FMR) in comparison to existing leading methodologies. Moreover, the implementation of the proposed registration method resulted in the highest recorded registration success rate, exceeding the second-best method by 0.8%. In addition, our approach demonstrated remarkable efficiency, being 26% faster than the alternative methods.

关键词： Feature extraction Point cloud compression Accuracy Transformers Data mining Three-dimensional displays Deep learning Attention mechanisms Robustness Real-time systems Gating mechanisms multilevel feature extraction part attention point cloud registration rotary position embedding (RoPE)

来源：评论

学校读者我要写书评

暂无评论

Learning Nonlinear Marine Predator Algorithm for Multi-objective Optimization of Setpoints in Wastewater Treatment Operations

Learning Nonlinear Marine Predator Algorithm for Multi-objec...

引用

Robotics, control and Automation (ICRCA), International Conference on

作者： Jiahua Liu Daoping Huang Yiqi Liu Key Laboratory of Autonomous Systems and Networked Control Ministry of Education the School of Automation Science & Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

The nitrogen removal in wastewater treatment plants (WWTPs) usually consumes a significant amount of energy, for example, oxygen injection. To reduce energy consumption while ensure the quality in the effluent of WWTPs, this paper proposes a control strategy based on the Multi-Objective Nonlinear Marine Predator Algorithm (MONMPA). First, to address the unacceptable energy consumption issue due to fixed setpoints in the wastewater treatment process, a multi-objective setpoint optimization scheme is proposed in this paper. Second, to deal with uncontrollable inflow disturbances and uncertainty, a predictive controller with feedforward compensation for inflow disturbances is adopted to further accurately track the optimized setpoints. Finally, the proposed control strategy is compared with other standard approaches, and experimental results showed the effectiveness and superiority of this strategy.

关键词： Energy consumption Uncertainty Simulation Optimization methods Effluents Prediction algorithms Nitrogen Wastewater treatment Standards Robots

来源：评论

学校读者我要写书评

暂无评论

Multimodal Industrial Anomaly Detection via Uni-Modal and Cross-Modal Fusion

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第6期21卷 5000-5010页

作者： Cheng, Hao Luo, Jiaxiang Zhang, Xianyong South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China South China Univ Technol Engn Res Ctr Precis Elect Mfg Equipments Minist Educ Guangzhou 510640 Peoples R China South China Univ Technol Key Lab Autonomous Syst & Networked Control Minist Educ Guangzhou 510640 Peoples R China Guangdong Polytech Normal Univ Sch Automat Guangzhou 510180 Peoples R China

Constructing comprehensive multimodal feature representations from RGB images (RGB) and point clouds (PT) in 2D-3D multimodal anomaly detection (MAD) methods is very important to reveal various types of industrial anomalies. For multimodal representations, most of the existing MAD methods often consider the explicit spatial correspondence between the modality-specific features extracted from RGB and PT through space-aligned fusion, while overlook the implicit interaction relationships between them. In this study, we propose a uni-modal and cross-modal fusion (UCF) method, which comprehensively incorporates the implicit relationships within and between modalities in multimodal representations. Specifically, UCF first establishes uni-modal and cross-modal embeddings to capture intramodal and intermodal relationships through uni-modal reconstruction and cross-modal mapping. Then, an adaptive nonequal fusion method is proposed to develop fusion embeddings, with the aim of preserving the primary features and reducing interference of the uni-modal and cross-modal embeddings. Finally, uni-modal, cross-modal, and fusion embeddings are all collaborated to reveal anomalies existing in different modalities. Experiments conducted on the MVTec 3D-AD benchmark and the real-world surface mount inspection demonstrate that the proposed UCF outperforms existing approaches, particularly in precise anomaly localization.

关键词： Feature extraction Anomaly detection Image reconstruction Location awareness Training Benchmark testing Interference Inspection Informatics Fuses Anomaly localization industrial anomaly detection multimodal fusion unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards sludge bulking diagnosis via dynamic attention graph neural network

引用

JOURNAL OF WATER PROCESS ENGINEERING 2025年 69卷

作者： Chen, Yan Huang, Daoping Wu, Jing Fang, Gang Li, Yan Aman, Abid Liu, Yiqi South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Minist Educ Guangzhou 510640 Peoples R China South China Univ Technol Unmanned Aerial Vehicle Syst Engn Technol Res Ctr Sch Automat Sci & Engn Guangzhou 510640 Peoples R China Guizhou Minzu Univ Sch Data Sci & Informat Engn Guiyang 550025 Peoples R China

Sludge bulking is a critical issue in activated sludge-based wastewater treatment processes, leading to severe problems with solids settling that pose threats to environmental sustainability, public health, and economic efficiency. Existing traditional statistical models often struggle to identify early-stage sludge bulking due to their inability to dynamically account for variations in performance. To address these shortcomings, we propose a novel Dynamic Graph Convolutional Network (DA-GCN) enhanced with an attention mechanism that effectively detects incipient faults related to sludge bulking. This model utilizes graph structures to represent the complex interrelationships and temporal dynamics of time-series data, leveraging lagged observations to create adjacency matrices that reflect the system's behavior over time. By reconstructing node features through two-hop neighbor connections, the DA-GCN learns to identify key dependencies, and the application of attention mechanisms helps prioritize significant relationships, which improves the detection of subtle faults often masked by noise. We validate the effectiveness of this approach using the Benchmark Simulation Model No. 2 (BSM2) to simulate various sludge bulking scenarios, as well as data from a real-world wastewater treatment plant experiencing these challenges. Experimental findings demonstrate that the DA-GCN outperforms traditional models in managing dynamic data, presenting a reliable and innovative tool for the early diagnosis and classification of sludge bulking issues.

关键词： Graph convolutional network (GCN) Sludge bulking Fault diagnosis Attention mechanism Incipient faults

来源：评论

学校读者我要写书评

暂无评论

Compound Learning-Based Model Predictive control Approach for Ducted-Fan Aerial Vehicles

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2025年第5期36卷 9395-9407页

作者： Manzoor, Tayyab Pei, Hailong Xia, Yuanqing Sun, Zhongqi Ali, Yasir Zhongyuan Univ Technol Sch Automat & Elect Engn Zhengzhou Henan Peoples R China South China Univ Technol Unmanned Aerial Vehicle Syst Engn Technol Res Ctr Key Lab Autonomous Syst & Networked Control Sch Automat Sci & EngnMinist Educ Guangzhou 510640 Peoples R China Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Zhongyuan Univ Technol Zhengzhou 450007 Henan Peoples R China Silesian Tech Univ Fac Automat Control Elect & Comp Sci Joint Doctoral Sch Dept Telecommun & Teleinformat PL-44100 Gliwice Poland

Designing an efficient learning-based model predictive control (MPC) framework for ducted-fan unmanned aerial vehicles (DFUAVs) is a difficult task due to several factors involving uncertain dynamics, coupled motion, and unorthodox aerodynamic configuration. Existing control techniques are either developed from largely known physics-informed models or are made for specific goals. In this regard, this article proposes a compound learning-based MPC approach for DFUAVs to construct a suitable framework that exhibits efficient dynamics learning capability with adequate disturbance rejection characteristics. At the start, a nominal model from a largely unknown DFUAV model is achieved offline through sparse identification. Afterward, a reinforcement learning (RL) mechanism is deployed online to learn a policy to facilitate the initial guesses for the control input sequence. Thereafter, an MPC-driven optimization problem is developed, where the obtained nominal (learned) system is updated by the real system, yielding improved computational efficiency for the overall control framework. Under appropriate assumptions, stability and recursive feasibility are compactly ensured. Finally, a comparative study is conducted to illustrate the efficacy of the designed scheme.

关键词： Aerial robots machine learning (ML) model predictive control (MPC) reinforcement learning (RL) unmanned aerial vehicles (UAVs) Aerial robots machine learning (ML) model predictive control (MPC) reinforcement learning (RL) unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming for Optimal control of Unknown LTI System via Interval Excitation

引用

IEEE Transactions on Automatic control 2025年

作者： Ma, Yong-Sheng Sun, Jian Xu, Yong Cui, Shi-Sheng Wu, Zheng-Guang The National Key Lab of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing100081 China The Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

This paper investigates the optimal control problem for an unknown linear time-invariant (LTI) system. To solve this problem, a novel composite policy iteration (CPI) algorithm based on adaptive dynamic programming is developed to adaptively learn the optimal control policy from system data. The existing methods require the initial stabilizing control policy, the persistence of excitation (PE) condition and the data storage to ensure the algorithm convergence. Fundamentally different from them, these restrictions can be relaxed in the proposed method. Specifically, an adaptive parameter is elaborately designed to remove the requirement of the initial stabilizing control policy. Besides, an online data calculation scheme is proposed, which can not only replace the stored historical data by online data, but also can relax the PE condition to the interval excitation (IE) condition. The simulation results demonstrate the efficacy of the proposed algorithm, and its superiority is also demonstrated by comparing it with existing algorithms. © 1963-2012 IEEE.

关键词： Dynamic programming

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：