检索结果-内蒙古大学图书馆

Point-Based Stabilization control of Linear Parabolic Partial Differential Equation Systems on Space-Time Scales

IEEE TRANSACTIONS ON AUTOMATIC control 2025年第4期70卷 2552-2559页

作者： Wan, Peng Zeng, Zhigang Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Engn Res Ctr Met Automat & Measurement Technol Wuhan 430081 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

The extensively studied partial differential equation (PDE) systems evolve on continuous time and continuous space, which restricts the investigation scope of PDE systems. A parabolic PDE system on space-time scales is constructed for the first time. This article focuses on global exponential stabilization (GES) of a linear parabolic PDE systems on space-time scales by using point-based collocated and noncollocated observations. First, we give the definitions of space-time scales, which contain four cases: continuous time and continuous space, continuous time and discrete space, discrete time and continuous space, and discrete time and discrete space. Wirtinger inequality on space scales is demonstrated, which provides mathematically analytical technique for PDE systems on space-time scales. Second, point-based collocated stabilization control strategy is developed for parabolic PDE systems on space-time scales. Third, considering the fact that sensors and actuators are always placed at different locations, a noncollocated point-based feedback controller is designed by using the observer estimation states. Different from the existing literature, the spatial domain does not need to be divided again according to the actuator and sensor locations. By using the Lyapunov function method, calculus on space-time scales, integration by parts, and Wirtinger inequality on space scales, sufficient criteria are developed such that the closed-loop systems can achieve GES. Finally, numerical simulation examples are presented to show the effectiveness of the developed point-based controllers.

关键词： Aerospace electronics Sensors Actuators Observers Germanium Vectors Symmetric matrices Linear matrix inequalities Adaptive control Sensor systems Noncollocated observation observer partial differential equation (PDE) point-based control space-time scales

来源：评论

学校读者我要写书评

暂无评论

Multispectral Semantic Land Cover Segmentation From Aerial imagery With Deep EncoderDecoder Network

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Liu, Chengxin Du, Shuaiyuan Lu, Hao Li, Dehui Cao, Zhiguo Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

Developing accurate algorithms for agricultural pattern recognition from aerial imagery has become increasingly important due to the prevalence of unmanned aerial vehicles (UAVs). This letter introduces a deep encoderx2013;decoder network for semantic land cover segmentation, where the goal is to classify six anomaly categories from multispectral aerial imagery. Since aerial imagery exhibits specific characteristics and visual challenges in this imaging domain, existing semantic segmentation models are not plug-and-play. Starting from a state-of-the-art segmentation model, we present a step-by-step analysis of key challenges and also reveal our observations in addressing these challenges. In particular, we investigate on how to exploit data prior knowledge, how to deal with sample imbalance, and how to encode global semantic and contextual information to improve segmentation. Experiments on a recent large-scale aerial land cover data set demonstrate that our method achieves compelling performance against other state-of-the-art approaches. Our results and insights can provide references for practitioners working in this field when dealing with similar segmentation problems.

关键词： image segmentation Semantics Training Convolution Decoding Agriculture Measurement Aerial imagery class imbalance context encoding convolutional neural network (CNN) semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Editorial: Distributed learning, optimization, and control methods for future power grids

引用

FRONTIERS IN ENERGY RESEARCH 2023年 11卷

作者： Liu, Zhi-Wei Liu, Xiao-Kang Yan, Jun Deng, Chao Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan Peoples R China Concordia Univ Concordia Inst Informat Syst Engn Montreal PQ Canada Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing Peoples R China

The development of renewable energy sources makes an important contribution to low-carbon sustainable ***, renewable energy such as wind and photovoltaic energy are highly random and intermittent, which brings great challenges to the operation and control of power networks. The traditional method is to build a large number of peak-shaving power stations and arrange a large number of energy storage devices to stabilize the fluctuations of renewable energy, and the cost may be prohibitive to be sustainable. In the future power network, advanced sensors, actuators, and communication equipment will be deployed on various systems such as generators, substations, transformers, distributed energy resources, air conditioners, and electric vehicles. A challengeable issue arises on how to manage these hundreds of millions of active endpoints. %power lines, Recently, distributed learning, optimization, and control methods for networked systems have received growing attention. Distributed learning, optimization, and control methods for managing hundreds of millions of active endpoints in the future power network are expected to enable a stable and economic operation of the power network with a high proportion of new energy, as illustrated in Fig. \ref{fig:illustration}.This issue contains nine research articles focusing on distributed control and optimization for power systems and smart power electronics, multi-agent reinforcement learning in power systems, advanced energy management and economic dispatch, *** paper by \href{https://***/articles/10.3389/fenrg.2022.1097319}{Ma et al.} proposes a multi-time-scale control method based on a deep Q network-deep deterministic policy gradient (DQN-DDPG) algorithm to maintain optimal voltage in distribution *** optimizes voltage regulation for longer times using the DQN algorithm and shorter times using the DDPG ***, based on the Markov decision process transformation, the design s

关键词： distributed learning distributed optimization distributed control data analytics microgrids demand response

来源：评论

学校读者我要写书评

暂无评论

Electric vehicle scheduling based on stochastic trip time and energy consumption

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2023年第1期177卷

作者： Shen, Yindong Li, Yuanyuan Chen, Chen Li, Jingpeng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan Peoples R China Univ Stirling Div Comp Sci & Math Stirling FK9 4LA Scotland

The vehicle scheduling problem (VSP) is profound in public transit planning. Especially electric VSP (EVSP) occupies a hot topic, as electric vehicles have enjoyed a fast-expanding market share in the bus market in recent years. It used to be solved regardless of the dreadful variability of traffic by setting the fixed trip times and further deterministic energy consumption, then the robustness of resulting schedules is compromised. Therefore, EVSP based on stochastic trip time and energy consumption is studied. We propose a probabilistic model for EVSP based on the probability density function (PDF) of trip time to minimize the fleet size and operating cost and maximize on-time performance. For modeling, we define the time compatibility and energy compatibility of trips by PDF. Based on the time compatibility, the lower bound of the fleet size is derived. As energy compat-ibility is a non-inherent attribute of trips, we next develop an adaptive large neighborhood search (ALNS) heuristic for EVSP. Experiments demonstrate that ALNS may considerably surpass the large neighborhood search algorithm for solving EVSP, and the probabilistic model may lead to more robust schedules without increasing fleet size.

关键词： Public transit Electric vehicle scheduling Stochastic trip time Stochastic energy consumption Adaptive large neighborhood search

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Scale Model for Medium-Term Load Forecasting 35

A New Multi-Scale Model for Medium-Term Load Forecasting

引用

35th Chinese control and Decision Conference (CCDC)

作者： Liu, Peng Fang, Hongliang Xiao, Jian-Wen Wang, Yan-Wu Liu, Xiao-Kang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

ISBN: (纸本)9798350334722

When a large number of distributed power and renewable energy are connected to the smart grid, the volatility and intermittency of renewable energy bring some challenges to the smart grid. Therefore, accurate medium-term load forecasting is essential because it is conducive to the stability of the power grid and can provide data support for the power generating plan. Many factors affect medium-term load forecasting and the real-time electricity price is a very important factor among them. In this paper, a multi-scale model based on LSTM model is proposed to extracts features from 3 different time scales including half-hourly time scale, daily time scale and monthly time scale. At first, the half-hourly data is processed by a half-hourly data processing layer to extract the half-hourly features. Then, its output is concatenated with the daily load data and is input into a daily data processing layer. Finally, the daily features are concatenated with the monthly load data and they are input into a monthly data processing layer to extract the monthly features and get the final forecasting results. The case study results demonstrate that the proposed multi-scale model has better performance than the single-scale models.

关键词： Deep learning medium-term load forecasting LSTM real-time electricity price

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based Robust control Against Quantified False Data Injection Attacks in Cyber-Physical Systems

引用

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1440-1450页

作者： Yue Zhao Ze Chen Chunjie Zhou Yu-Chu Tian Yuanqing Qin Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China School of Computer Science Queensland University of TechnologyBrisbane QLD 4001Australia

Secure control against cyber attacks becomes increasingly significant in cyber-physical systems(CPSs).False data injection attacks are a class of cyber attacks that aim to compromise CPS functions by injecting false data such as sensor measurements and control *** quantified false data injection attacks,this paper establishes an effective defense framework from the energy conversion ***,we design an energy controller to dynamically adjust the system energy changes caused by unknown *** designed energy controller stabilizes the attacked CPSs and ensures the dynamic performance of the system by adjusting the amount of damping ***,with the disturbance attenuation technique,the burden of control system design is simplified because there is no need to design an attack *** addition,this secure control method is simple to implement because it avoids complicated mathematical *** effectiveness of our control method is demonstrated through an industrial CPS that controls a permanent magnet synchronous motor.

关键词： Cyber-physical systems energy controller energy conversion false data injection attacks L2 disturbance attenuation technology

来源：评论

学校读者我要写书评

暂无评论

Performance analysis and multi-objective optimization of a hybrid system combining reversible solid oxide cell and direct contact membrane distillation

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 327卷

作者： Xu, Sheng Huo, Haibo Zhu, Hongxiang Xu, Kui Lei, Zhengling Xu, Jingxiang Li, Xi Shanghai Ocean Univ Coll Engn Sci & Technol Shanghai Engn Res Ctr Marine Renewable Energy Shanghai 201306 Peoples R China Harbin Engn Univ Coll Power & Energy Engn Harbin 150000 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc Intelligent & Control Educ Minist Wuhan 430074 Peoples R China

To meet the electricity, hydrogen, and freshwater demands of isolated island users, and coping with the intermittent and fluctuating nature of renewable energies, this paper proposes a hybrid system of combining a reversible solid oxide cell (rSOC) with direct contact membrane distillation (DCMD). The rSOC technology is used to achieve energy time-shifting. The waste heat from the operation of rSOC is recovered through DCMD to improve the system's overall performance and produce freshwater. A high-fidelity model of the rSOC-DCMD hybrid system is established and validated. Based on this model, a comprehensive sensitivity analysis including single-parameter sensitivity analysis, Spearman correlation analysis, and multi-parameter sensitivity analysis was performed. The analysis results indicate that current density is the critical factor influencing system performance while fuel utilization and fuel mole fraction primarily affect operating costs. The air excess ratio is crucial for optimizing system efficiency and freshwater productivity by balancing parasitic power and waste heat, however, adjusting the feed flow rate can further improve performance by regulating the temperature of the seawater entering the DCMD. Additionally, spearman correlation analysis further quantifies the conflicting relationship between any two of the performance indicators in the electrolysis cell/fuel cell (EC/FC) mode. In both modes, minimizing operating costs shows a weak conflict with maximizing system efficiency (correlation coefficient < 0.1) but a strong conflict with maximizing freshwater yield (correlation coefficient > 0.3). Through multi-objective optimization and optimal point decision-making, the optimal solution for three performance indicators is identified at each power level, ensuring optimal hybrid system operation under any condition. As a result, within the full power range of the EC/FC mode, the hybrid system can achieve average system efficiencies of 82.2 %/76.6 %, avera

关键词： Reversible solid oxide cell Direct contact membrane distillation Waste heat recovery Sensitivity analysis Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Class-attribute inconsistency learning for novelty detection

引用

PATTERN RECOGNITION 2022年 126卷 108582-108582页

作者： Du, Shuaiyuan Hong, Chaoyi Chen, Yinpeng Cao, Zhiguo Zhang, Ziming Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Worcester Polytech Inst Dept Elect & Comp Engn Worcester MA 01609 USA

In this paper, we address the problem of novelty detection whose goal is to recognize instances from unseen classes during testing. Our key idea is to leverage the inconsistency between class similarity and (latent) attribute similarity. We are motivated by the observation that a novel class may holistically appear like a certain known class (class-level reference) but often exhibits unique properties similar to others (attribute-level references). That is, the related class-and attribute-level references are often inconsistent for a novel class. A new two-stage Class-Attribute Inconsistency Learning network (CAILNet) is proposed to explore class-attribute inconsistency for novelty detection. Stage one aims to learn both class and attribute features based on the class labels and fake attribute labels, and stage two aims to search for the corresponding references and make fine-grained comparisons for final novelty decision. Empirically we conduct comprehensive experiments on three benchmark datasets, and demonstrate state-of-the-art performance. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Novelty detection Class-attribute inconsistency Class-level similarity Attribute-level similarity

来源：评论

学校读者我要写书评

暂无评论

Degree of Spiking Neural P Systems Without Delay

引用

Chinese Journal of Electronics 2023年第3期21卷 419-424页

作者： Keqin JIANG Xiaolong SHI Department of Control Science and Engineering Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China School of Computer and Information Anqing Teachers College Anqing China

Spiking neural P systems are a class of distributed parallel computing models inspired from the way neurons communicate with each other by means of electrical impulses (called “spikes”). In this paper, we continue the research of normal forms for spiking neural P systems. Specifically, we prove that the degree of spiking neural P systems without delay can be decreased to two without losing the computational completeness (both in the generating and accepting modes).

关键词： Computational modeling Neurons Parallel processing Delays

来源：评论

学校读者我要写书评

暂无评论

CondNet: Conditional Classifier for Scene Segmentation

引用

IEEE SIGNAL processing LETTERS 2021年 28卷 758-762页

作者： Yu, Changqian Shao, Yuanjie Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1 x 1 convolution) to recognize each pixel to a semantic label. We empirically show that this global classifier, ignoring the intra-class distinction, may lead to sub-optimal results. In this work, we present a conditional classifier to replace the traditional global classifier, where the kernels of the classifier are generated dynamically conditioned on the input. The main advantages of the new classifier consist of: (i) it attends on the intra-class distinction, leading to stronger dense recognition capability;(ii) the conditional classifier is simple and flexible to be integrated into almost arbitrary FCN architectures to improve the prediction. Extensive experiments demonstrate that the proposed classifier performs favourably against the traditional classifier on the FCN architecture. The framework equipped with the conditional classifier (called CondNet) achieves new state-of-the-art performances on two datasets. The code and models are available at https://***/CondNet.

关键词： Kernel Convolution Feature extraction Semantics Training Task analysis Aggregates Conditional classifier dynamic convolutions semantic segmentation

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：