检索结果-内蒙古大学图书馆

A New Parameter Tuning Method for Generalized Multiresonant Current controllers in Grid-Connected Inverters

IEEE TRANSACTIONS ON POWER ELECTRONICS 2024年第9期39卷 10962-10975页

作者： Ye, Jie Huang, Songtao Huang, Yukai Hu, Yihua Zhang, Chen Xu, Jinbang Shen, Anwen Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Peoples R China Kings Coll London Dept Engn London WC2R 2LS England Huazhong Univ Sci & Technol China EU Inst Clean & Renewable Energy Wuhan 430074 Peoples R China

Multiresonant controllers are widely used in the current control of grid-connected converters due to their accurate tracking of reference sinusoidal signals containing high harmonic counts. However, the performance of multiresonant controllers relies heavily on the suitability of the parameter design. In this paper, a generalized multiresonant controller that unifies various existing resonant controllers is proposed, which achieves the decoupling of the proportional terms, eliminates the need for online operation of trigonometric functions, and obtains a more extensive range of regulation capability. Furthermore, a new multioptimized parameter tuning method that considers several performance indexes is proposed to utilize the generalized resonant controller's performance fully. Finally, based on the proposed method, a generalized multiresonant controller is designed for L-type and LCL-type grid-connected inverters, respectively, demonstrating the universality of the proposed approach. Simulation and experimental results validate the effectiveness of the proposed method.

关键词： Inverters Tuning Design methodology Current control Computational modeling Stability analysis Reviews generalized multi-resonant controller (RC) grid-connected inverter (GCI) parameter tuning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Load Frequency control of Multi-Area Power Systems: Recent Challenges and Strategies

引用

ENERGIES 2023年第5期16卷 2323页

作者： Liu, Xinghua Qiao, Siwei Liu, Zhiwei Xian Univ Technol Sch Elect Engn Xian 710048 Peoples R China Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Load frequency control (LFC) is well known for balancing the load demand and frequency for a multi-area power system. Studies have proven that LFC can improve the global performance of multi-area power systems. In recent years, the increasing proportion of renewable energy, integration of EVs, and cyber-attacks have become the main challenges in LFC power systems. Different strategies have been applied in the literature for LFC power systems and the possible impacts of renewable energy, EVs, and cyber-attacks. This survey paper is devoted to the research on directions in LFC multi-area power systems. The mathematical model of recent challenges in LFC multi-area power systems is summarized and the similarities and differences of these challenges are analyzed. The uncertainty of renewable energy is a frequently noted issue in LFC power systems;however, the uncertainty that exists in controller design is often ignored. In this survey, we analyze methods for treating the uncertainty of renewable energy and controller. This survey paper introduces the most recent research on LFC and acquaints anyone interested in its development, such that the most effective strategies can be developed by the researchers.

关键词： power system LFC renewable energy cyber-attacks sliding mode control data-driven

来源：评论

学校读者我要写书评

暂无评论

Proximal nested primal-dual gradient algorithms for distributed constraint-coupled composite optimization

引用

APPLIED MATHEMATICS AND COMPUTATION 2023年第1期444卷

作者： Li, Jingwang An, Qing Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Luoyu Rd 1037 Wuhan 430074 Peoples R China Wuchang Univ Technol Articial Intelligence Sch Wuhan 430223 Peoples R China

In this paper, we study a class of distributed constraint-coupled optimization problems, where each local function is composed of a smooth and strongly convex function and a convex but possibly non-smooth function. We design a novel proximal nested primal-dual gradient algorithm (Prox-NPGA), which is a generalized version of the exiting algorithm- NPGA. The convergence of Prox-NPGA is proved and the upper bounds of the step-sizes are given. Finally, numerical experiments are employed to verify the theoretical results and compare the convergence rates of different versions of Prox-NPGA.(c) 2022 Elsevier Inc. All rights reserved.

关键词： Constraint-coupled optimization Non-smooth function Proximal operator Primal-dual gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Class-Agnostic Motion Prediction with Pseudo label Regeneration and BEVMix 38

Semi-supervised Class-Agnostic Motion Prediction with Pseudo...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Wang, Kewei Wu, Yizheng Pan, Zhiyu Li, Xingyi Xian, Ke Wang, Zhe Cao, Zhiguo Lin, Guosheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Key Lab Image Proc & Intelligent Control Wuhan Peoples R China Nanyang Technol Univ S Lab Singapore Singapore SenseTime Res Hong Kong Peoples R China

ISBN: (纸本)1577358872

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and regenerates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://***/kwwcv/SSMP.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Space Decoupled Prototype Learning for Few-Shot Attack Detection in Cyber-Physical Systems

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第10期20卷 12350-12362页

作者： Sun, Haili Huang, Yan Zhou, Chunjie Han, Lansheng Liu, Hongle Chen, Juan Li, Xin Huazhong Univ Sci & Technol Hubei Engn Res Ctr Big Data Secur Sch Cyber Sci & Engn Hubei Key Lab Distributed Syst Secur Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China

Due to the lack of effective attack detection measures, cyberattacks may cause strong damage to industrial cyber-physical systems (CPSs). The embedding of attack categories learned by the existing attack detection methods is highly coupled to each other with fuzzy boundaries and overlapped neighborhood, leading to weak robustness and high false positive rates. To address these issues, in this article, we propose a few-shot attack detection method based on decoupled prototype learning (DPL-FSAD), aiming to enhance the detection accuracy and generalization capabilities for malicious attacks in CPS. Specifically, we first introduce feature contrastive learning to extract differentiated features from highly similar samples, achieving compact intraclass and sparse interclass feature embedding space. To solve the problem of fuzzy boundaries of different attack categories, prototype contrastive learning is then employed to reduce the coupling degree among prototypes and enhance their discriminability. A regularization term is exploited to mitigate the overfitting problem by reducing the gap between the feature embedding and prototypes. Furthermore, an orthogonal constraint is employed to separate prototypes of different attack types, generating a decoupled prototype embedding space. The experimental results on three public cyberattack datasets show that, compared with the suboptimal model a few-shot learning model with Siamese convolutional neural network (FSL-SCNN), the proposed DPL-FSAD can improve the precision by 5.53%, F1-score by 3.3%, and reduce the false positive rate by 2.37% in average, which proves that the space decoupled prototype learning is effective for improving the generalization and robustness of industrial CPS attack detection in few-shot scenario.

关键词： Prototypes Feature extraction Couplings Task analysis Sun Contrastive learning Mutual information Few-shot learning (FSL) industrial cyber-physical system (CPS) network attack detection prototype contrastive learning (PCL) space decoupling

来源：评论

学校读者我要写书评

暂无评论

Model-Free Event-Triggered Consensus Algorithm for Multiagent Systems Using Reinforcement Learning Method

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2022年第8期52卷 5212-5221页

作者： Long, Mingkang Su, Housheng Zeng, Zhigang 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

In this article, we study the consensus issues of multiagent systems (MASs) without any information of the system model by using the reinforcement learning (RL) method and event-based control strategy. First, we design an adaptive event-based consensus control protocol using the local sampled state information so that the consensus errors of all agents are uniformly ultimately bounded. The validity of the above event-triggered adaptive control protocol is confirmed by excluding the Zeno behavior within finite time. Then, based on the RL approach, we present a model-free algorithm to get the feedback gain matrix, and accomplish constructing the adaptive event-triggered control strategy without the knowledge of model information. Distinct with the existing related works, this RL-based event-triggered adaptive control algorithm only relies on the local sampled state information, irrelevant to any model information or global network information. Finally, we provide some examples to demonstrate the validity of the above adaptive event-based consensus algorithm.

关键词： Adaptation models Consensus algorithm Heuristic algorithms Protocols Computational modeling Multi-agent systems Adaptive control Consensus event triggered model-free algorithm multiagent systems (MASs) reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Predictor-Based Extended State Observer for Disturbance Rejection control of Multirate Systems With Measurement Delay

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第3期70卷 3003-3012页

作者： Sun, Jiankun Liu, Xiangyang Yang, Jun Zeng, Zhigang Li, Shihua Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan Peoples R China Key Lab Image Proc & Intelligent Control Educ Mini Wuhan 430074 Peoples R China Southeast Univ Sch Automat Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Peoples R China Loughborough Univ Dept Aeronaut & Automot Engn Leicestershire LE11 3TU England

This article investigates the multirate disturbance rejection control problem for linear control systems with mismatched disturbance and measurement delay using predictor-based extended state observer. A new extended state observer together with output predictor is first designed to obtain the estimation values of system state and mismatched disturbance, where output predictor is used to compensate the influences of measurement delay and sampling of output. To attenuate the undesirable influence of mismatched disturbance, we then design a new sampled-data robust controller with disturbance compensation, and the updating rate of the proposed controller is allowed to be different from that of the sensor. Thanks to prediction and disturbance/uncertainty estimation and attenuation techniques, the disturbance rejection property of the resultant closed-loop control systems is enhanced despite the multirate and measurement delay. Some sufficient conditions are presented to ensure the stability property of the resultant control systems. We finally consider the application of the visual servoing control system for an inertially stabilized platform, and the experiment results verify superiorities of the predictor-based disturbance rejection control method proposed in the article.

关键词： Disturbance/uncertainty estimation and attenuation (DUEA) measurement delay predictor-based ex-tended state observer sampled-data control

来源：评论

学校读者我要写书评

暂无评论

Unsupervised image Translation with GAN Prior 5th

Unsupervised Image Translation with GAN Prior

引用

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Tu, Pengqi Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

ISBN: (纸本)9783031189067;9783031189074

Unsupervised image translation aims to learn the translation between two domains without paired data. Although impressive progress has been made in recent years, existing methods are difficult to build mapping between domains with drastic visual discrepancies. In this paper, we propose a novel framework for unsupervised image translation with large discrepancies. The key insight is to leverage the generative prior from pretrained GANs for the target domain (e.g., StyleGAN), to learn rich prior information of the target domain. We propose a two-stage framework, the GAN of the target domain is pretrained to obtain the prior information in the first stage, the pretrained GAN for the target domain is embedded as the decoder of the translation network and the translation network is trained with the guidance of the prior information in the second stage. Experimental results show the superiority of our method compared to the existing state-of-the-art methods for the translation between challenging and distant domains.

关键词： image translation Generative prior Two-stage

来源：评论

学校读者我要写书评

暂无评论

Siamese Tracking with Bilinear Features 1

引用

6th Asian Conference on Pattern Recognition (ACPR)

作者： Pi, Zhixiong Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

ISBN: (数字)9783031024443

ISBN: (纸本)9783031024443;9783031024436

Bilinear features arise in fine-grained visual recognition. They are advantageous to encode detailed representations and attributes to differentiate visually similar objects. The apparent similarity is challenging in visual tracking where background distractors interfere siamese trackers to localize the target object. Especially when distractors and the target belong to the same object category. To increase the discrimination between similar appearance objects, we propose an efficient bilinear encoding method for siamese tracking. The proposed method consists of a self-bilinear encoder and an cross-bilinear encoder. The bilinear features generated via the self-bilinear encoder and the cross-bilinear encoder represent target variations itself and target distractor difference, respectively. To this end, the proposed bilinear encoders advance siamese trackers to capture target appearance variations while differentiating the target and background distractors. Experiments on the benchmark datasets show the effectiveness of bilinear features. Our tracker performs favorably against state-of-the-art approaches.

关键词： Siamese network Bilinear feature Visual tracking

来源：评论

学校读者我要写书评

暂无评论

User Identity Protection in EEG-Based Brain–Computer Interfaces

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2023年 31卷 3576-3586页

作者： Meng, Lubin Jiang, Xue Huang, Jian Li, Wei Luo, Hanbin Wu, Dongrui Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Belt & Rd Joint Lab Measurement & Control Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China

A brain-computer interface (BCI) establishes a direct communication pathway between the brain and an external device. Electroencephalogram (EEG) is the most popular input signal in BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals;however, EEG signals also contain rich private information, e.g., user identity, emotion, and so on, which should be protected. This paper first exposes a serious privacy problem in EEG-based BCIs, i.e., the user identity in EEG data can be easily learned so that different sessions of EEG data from the same user can be associated together to more reliably mine private information. To address this issue, we further propose two approaches to convert the original EEG data into identity-unlearnable EEG data, i.e., removing the user identity information while maintaining the good performance on the primary BCI task. Experiments on seven EEG datasets from five different BCI paradigms showed that on average the generated identity-unlearnable EEG data can reduce the user identification accuracy from 70.01% to at most 21.36%, greatly facilitating user privacy protection in EEG-based BCIs.

关键词： Brain-computer interfaces machine learning privacy protection

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：