检索结果-内蒙古大学图书馆

Cascading Failure Screening Based on Gradient Boosting Decision Tree for HVDC Sending-End systems with High Wind Power Penetration

引用

IEEE Transactions on Power systems 2025年

作者： Liu, Tianhao Yan, Jiongcheng Liu, Yutian Chung, Chi Yung Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Jinan China The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Kowloon Hong Kong

In LCC-HVDC sending-end AC systems, cascading failures combined with the dynamic response of wind turbines (WTs) can lead to HVDC commutation failures. The resulting transient voltage disturbances cause WT tripping in sending-end systems. Cascading failures that involve the interaction between WTs and HVDC significantly limit the wind power transmitted by HVDC systems. This paper proposes an online cascading failure screening method based on gradient boosting decision tree (GBDT) for HVDC sending-end systems with large-scale WTs. First, a confidence level-based WT tripping model is proposed for cascading failure risk assessment considering a typical cascading failure propagation pattern. Then, Monte Carlo tree search is improved using a contrastive pruning technique to generate evenly distributed samples of cascading failures offline. Dynamic insecure scenarios are quickly identified using an improved support vector machine. Finally, GBDT is utilized to screen for cascading failures online by predicting subsequent high-risk failures using operating features. A dynamic weighting technique is proposed for GBDT to improve the fault prediction accuracy. Simulation results of a modified New England test system and the Ningxia provincial power grid in western China demonstrate that the proposed method can quickly screen for cascading failures considering the dynamic interaction between WTs and HVDC. © 1969-2012 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

An Anti-Time Domain Impulse Interference Algorithm for Aviation Swarms Communication system

An Anti-Time Domain Impulse Interference Algorithm for Aviat...

引用

2022 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2022

作者： Shang, Yaobo Zhang, Dongwei Li, Zhe Liang, Xiaolong Ren, Baoxiang Air Force Engineering University Air Traffic Control and Navigation College Xi'an710051 China Shaanxi Key Laboratory of Meta-Synthesis for Electronic and Information System Xi'an710051 China

ISBN: (数字)9781665499910

ISBN: (纸本)9781665499910

Aiming at the problem of anti-impulse interference in aviation swarms communication system, a time-domain anti-impulse interference algorithm combining nonlinear filtering and interleaving coding is proposed. Firstly, the mathematical model of time-domain impulse interference is established by Middleton Class A model, and then the model is analyzed, and the signal processing methods such as limiting method, punching method and other nonlinear filtering methods are integrated, and the simplified method of channel measurement is obtained. Aiming at the problem of continuous errors caused by continuous pulse interference, a method combining channel coding and outer interleaving is proposed. This method turns continuous errors into random errors through interleaving and deinterleaving, and then uses channel decoding to complete information error correction. Through the analysis and numerical simulation of the demodulation performance of this algorithm, it is proved that it can significantly improve the anti-interference performance of aviation swarms communication system, and it is easy to realize and has good application value. © 2022 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Cooperative control Strategy for Virtual Inertia Based on Fuzzy control 8

Cooperative Control Strategy for Virtual Inertia Based on Fu...

引用

8th International Conference on control Science and systems engineering, ICCSSE 2022

作者： Gao, Zhimin Cao, Yongji Zhang, Hengxu Qin, Hao Zhang, Xiaoning Li, Changgang Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Shandong University Jinan China Technical University of Denmark Department of Electrical Engineering Kgs. Lyngby Denmark School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781665484138

The large-scale integration of renewable energies brings about low inertia characteristics to the power system, and the frequency security faces greater challenges. The existing inertia research lacks the synergy between different types of inertia sources and different control methods, and the inertia response capability of power system still can be improved. In this paper, with the aim of proposing a virtual inertia cooperative control strategy for the power system with high penetration of renewable energies, we analyze the virtual inertia mechanisms of wind power, PV units and energy storage system (ESS), and propose control methods for wind power and PV units to participate in inertia response. Considering the reason of limited inertia response capability of renewable energy units, the fuzzy control is used to make the ESS participate in inertia compensation to improve the frequency response capability. Finally, case study is carried out to verified the effectiveness of the proposed control strategy. © 2022 IEEE.

关键词： Fuzzy control

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

An Approach for Predicting and Compensating the End Deformation of a Heavy Load Robot for Friction Stir Welding 16th

An Approach for Predicting and Compensating the End Deformat...

引用

16th International Federation of Theory of Machines and Mechanisms World Congress, IFToMM WC 2023

作者： Bai, Yujie Liu, Haitao Meng, Shaofei Ma, Yue Yue, Wei Li, Guangxi Xiao, Juliang Wang, Guofeng Ding, Yabin Key Laboratory of Mechanism Theory and Equipment Design of State Ministry of Education Tianjin University Tianjin300072 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Dongguan University of Technology Dongguan523808 China

ISBN: (纸本)9783031457043

Aiming at solving the problem of insufficient plunge depth by the deformation of friction stir welding robots, this paper presents a method for predicting and compensating for the end deformation of friction stir welding robots. Firstly, the numerical model of FSW is established using DEFORM-3D software, then the axial force on the welding tool is obtained. Subsequently, the robot stiffness model is established based on the screw theory to realize the prediction of robot deformation in the workspace. Finally, a deformation compensation method based on the mirror principle is proposed to realize the compensation of the welding trajectory. Taking the 10 mm AA6061 aluminium alloy FSW as an example, the compensation method proposed in this paper is verified by using computer simulation. The results show that the stiffness model established in this paper can accurately predict the end deformation of the robot. The maximum plunge depth deviation of the compensation method proposed in this paper is reduced by 95.17% compared with the uncompensated case, which proves the effectiveness of the proposed compensation method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Friction stir welding

来源：评论

学校读者我要写书评

暂无评论

A Fault Diagnosis Method of Actuator via Single Class Probability Density Learning 18th

A Fault Diagnosis Method of Actuator via Single Class Prob...

引用

18th Chinese Intelligent systems Conference, CISC 2022

作者： Wang, Na Li, Yang Peng, Kun School of Control Science and Engineering Tiangong University Tianjin300387 China Tianjin Key Laboratory of Intelligent Control of Electrical Equipment University Tianjin300387 China Key Laboratory of low light level electromechanical system technology of Ministry of education Tianjin University Tianjin300387 China

ISBN: (纸本)9789811962028

A fault diagnosis method via Single Class Probability Density Learning for the actuator is proposed in this paper. Firstly, for the normal current data of the original actuator, the Fuzzy c-Means approach is combined with the matrix transformation. Then the Single Class Learning process is realized. Thus the distribution centers of the normal current data and the Probability Density control Threshold are obtained. On this basis, the fault diagnosis model is established. Secondly, for the actuator data to be tested, the Principal Component Analysis is adopted to reduce their dimension. Then the Affinity Propagation Clustering method is improved and the new centers of clustering are acquired by the test data. Additionally, the original distribution centers of current are compared with the new centers of clustering. So the actuator fault is diagnosed quickly. Finally, by some actuator measured data simulation, the effectivity of the proposed approach is verified in construct with the traditional methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Power Switching control Method of the Wind Power MPPT system Based on the Switching system Theory 24

A Novel Power Switching Control Method of the Wind Power MPP...

引用

24th International Electronics Symposium, IES 2022

作者： Guo, Xin Li, Wei-Peng Pan, Yuan Liu, Jun Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China Xi'an University of Technology School of Automation and Information Engineering Xi'an China

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

In order to effectively utilize the wind energy, the max power point tracking (MPPT) control method has been extensively used in the wind power system. The MPPT control in the wind power system is actually to control the power electronic converters connected with the wind turbine. However, due to the existing of the power switching devices, the converters were the typical nonlinear system. The traditional linearization modeling methods of the converters cannot represent the working process of the system accurately and the control strategies based on the linearization model of the converters only guarantee the satisfactory performance of system near the predefined working point. They were not suitable to the wind power MPPT system, which has the variable wind speeds and the variable max power points. This paper proposes a power switching control method based on a novel power switched model of the wind power MPPT system with Boost converter. The main contributions of the work are: (1) The proposed power switched model realizes the accurate description of the converter working process, which directly focus on the power states of the wind power system. (2) The proposed switching control method realizes the direct power switching control of the converter of the wind power MPPT system. The merits of the proposed method are simple control structure, no control parameter, no pulse width modulation block and strong robustness under circuit parameters uncertainty. The simulation results verify the effectiveness and the superiority of the proposed methods. © 2022 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation 39

DuSSS: Dual Semantic Similarity-Supervised Vision-Language M...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

ISBN: (纸本)157735897X

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantitative Inertia Estimation Method for Wind Farm Based on AFF-RLS 8

Quantitative Inertia Estimation Method for Wind Farm Based o...

引用

8th International Conference on control Science and systems engineering, ICCSSE 2022

作者： Qin, Hao Cao, Yongji Zhang, Hengxu Gao, Zhimin Zhang, Xiaoning Li, Changgang Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Shandong University Jinan China Technical University of Denmark Kgs. Department of Electrical Engineering Lyngby Denmark School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781665484138

In order to guarantee the frequency security and stability of the power system with high proportional of wind generation, virtual inertia control techniques are gradually being promoted and applied. However, there is still a lack of methods and techniques to accurately estimate the equivalent virtual inertia of wind farms in real time, which makes it difficult to quantitatively evaluate the effect of virtual inertia control and to dynamically monitor the inertia level of power systems. Therefore, in this paper, an AR model with eXogenous input is applied to the time-varying characteristics of the virtual inertia of wind farm, and a recursive least squares identification algorithm based on a fuzzy control algorithm with an adaptive forgetting factor is proposed to estimate the virtual inertia of wind farms online. The proposed identification model and solution algorithm have superior tracking ability and good convergence. All that is required is to obtain perturbation data on the frequency and active power of the point of common coupling from the phasor measurement unit. A case study is carried out to verify the effectiveness of the proposed method. © 2022 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Electric Field Distribution Analysis During the Very Fast Transient Process Based on 3D Full Maxwell Simulation 4th

Electric Field Distribution Analysis During the Very Fast Tr...

引用

4th International Conference on Power and Electrical engineering, ICPEE 2023

作者： Sun, Qiang Gao, Wensheng Zhang, Ziwei Nie, Hongyu Lu, Guiyou He, Yufeng Qu, Jiaqi Department of Electrical Engineering State Key Laboratory of Control and Simulation of Power System and Generation Equipment Tsinghua University Beijing China Sichuan Energy Internet Research Institute Tsinghua University Chengdu China Ultra High Voltage Branch State Grid Sichuan Electric Power Company Chengdu China School of Instrumentation and Optoelectronic Engineering Beihang University Beijing China

ISBN: (纸本)9789819716739

Most simulations of electric field distribution during the very fast transient (VFT) process are based on equivalent waveforms, which affects the analysis of the electric field. In this paper, the actual VFT process is simulated based on the 3D full Maxwell finite element method (FEM). The electric field distribution at different points is measured. To investigate the influence of the induced electric field during the VFT process, and whether high amplitude or high steepness is the main factor affecting insulation during the VFT process, the simulation results are compared with the electrostatic simulation results. The results show that the induced electric field caused by the wave process does not play an important part. The electric field distribution is hardly influenced by the induced electric field. Therefore, the threat to insulation caused by VFTO is mainly due to its high amplitude, which leads to a stronger Coulomb electric field. Besides, the wave process only leads to a 6~8% voltage amplitude increase, which is much lower than the amplitude increase due to externally generated low-frequency oscillations. Therefore, the high amplitude of VFTO is mainly caused by low-frequency oscillations, rather than the high-frequency components during the VFT process. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electric fields

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：