检索结果-内蒙古大学图书馆

Transmission-Constrained Consensus Over Random Graphs

IEEE TRANSACTIONS ON CYBERNETICS 2024年第5期54卷 3265-3274页

作者： Wang, Xiaotian Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

The exchange of information is a crucial factor in achieving consensus among agents. However, in real-world scenarios, nonideal information sharing is prevalent due to complex environmental conditions. Consider the information distortions (data) and stochastic information flow (media) during state transmission both caused by physical constraints, a novel model of transmission-constrained consensus over random networks is proposed in this work. The transmission constraints are represented by heterogeneous functions that reflect the impact of environmental interference in multiagent systems or social networks. A directed random graph is applied to model the stochastic information flow where every edge is connected probabilistically. Using stochastic stability theory and the martingale convergence theorem, it is demonstrated that the agent states will converge to a consensus value with probability 1, despite information distortions and randomness in information flow. Numerical simulations are presented to validate the effectiveness of the proposed model.

关键词： Stochastic processes Social networking (online) Interference Convergence Information exchange Multi-agent systems Image edge detection Almost surely convergence multiagent system (MAS) random networks transmission constraint

来源：评论

学校读者我要写书评

暂无评论

DR-CIML: Few-shot Object Detection via Base Data Resampling and Cross-iteration Metric Learning

引用

APPLIED ARTIFICIAL INTELLIGENCE 2023年第1期37卷

作者： Cao, Guoping Zhou, Wei Yang, Xudong Zhu, Feijia Chai, Lin Southeast Univ Sch Automation Key Lab Measurement & Control Complex Syst Engn Nanjing Peoples R China Sun Yat sen Univ Sch Intelligent Syst Engn Shenzhen Peoples R China Walvis Intelligent Technol Co Ltd Shenzhen R&D Ctr Nanjing Peoples R China Southeast Univ Sch Automation Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Peoples R China

Aiming at the problems of difficult data collection and labor-intensive manual annotation, few-shot object detection (FSOD) has gained wide attention. Although current transfer-learning-based detection methods outperform meta-learning-based methods, their data organization fails to fully utilize the diversity of the source domain data. In view of this, Data Resampling (DR) organization is proposed to fine-tune the network, which can be employed as a component of any model and dataset without additional inference overhead. In addition, in order to improve the generalization of the model, a Cross-Iteration Metric-Learning (CIML) branch is embedded in the few-shot object detector, thus actively improving intra-category feature propinquity and inter-category feature discrimination. Our generic DR-CIML approach obtained competitive scores in extensive comparative experiments. The nAP50 performance on PASCAL VOC improved by up to 6.3 points, and the bAP50 performance reached 81.0, surpassing the base stage model (80.8) for the first time. The nAP75 performance on MS COCO improved by up to 1.6 points.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Consensus-Based Time Synchronization Using Bayesian Estimation in Wireless Sensor Networks Under Communication Delays

引用

IEEE SYSTEMS JOURNAL 2023年第2期17卷 3332-3342页

作者： Wang, Heng Zhang, Ning Chen, Xinping Li, Min Chongqing Univ Posts & Telecommun Key Lab Ind Internet Things & Networked Control Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Coll Automation Chongqing Peoples R China

Time synchronization is crucial for various applications in wireless sensor networks. Consensus-based time synchronization is an essential distributed strategy for its high precision, robustness, and scalability. In practical networks, however, communication delays are not ignorable and make time messages received inaccurate, which is the fundamental limitation for time synchronization. It was pointed out that if a consensus-based time synchronization algorithm does not consider the influence of delays, it may be divergent under the scenario with delays. Making use of the knowledge of statistical signal processing to develop an efficient relative skew estimator is a viable method to restrain communication delays. In this article, we propose a relative skew estimator based on Bayesian estimation theory to counteract the impact of time delays, which improves the estimation accuracy while reducing the memory requirement. By applying the presented estimator to average consensus protocol, precise network-wide synchronization is achieved in the presence of delays. In addition, the proof of convergence of the proposed scheme is given by theoretical analysis. Simulation results demonstrate the effectiveness of the proposed scheme and show that our algorithm outperforms other similar algorithms in terms of synchronization accuracy under random delays.

关键词： Bayesian estimation communication delays consensus time synchronization wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Tuning Decision-Making Model Using Multi-Feature Fusion

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2023年第2期70卷 601-605页

作者： Guo, Linwei Cao, Weihua Bi, Leyu Hu, Wenkai Yuan, Yan Wu, Min China Univ Geosci Sch Automation Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automation Wuhan 430074 Peoples R China Minist Educ Engn Res Ctr Intelligent Technol Geoexplorat Wuhan 430074 Peoples R China

Dielectric Filters (DFs) are tuned to meet the requirements of 5G communication systems. The tuning methods based on Tuning Decision-Making Models (TDMMs) are efficient. However, how to build TDMMs accurately and fast is rather difficult due to the complex performance representation and the poor consistency of DFs. In this brief, a dynamic tuning decision-making model using multi-feature fusion is proposed. The contributions of this brief are as follows: 1) For the problem of incomplete feature representation of DFs performance, the multiple features are fused to improve the accuracy of TDMMs;2) to deal with the problem that high-quality samples are challenging to obtain, a guided sampling method is designed to determine the sampling range, driven by the characteristics of DFs;3) to solve the problem of inefficient modeling for inconsistent DFs, TDMMs are built dynamically using transfer learning. Finally, the excellent performance of the proposed method is demonstrated through comparative simulations.

关键词： Tuning Feature extraction Dielectrics Decision making Training Permittivity Computational modeling Dielectric filters decision-making models sampling multi-feature fusion dynamic modeling

来源：评论

学校读者我要写书评

暂无评论

Are edger rolls useful to control the plate motion and camber in a reversing rolling mill?

引用

JOURNAL OF PROCESS control 2022年 114卷 71-81页

作者： Pietschnig, Christopher Steinboeck, Andreas Kugi, Andreas TU Wien Automat & Control Inst Christian Doppler Lab Model Based Proc Control Ste Gusshausstr 27-29 A-1040 Vienna Austria TU Wien Automation & Control Inst Gusshausstr 27-29 A-1040 Vienna Austria

In heavy-plate hot rolling, reversing rolling mills are typically used to reduce the thickness of steel slabs. Some reversing rolling mills are equipped with edger rolls to control the width of the rolled plate. At best, the straight plate centerline coincides with the lateral centerline of the rolling mill and the desired rectangular shape is exactly realized. In reality, lateral asymmetries like temperature gradients and thickness inhomogeneities cause a lateral movement, a camber, and a wedge-shaped cross section of the plate. These effects can reduce the product quality and entail collisions with the mill stand or other equipment along the roller table. To prevent this, active control of the lateral position and contour shape is desirable. In this work, a roughing mill where the roll gap adjustment is self-retaining, meaning that it can only be adjusted between rolling passes, is considered. As a control input during the rolling passes, the lateral position of the edger rolls is exploited. A mathematical model for both the lateral motion and the resulting shape of the plate is derived. The model is validated by measurement data recorded in an industrial plant. Based on the validated model, the question if edger rolls are useful to control the plate motion and shape is discussed. A two-degrees-of-freedom control concept composed of an optimization-based feedforward controller and a proportional feedback controller with Smith predictor is derived for the lateral motion and shape. The performance of the proposed control concept is demonstrated in simulation studies based on the validated model. (c) 2022 The Author(s). Published by Elsevier Ltd.

关键词： Heavy-plate hot rolling Roughing mill with edger rolls Steel industry Model-based control Camber control Optimal control

来源：评论

学校读者我要写书评

暂无评论

Consensus of interconnected systems via event-triggered control with different cyber-physical topologies

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR control 2023年第12期33卷 6950-6968页

作者： Yu, Guan-Nan Xiao, Jiang-Wen Liu, Xiao-Kang Zeng, Ze-Hong Wang, Yan-Wu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Wuhan Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

In this paper, the consensus problem for a class of interconnected systems with different cyber-physical topologies is investigated. A two-layer control framework is proposed where two different connections exist among the systems in physical and cyber layers, respectively. The former directly reflects the physical coupling among systems, while the latter uses the states' information transferred by communication channels to generate control. The physical and cyber topologies are undirected and not required to be connected. An event-triggered protocol based on cyber local sampled information is designed with no need to solve any matrix equation or inequality. Theoretical sufficient conditions for consensus are derived in terms of algebraic inequality and Zeno behavior is excluded. A novel expandable construction scheme is proposed to construct switching topologies for cyber layer. Numerical simulation and comparison show the effectiveness of the proposed control method and the advantage on saving communication network constructions.

关键词： consensus cyber-physical framework event-triggered control interconnected system jointly connected topology

来源：评论

学校读者我要写书评

暂无评论

Norm-free adaptive event-triggering rule for distributed control of multiagent systems

引用

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE 2023年第4期54卷 791-801页

作者： Kurtoglu, Deniz Yucelen, Tansel Ristevski, Stefan Muse, Jonathan. A. A. Univ S Florida Dept Mech Engn Tampa FL USA Combine Control Syst AB Control & Automation Lund Sweden Wright patterson AFB Air Force Res Lab Dayton OH USA Univ S Florida Lab Auton Control Informat & Syst LACIS Tampa FL 33620 USA Univ S Florida Dept Mech Engn Tampa FL 33620 USA

We focus on reducing agent-to-agent information exchange in distributed control of multiagent systems. Specifically, our contribution is a norm-free and adaptive event-triggering rule for each agent, where it is decentralised and predicated on the solution-predictor curve method. The decentralised feature means that the proposed event-triggering rule depends on the own error signals of an agent without requiring any neighbouring or global information. The norm-free feature means that the left-hand side of the proposed event-triggering rule inequality does not depend on distances such as absolute values of error signals to allow for better agent-to-agent information exchange reduction. To achieve both decentralised and norm-free features together, an adaptive term is utilised in the event-triggering rule for each agent to estimate unknown variable unavailable to an agent. Here, the presented system-theoretical analysis of the proposed event-triggering rule holds for both the sampled data exchange case and the data exchange case predicated on the solution-predictor curve method. In contrast to standard sampled data exchange, the solution-predictor curve method has the ability to further reduce agent-to-agent information exchange, where each agent stores this curve and exchanges its parameters when an event occurs in a distributed manner for approximating the solution trajectory of each agent.

关键词： Multiagent systems distributed control event-triggering adaptive control

来源：评论

学校读者我要写书评

暂无评论

Scenarios Engineering: Enabling Trustworthy and Effective AI for Autonomous Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第5期8卷 3205-3210页

作者： Li, Xuan Wang, Fei-Yue Peng Cheng Lab Dept Math & Theories Shenzhen 518055 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The first journal impact factor (IF) of IEEE TIV is 5.009 with a CiteScore = 10.9 in 2022, signifying a promising start for our periodical. By April 2023, our real-time IF stands at 7.03 according to Web of Science, and CiteScore from Elsevier is 11.6. These numbers indicate that IEEE TIV is among the top-tier publications in the related fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Integral Terminal Sliding Mode control to Improve Maneuverability of Electric Vehicle Considering Rollover and Inputs Saturation

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第2期11卷 6012-6024页

作者： Liang, Zhongchao Gao, Qingyang Shen, Mingyu Liu, Jian Gao, Jinwu Hu, Yunfeng Zhao, Jing Northeastern Univ Sch Mech Engn & Automation Shenyang 110819 Peoples R China Natl Key Lab Automot Chassis Integrat & Bion Changchun 130025 Peoples R China Jilin Univ Dept Control Sci & Engn Changchun 130012 Peoples R China

As vehicles approach or exceed safety thresholds, their dynamics may deteriorate, potentially causing rollovers. In such circumstances, control inputs frequently encounter saturation. This article concentrates on enhancing vehicle maneuverability and preventing rollovers under input saturation constraints. A composite control structure is established to address saturation situations when control inputs approach or reach their unknown boundaries, ensuring improved control performance. Specifically, an adaptive integral terminal sliding mode controller, combined with a torque distribution strategy, is designed to align the controlled vehicle with a reference model while managing input saturation. Furthermore, an active suspension system is implemented to stabilize load transfer effects and prevent rollovers. The proposed control strategy are validated through hardware-in-the-loop (HiL) tests. Specifically, in the fishhook test and the S-curve test, the mean square errors (mse) of the difference between the ideal value and the yaw rates are 6.852E-4 and 6.464E-4, respectively. Additionally, the load transfer ratios (LTRs) mse are 1.970E-3 and 1.940E-3. These results indicate that the AITSMC protocol consistently outperforms conventional controllers.

关键词： Tires Rollover Force Sliding mode control Protocols Wheels Roads Perturbation methods Mathematical models Couplings Input saturation integral terminal sliding mode control maneuverability improvement rollover prevention

来源：评论

学校读者我要写书评

暂无评论

Efficient Mobile Deployment of Lightweight CNN-Transformer Model for Crop Disease Diagnosis in Smart Agriculture 4

Efficient Mobile Deployment of Lightweight CNN-Transformer M...

引用

4th Asia Conference on Information Engineering, ACIE 2024

作者： Lv, Zirong China University of Geosciences Hubei Key Lab. of Adv. Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation Wuhan China

ISBN: (纸本)9798350371925

Crop disease diagnosis is of great significance for crop yield and agricultural production. Deep learning methods have become a major research direction for solving crop disease diagnosis. However, recent studies have shown that deploying complex neural network models on mobile devices poses a significant challenge to mobile hardware performance. To address this issue, this paper proposes a lightweight network model based on the Transformer and deploys it on mobile devices. Compared to other lightweight network models, our approach significantly reduces computational complexity using Transformer modules and exhibits a particular advantage in recognition accuracy. It achieves a recognition rate of 97.76% for ten categories of tomato diseases, while the model size is only 3.86 MB. Furthermore, we deploy the model on embedded devices and apply it to tomato crop recognition, enabling farmers to monitor crop conditions in real-time and realizing smart agriculture. © 2024 IEEE.

关键词： Deep learning

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：