检索结果-内蒙古大学图书馆

2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

作者： Pan, Ziheng Pan, Congcong Ruan, Gang Hu, Bo Wang, Y. Xie, Kaigui The Power and Energy Reliability Research Center State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing400044 China

ISBN: (纸本)9798350322699

This paper proposed a survivability assessment model for the waek-link power grid (WLPG) under extreme events. Firstly, the survivability index system is constructed to reflect the impact of extreme events. It mainly includes secondary index from multiple dimensions and the corresponding tertiary index. Secondly, the objective secondary index information entropy model and primary index principal component analysis model are proposed. Finally, IEEE RTS79 was tested as case study to validate the proposed index assessment model. The proposed model can effectively characterize the survivability of WLPG under extreme events of different severity with a simple calculation process and not require human weighting, making it relatively objective. © 2023 IEEE.

关键词： extreme event index assessment Survivability WLPG

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modeling of key Operating Parameters for Supercritical Circulating Fluidized Bed Units based on Data-Knowledge-Driven Method

引用

Journal of Thermal Science 2024年第3期33卷 1216-1230页

作者： YU Haoyang GAO Mingming ZHANG Hongfu CHEN Jiyu LIU Jizhen YUE Guangxi The State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer EngineeringNorth China Electric Power UniversityBeijing102206China CHN Energy New Energy Technology Research Institute Co. Ltd.Beijing102209China Department of Energy and Power Engineering Tsinghua UniversityBeijing100084China

To address the pressing need for intelligent and efficient control of circulating fluidized bed(CFB)units,it is crucial to develop a dynamic model for the key operating parameters of supercritical circulating fluidized bed(SCFB)***,data-knowledge-driven dynamic model of bed temperature,load,and main steam pressure of the SCFB unit has been ***,a knowledge-driven method is employed to develop a dynamic model for key operating parameters of SCFB *** model parameters are determined based on the operating data of the unit and continuously optimized in real ***,Bidirectional Long Short-Term Memory combined with Convolutional Neural Network and Attention Mechanism is utilized to build the dynamic model of bed temperature,load,and main steam ***,a collaboration and integration method based on the critic weight method and the variation coefficient method is proposed to establish data-knowledge-driven model of key operating parameters for SCFB *** model displays great accuracy and fitting ability compared with other methods and effectively captures the dynamic characteristics,which can provide a research basis for the design of intelligent flexible control mode of SCFB unit.

关键词： circulating fluidized bed dynamic model data-knowledge-driven method deep learning power plant

来源：评论

学校读者我要写书评

暂无评论

Overvoltage Suppression Strategy Based on Active Control of Current for Half-Wave Commutated Modular Multilevel Converters 14

Overvoltage Suppression Strategy Based on Active Control of ...

引用

14th International Conference on Power and Energy systems, ICPES 2024

作者： Liu, Bao Xu, Yunfei Zhao, Guoliang Fu, Nan Jia, Chen China Electric Power Research Institute State Key Laboratory of Advanced Power Transmission Technology Beijing China Tsinghua University State Key Laboratory of Control and Simulation of Power System and Generation Equipment Beijing China Electric Power Research Institute State Grid Liaoning Electric Power Co. Ltd. Shenyang China

ISBN: (纸本)9798350391329

Flexible low-frequency AC transmission technology combines the advantages of 50 Hz AC transmission and DC transmission, and has good application scenarios. High voltage and large capacity AC/AC converters are the core equipment of flexible low-frequency AC transmission systems. The proposal of half-wave commutated modular multilevel converters effectively reduces the number of components and improves system economy. In view of this, this paper proposes an overvoltage suppression strategy for active control of inductor current, which effectively reduces the overvoltage level during commutation. The article first introduces the sparse topology and mathematical model of the half-wave commutated modular multilevel converters. Secondly, the mechanism of overvoltage generation is analyzed. Then, overvoltage suppression strategies are proposed. Finally, a PSCAD simulation model is built to verify the effectiveness and feasibility of the proposed method through simulation. © 2024 IEEE.

关键词： Flexible AC transmission systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative Prediction Approach for the Small-Signal Stability Margin of Renewable Power system Based on Vertical Federated Learning 3

Cooperative Prediction Approach for the Small-Signal Stabili...

引用

3rd International Conference on Power systems and Electrical technology, PSET 2024

作者： Lai, Xiang Chen, Zhihao Liu, Yun Dai, Tianchen Cai, Haiqing Gu, Haohan Chen, Wei South China University of Technology School of Electric Power Engineering Guangzhou China CSG Electric Power Research Institute State Key Laboratory of HVDC Guangzhou China Laboratory of Intelligent Operation and Control for New Energy Power System Guangdong Provincial Key Guangzhou China

ISBN: (纸本)9798350353204

Since sub-synchronous oscillations have been frequently witnessed in large-scale wind farms under weak grid conditions, it is significant to predict the critical stability situations in short term so that timely preventative actions can be taken to avoid potential small-signal stability (SS) risks. To this end, this paper proposes a SS prediction approach based on the grid strength metric of generalized short-circuit ratio (gSCR) under the mechanism of vertical federated learning. Specifically, the improved ridge regression prediction model is employed and its corresponding distributed training and the distributed predicting are derived by utilizing the separable characteristic of gradient vector calculation in the context of federated learning. On this basis, the original largescale predicting problem is decomposed into a large number of small-scale subproblems, and each subproblem is calculated locally by the corresponding wind farm. The feature data information of adjacent wind farms can be effectively used to improve the accuracy of the prediction of the stability margin while ensuring the data privacy and security of all participants. Finally, simulation results illustrate the effectiveness and efficiency of the proposed approach under various scenarios. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Attention-enhanced BLSTM Network for Liquid Volume Estimation based on Tactile Sensing

Attention-enhanced BLSTM Network for Liquid Volume Estimatio...

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Su, Yuanzhe Wang, Jingnan Huang, Binhua Li, Xiaoyu Liu, Yiwen Liu, Chengliang Zhou, Zhenning Yi, Zhengkun Wu, Xinyu Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Siat Branch Shenzhen518055 China

ISBN: (纸本)9798350327182

The task of liquid volume estimation based on tactile sensing is challenging. Previous researches mainly focused on the classification of different contents in the container, rather than achieving accurate estimation of a certain property of the contents in container, such as volume or viscosity. In addition, few studies are conducted for the regression task with advanced tactile sensors, but the performance is unsatisfactory. We propose a new deep-learning algorithm for processing the tactile signals collected from the photoresistors in the task of liquid content estimation. The proposed algorithm doesn't need hand-crafted features. In addition, we use attention after BLSTM, so that more important features can be selected to achieve better performance for liquid volume estimation. We utilize a bi-directional Long Short-Term Memory (BLSTM) architecture, which allows for the incorporation of information from both preceding and subsequent time, thereby providing a more comprehensive and informative feature set for learning. Additionally, we employ an attention mechanism following the BLSTM, allowing for the selection of more critical features and improved performance in liquid volume estimation. To prove the effectiveness of our method, we conduct experiments utilizing tactile sensors on a physical robot, achieving superior performance in liquid volume estimation. © 2023 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Matching of Humanoid-Eye Binocular Images Based on Susan-Sift Algorithm

SSRN

引用

SSRN 2023年

作者： Xia, Xiaohua Xiang, Haoming Cao, Yusong Ge, Zhaokai Jiang, Zainan Key Laboratory of Road Construction Technology and Equipment MOE Chang’an University Xi’an710064 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Imitating the visual characteristics of human eyes is one of the important tasks of digital image processing and computer vision. Feature correspondence of humanoid-eye binocular images is a fundamental step. However, in some scenes, due to a lack of edge features and mismatching problems, the performance of humanoid-eye binocular images in feature matching is greatly limited. To address the aforementioned challenges, a method of feature extraction and matching based on SUSAN-SIFT algorithm is proposed in this paper. The SUSAN detector is utilized in the feature detection stage for its outstanding edge feature extraction capability like human eyes. Then we build a multi-scale SIFT descriptor, to provide the neighborhood information at different resolutions for each feature and guide feature points to generate the corresponding pairs. Compared with state-of-the-art algorithms, the method can improve matching accuracy while retaining more edge features, and its resulting feature pairs are more evenly distributed. © 2023, The Authors. All rights reserved.

关键词： Binoculars

来源：评论

学校读者我要写书评

暂无评论

Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator

Open-Source Reinforcement Learning Environments Implemented ...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Zichun Xu Yuntao Li Xiaohang Yang Zhiyuan Zhao Lei Zhuang Jingdong Zhao State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin Heilongjiang Province China

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

This paper presents three open-source reinforcement learning environments developed on the MuJoCo physics engine with the Franka Emika Panda arm in MuJoCo Menagerie. Three representative tasks, push, slide, and pick-and-place, are implemented through the Gymnasium robotics API, which inherits from the core of Gymnasium. Both the sparse binary and dense rewards are supported, and the observation space contains the keys of desired and achieved goals to follow the Multi-Goal Reinforcement Learning framework. Three different off-policy algorithms are used to validate the simulation attributes to ensure the fidelity of all tasks, and benchmark results are also given. Each environment and task are defined in a clean way, and the main parameters for modifying the environment are preserved to reflect the main difference. The repository, including all environments, is available at https://***/zichunxx/panda_mujoco_gym.

关键词： Mechatronics Reinforcement learning Benchmark testing Manipulators Task analysis Physics Engines

来源：评论

学校读者我要写书评

暂无评论

A Lightweight YOLOv5 Model Integrating GhostNet and Attention Mechanism 4

A Lightweight YOLOv5 Model Integrating GhostNet and Attentio...

引用

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： Dou, Xinke Wang, Ting Shao, Shiliang School of Information Engineering Shenyang University of Chemical Technology Shenyang China Shenyang Institute of Automation State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350326444

Aiming at the problems of complex structure of neural network, large number of parameters and difficult deployment to terminal devices, this paper proposes an improved lightweight object detection model for the purpose of building a model with high classification accuracy and low complexity. First, the one-stage detector yolov5 is used as the base network. Considering the excessive redundant features of feature extraction, Ghost module is used to replace the traditional convolution, effectively allocate computing resources, to reduce the size of the model and improve the speed of model detection. When designing model bottleneck structure, Normalization-based Attention Module (NAM) is added to improve training efficiency and reduce model complexity. Experimental results show that compared with YOLOv5, the calculation speed of the proposed model is increased by 17% and the accuracy is reduced by less than 2%, which is of great significance in the environment of low-performance computing equipment. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on antioxidant property of ester with different ortho-substituted phenolic antioxidant groups based on DFT simulation 6

Research on antioxidant property of ester with different ort...

引用

6th IEEE International Electrical and Energy Conference, CIEEC 2023

作者： Luo, Yao Zhao, Yihui Li, Jian Chen, Xingyu Chongqing University State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing400044 China Jiangsu Shuangjiang Energy Technology Co Jiangsu 214500 China

ISBN: (纸本)9798350346671

Synthetic polyol esters derived from natural esters have become the direction of development for safe and environmentally friendly liquid insulating oils in recent years. However, the oxidative stability performance of natural ester-based synthetic esters is still inadequate due to the influence of natural ester fatty acid feedstock. Besides, the introduction of phenolic antioxidant groups into the oil molecules via transesterification is a novel way to solve this problem. Phenolic methyl ester is an important raw material for introducing antioxidant groups into the oil molecule during the transesterification modification process, and its antioxidant property is affected by its ortho substituting group. Therefore, in this paper, frontline molecular orbitals, energy gaps and O-H bond dissociation energies of phenolic antioxidant groups under different ortho substituents were obtained by DFT simulation in order to figure out the mono-phenolic group with optimal antioxidant property. The results show that the ortho substitution decreases the energy of LUMO orbital of phenolic ester molecules, making the antioxidant groups more likely to react with alkyl radicals. In addition, the fully hindered phenolic ester with ortho bis-tert-butyl substitution shows the smallest O-H bond dissociation energy due to spatial effects, and are the best monophenolic options for introducing antioxidant groups into oil molecules. © 2023 IEEE.

关键词： Antioxidants

来源：评论

学校读者我要写书评

暂无评论

A Method for Reconstructing The Shape of Wing Panels Based on Fiber Optic Sensors and Tomographic Imaging Principles 15

A Method for Reconstructing The Shape of Wing Panels Based o...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Zhan, Jun Zeng, Jie Xiang, Chao Cui, Jinpeng Zeng, Cheng Zhu, Linfeng Lu, Mingyu State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics No. 29 Yudao Street Nanjing210016 China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing Engineering Institute of Aircraft System Jincheng AVIC Nanjing China COMAC Beijing Aircraft Technology Research Institute Changping District Xiaotangshan Future Science and Technology City Beijing102211 China

ISBN: (纸本)9798350354010

The aircraft wing structure shape reconstruction method based on discrete strain information not only provides data support for the digital collaborative health monitoring and prediction technology of wing structure but also helps to improve the aerodynamic shape and flight quality of the aircraft, achieve structural stealth, and enhance the pointing accuracy of the on-board conformal antenna. As result, a wing skin panel shape reconstruction method based on the principle of tomographic imaging and strain information perception is proposed. According to the idea of tomographic imaging, a "non-intrusive" layout form that only requires sensors to be arranged on the periphery of the monitoring area is designed, breaking through the limitation that sensors can not be arranged in the monitoring area under special working conditions. A method for constructing the deflection shape function of the wing skin panel based on the concept of synthetic curvature is proposed, solving the problem of error accumulation and elimination of deformation inversion at non-monitoring points of the measured structure caused by the uncertainty of the limited discrete layout of sensors and the choice of interpolation fitting method. On this basis, a model deformation monitoring and inversion system for wing skin panel based on fiber optic grating sensors is constructed. The experimental results show that under the single-end fixed bending and torsion working condition, the average relative error of the panel model shape reconstruction is 4.17%. Under the double-end fixed double-concentrated load working condition, the average relative error of the shape reconstruction is 8.07%. The wing deformation distribution information reconstructed by the method proposed in this paper can be mapped onto the virtual twin model of the wing, providing technical support for the safety assessment, early warning, and on-condition maintenance of the entire service life of key structures of the aircraft. © 2024

关键词： Fixed wings

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：