检索结果-内蒙古大学图书馆

Advanced Electrical and Energy Systems (AEES), International Conference on

作者： Changwei Yin Wenlu Ji Ting Ye Tingfeng Mao Kaifeng Zhang Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing China Nanjing Power Supply Company of State Grid Jiangsu Electric Power Co. Ltd. Nanjing China

Distributed flexible resources are developing in the trend of sea quantization. In this situation, the existing resource aggregation methods are facing bottlenecks, and it is difficult to fully exploit the regulation potential of massive flexible resources. In order to achieve efficient and flexible aggregation in the scenario of massive resources, this paper proposes a self-organizing aggregation method for flexible resources based on the social network and simulates the aggregation process under the proposed method based on the multi-agent simulation platform NetLogo. Firstly, this paper outlines the idea of the self-organizing aggregation method for flexible resources, which projects flexible resources from the physical space to the social network space, and realizes flexible aggregation through the interactive attraction between resources in the social network. Secondly, this paper establishes a simulation model for flexible resource self-organizing aggregation based on the NetLogo platform. The model defines four types of agents involved in the self-organizing aggregation process and provides detailed specifications for their attributes and interaction rules. Finally, simulation experiments are designed to verify the rationality of the self-organizing aggregation method and simulation model proposed in this paper. The simulation results show that, following the idea of self-organizing aggregation, massive flexible resources can autonomously and flexibly aggregate through the interaction attraction in the social network due to the incentive of task gain, demonstrating the effectiveness and rationality of the self-organizing aggregation method and the simulation model proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quick Routing Response to Link Failure in Low-Earth Orbit Satellite Networks 8

Quick Routing Response to Link Failure in Low-Earth Orbit Sa...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Lu, Zhiping Zhi, Ruxin Ma, Weiguo School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Beijing China Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781665450515

Low earth orbit satellite communication systems are attractive for provisioning global, high-speed and low latency Internet access services. In order to achieve global continuous multiple coverage, the number of satellites is tremendous. But Low earth orbit satellite networks are prone to instability due to unpredictable link failures and frequent topology changes. Therefore, in this paper, a novel routing schemes with quick response to link failures is first proposed. Based on Dijkstra algorithm, a scalable routing algorithm is proposed to minimize the end-to-end transmission delay. It takes advantage of the predictable constellation trajectory, and changes dynamically according to the changes of network topology. It provides the shortest routing path and an alternative path simultaneously. When a link failure is detected by one satellite, notification packets will be sent to its neighbors for adjustment to the alternative routing path. Notification packets also will be sent to the head node for the recalculation of routing table. Finally, extensive simulations have been conducted, and the results show that the proposed scheme is able to produce desired performance. © 2022 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Data Cleaning Method Based on DBSCAN Clustering, Quartile Algorithm and Pearson Correlation Coefficient Interpolation Method 6

Photovoltaic Data Cleaning Method Based on DBSCAN Clustering...

引用

6th International Conference on Energy, Electrical and Power engineering, CEEPE 2023

作者： Wang, Biyuan Deng, Xingye Chen, Taowei Li, Yidong Huizhou Power Supply Bureau Guangdong Power Grid Co Guangdong China School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (纸本)9798350348279

The proportion of photovoltaic power generation in the global energy structure is increasing year by year. Because of its volatility and periodicity, grid-connected photovoltaic challenges the safe and stable operation of power grid. One of the ways to solve this problem is data mining. Data mining needs high-quality data support, and data cleaning is one of the important means to improve data quality. Aiming at the problem of poor quality of original PV data, this paper analyzes two typical outliers of PV data and proposes a PV output data cleaning method based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm, quartile algorithm and Pearson correlation coefficient interpolation method. Comparison of DBSCAN clustering algorithm combined with the quartile method of outlier identification with the quartile method alone outlier identification, the effectiveness of the method proposed in this paper is verified. Then using the method proposed in this paper for outlier identification based on Pearson correlation coefficient interpolation and cubic spline interpolation to verify the data filling effect, the results show that Pearson correlation coefficient interpolation is superior to cubic spline interpolation. Finally, two sets of data with different data cleaning methods are substituted into the Long short-term memory (LSTM) Model to verify accuracy of the cleaning method proposed in this paper. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backstepping Sliding Mode control for Underwater Glider Trajectory Tracking Based on Nonlinear Disturbance Observer

Adaptive Backstepping Sliding Mode Control for Underwater Gl...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Zhenjia Cao, Weihua Gan, Chao Wen, Mingming School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Guangzhou Marine Geological Survey Guangzhou510000 China

ISBN: (纸本)9798350303759

An adaptive backstepping dynamic surface sliding mode controller based on nonlinear disturbance observer (NDOABSMC) is designed to track zigzag motion of underwater glider (UG). Firstly, a nonlinear disturbance observer is devised to observe ocean current. Then, the backstepping sliding mode control is used to devise motion attitude controller of UG to ensure that UG can track the target trajectory quickly. Additionally, the stability of UG's control system is analyzed. In the end, the proposed control strategy is compared with other approaches. © 2023 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Imdet: Injecting More Supervision to Centernet-Like Object Detection

SSRN

引用

SSRN 2023年

作者： Jia, Shukun Song, Chen Cao, Yichao Lu, Xiaobo School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Nanjing Enbo Technology Co. Ltd. Nanjing China

CenterNet-like object detectors are known for the concise post-processing method. But there are two bottlenecks that limit its further research and development. The first one is they merely encode one positive sample for each object in the classification task, failing to make full use of supervision information. And simply encoding more positive samples is not as effective as expectation. The other one lies in that they perform predictions on large-resolution feature maps, ignoring to utilize the insights of multi-level-feature object detection. The two shortcomings make their accuracy lag behind the detectors with one-to-many label assignment strategy and feature pyramids networks (FPN). To solve the two issues, we first find three rules based on Gaussian kernel to set proper target values for multiple positive samples, which are achieved uniformly and cost-free. Second, we devise a balanced and sufficient supervision network to ease the optimization of backbones. Both proposed methods inject more supervision signal to CenterNet-like detectors, and improve CenterNet-like detectors to a competitive performance. The effectiveness of each method is fully verified on large-scale datasets with different data distributions, i.e., the MS-COCO and PASCAL VOC dataset. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Optimized One-Stage Detector for Autonomous PV Defect Detection

An Optimized One-Stage Detector for Autonomous PV Defect Det...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Huidi, Xiao Jiajia, Zhao Lihui, Wang Qiucheng, Shen Nongjie, Ma Key Laboratory of Micro-Inertial Instrument and Advanced Navigation Technology Ministry of Education School of Instrument Science and Engineering Southeast University Nanjing210096 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China School of Mechanical and Electronic Control Engineering Beijing Jiaotong University Beijing China

ISBN: (纸本)9789811694912

To realize the defect detection of Photovoltaic (PV) modules based on infrared images, a one-stage detector based on FPT and loss function optimization is proposed. Firstly, ResNet50 is selected as the backbone network for feature extraction, combining with the idea of migration learning to strengthen its feature extraction ability. Besides, replacing the traditional feature pyramid with FPT, using Transformer structure help realize the interaction of the same position between different pyramid layers as well as different positions of the same layer, improving the feature fusion capability of the model. Finally, to alleviate the problem of suppression of non-optimal predictions by NMS strategy, a bipartite graph matching algorithm based on loss function minimization is designed to enhance the learning of the distribution of ground truth targets by the network. The dataset is expanded by Mosaic data enhancement method for model training, so as to achieve infrared image-based PV defect detection. Results show that the improved one-stage target detection network has a promising detection effect on PV module defects under infrared images, with the average accuracy improving by 2.20% compared with the original algorithm. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-enhanced dynamic multi-objective evolutionary algorithm for cooperative shovel scheduling in open-pit mining

Reinforcement learning-enhanced dynamic multi-objective evol...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Zihao Li, Changhe Yang, Shengxiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Artificial Intelligence Anhui University of Science & Technology Hefei232001 China School of Computer Science and Informatics De Montfort University Leicester United Kingdom

ISBN: (纸本)9798350368604

Aiming at the ore blending problem in the open-pit mining scenario, the optimization objective is to minimize the grade variance of the sliding window of the ore flow, and a cooperative shovel scheduling model for real-time ore blending is established. A reinforcement learning-enhanced dynamic multi- objective evolutionary algorithm is proposed, where a Q-learning operator selection mechanism is introduced to reuse the information from the previous environment for tracking the optimal solution in the dynamic environment. Experimental results show that the proposed method can effectively control the grade fluctuation of the ore flow and dynamically respond to external events, and can find a better solution in real time compared with the traditional operator selection algorithm. © 2024 IEEE.

关键词： Open pit mining

来源：评论

学校读者我要写书评

暂无评论

An Effective Nuclear Magnetic Resonance Gyroscope control Method Based on ESOPI-PLL

An Effective Nuclear Magnetic Resonance Gyroscope Control Me...

引用

Chinese Automation Congress (CAC)

作者： Pengjie Hu Dan Niu Yanlan Yang Yuansheng Liu Xiaoiie Sun Qi Fu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of CSE Ministry of Education Nanjing China Beijing Institute of Aerospace Control Devices Beijing China Quantum Engineering Research Center of CASC Beijing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

In the design of nuclear magnetic resonance gyroscopes, the closed-loop control of the excitation magnetic field is crucial. Among various control methods, the phase-locked loop (PLL) is widely used to enhance the dynamic characteristics and stability of the gyroscope. This research employs the Second-Order Generalized Integrator (SOGI) as the phase detector, with the loop filter utilizing PI control. However, the system, being of type 2, cannot track acceleration signals without a static error. To address this limitation, we propose a loop filter design based on an Extended State Observer (ESO) integrated with PI control, effectively transforming the system into ESOPI-PLL, which is a type of Type3-PLL. Compared to the traditional SOGI-PLL system, simulation results demonstrate that our proposed scheme extends the gyroscope range to 2000 °/s, with a bandwidth of 30Hz, and achieves zero static error tracking. This advancement presents significant application potential for nuclear magnetic resonance gyroscopes.

关键词： Dynamic response Magnetic separation Bandwidth Stability analysis Gyroscopes Nuclear magnetic resonance Systems simulation Phase locked loops State estimation Testing

来源：评论

学校读者我要写书评

暂无评论

Solid-phase sintering and vapor-liquid-solid growth of BP@MgO quantum dot crystals with a high piezoelectric response

引用

Journal of Advanced Ceramics 2022年第11期11卷 1725-1734页

作者： Qingwei LIAO Wei HOU Kexuan LIAO Liyin CHEN Yujun SONG Guowei GAO Lei QIN Key Laboratory of Sensors Beijing Information Science&Technology UniversityBeijing 100192China Key Laboratory of Modern Measurement&Control Technology Ministry of EducationBeijing Information Science&Technology UniversityBeijing 100192China Key Laboratory of Photoelectric Testing Technology Beijing Information Science&Technology UniversityBeijing 100192China School of Chemical Science and Engineering Tongji UniversityShanghai 200092China Harvard John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridge 02138USA Center of Modern Physics Technology School of Mathematics and PhysicsUniversity of Science and Technology BeijingBeijing 100083China

Low-dimensional piezoelectric and quantum piezotronics are two important branches of low-dimensional materials,playing a significant role in the advancement of low-dimensional devices,circuits,and ***,we firstly propose a solid-phase sintering and vapor–liquid–solid growth(SS–VLS-like)method of preparing a quantum-sized oxide material,i.e.,black phosphorus(BP)@MgO quantum dot(QD)crystal with a strong piezoelectric ***-sized MgO was obtained by Mg slowly released from MgB_(2) within the confinement of a nanoflake BP *** the slow release of Mg only grows nanometer-sized MgO to hinder the further growth of MgO,we added a heterostructure matrix constraint:nanoflake *** the BP as the matrix confinement,MgO QDs embedded in the BP@MgO QD crystals were *** crystals have a layered two-dimensional(2D)structure with a thickness of 11 nm and are stable in the *** addition,piezoresponse force microscopy(PFM)images show that they have extremely strong *** strong polarity can also be proved by polarization reversal and a simple pressure sensor.

关键词： quantum dots(QDs) piezoelectric black phosphorus(BP) MgO

来源：评论

学校读者我要写书评

暂无评论

Correction of Images Projected on Non-White Surfaces Based on Deep Neural Network 14

Correction of Images Projected on Non-White Surfaces Based o...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Wang, Zewei Zhang, Jingjing Du, Xingzhuo Cao, Sihua Wei, Wenxuan School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9781510657564

When projecting onto a non-white surface, the projected image is distorted or color mixing by complex luminance and chrominance information, which makes the projection result different from the visual perception of the human eye. The purpose of projection image correction is to remove these effects, and traditional solutions usually estimate parameters from the collected projection samples, compute an inverse model of the projection imaging process, and try to fit a correction function. In this paper, a deep neural network-based projection image correction network (PICN) is designed to implicitly learn complex correction functions. PICN consists of a U-shaped backbone network, a convolutional neural network that extracts projected surface features, and a perceptual loss network that optimizes the correction results. Such a structure can not only extract the deep features and surface interference features of the projected image, but also make the corrected projected image more in line with human visual perception. In addition, we built a projector-camera system under the condition of a fixed global illumination environment for verification experiment, and proved the effectiveness of the proposed method by calculating the evaluation metrics of projected images before and after correction. © 2022 SPIE.

关键词： Deep neural networks

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：