检索结果-内蒙古大学图书馆

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

Multi-objective Optimization of A CCHP System Model Integrated with P2G for Decarbonization 6

Multi-objective Optimization of A CCHP System Model Integrat...

引用

6th IEEE Conference on Energy Internet and Energy System Integration, EI2 2022

作者： Wei, Pengyu Bamisile, Olusola Cai, Dongsheng Li, Jian Adun, Humphrey Huang, Qi Chengdu University of Technology School of Nuclear Technology and Automation Engineering Chengdu China University of Electronic Science and Technology of China Sichuan Provincial Key Lab of Power System Wide-area Measurement and Control Chengdu China Cyprus International University KKTC Energy Systems Engineering Department Mersin10 Turkey

ISBN: (纸本)9798350347159

To realize the dual carbon policy, the goal of energy saving, and emission reduction, it is important to develop ways to better promote the low carbon economic operation of energy systems. Therefore, this research proposes an optimal operation strategy considering the electric-gas-cooling-heat demand response. Considering the demand response of each participant, an integrated energy system model with photovoltaic, wind energy, and traditional grid as energy supply. Also, electric energy, natural gas, cooling, and heating subsystems with co-production are established. With minimizing the overall system operation cost and optimizing environmental protection, the improved particle swarm optimization algorithm is used to solve the multi-constrained objective optimization problem. Finally, the optimized model is tested. The results from this study show that the energy system under cogeneration can find a balance between economy and environmental friendliness, and provide a reference for the subsequent energy supply configuration. © 2022 IEEE.

关键词： Environmental protection

来源：评论

学校读者我要写书评

暂无评论

Subgroup State Prediction under Different Noise Levels Using MODWT and XGBoost

引用

Journal of Healthcare engineering 2023年第1期2023卷

作者： Zhao, Xin Nie, Xiaokai School of Mathematics Southeast University Nanjing211189 China School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Shenzhen Research Institute Southeast University Shenzhen518057 China

In medical states prediction, the observations of different individuals are generally assumed to follow an identical distribution, whereas precision medicine has a rigorous requirement for accurate subgroup analysis. In this research, an aggregated method is proposed by means of combining the results generated from different subgroup models and is compared with the original method for different denoising levels as well as the prediction gaps. The results using real data demonstrate the effectiveness of the aggregated method exhibiting superior performance such as 0.95 in AUC, 0.87 in F1, and 0.82 in sensitivity, particularly for the denoising level that is set to be 2. With respect to the variable importance, it is shown that some variables such as heart rate and lactate arterial become more important when the denoising level increases. © 2023 Xin Zhao and Xiaokai Nie.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Continuous Terminal Sliding-Mode Speed control of Micro Gas Turbine System with Mismatched Disturbances

Finite-Time Continuous Terminal Sliding-Mode Speed Control o...

引用

2021 China automation Congress, CAC 2021

作者： Sun, Yanjun Xu, Long Chen, Ning Li, Shihua School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China China Electric Power Research Institute Nanjing210036 China

ISBN: (纸本)9781665426473

The micro gas turbine system acts as a key role in distributed renewable generation systems due to its flexibility, versatility, and low emissions. This paper focuses on the micro gas turbine speed control problem, which primarily determines the fuel flow for the turbine under variable load conditions. Due to nonlinear factors in MGTS, such as the coupling between systems parameters, and external disturbances such as electric load variation, it is a challenge to realize accurate speed control. In this paper, a continuous terminal sliding-mode control law based on a finite-time disturbance observer is designed for micro gas turbine control system. In this method, the integral of high-frequency switching function is introduced to control law. It guarantees the continuity of control signal and alleviates the chattering problem. Besides, the linear sliding mode surface is replaced by a full-order terminal sliding mode surface, and it obtains finite-time convergence and smaller speed tracking error. Furthermore, disturbance estimates are used in control law to eliminate the adverse effect of disturbances on control performance, which improves disturbance rejection ability. Finally, simulation comparison with conventional sliding-mode control validates the advantages of the composite controller. © 2021 IEEE

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Mdbfusion: A Visible And Infrared Image Fusion Framework Capable For Motion Deblurring

Mdbfusion: A Visible And Infrared Image Fusion Framework Cap...

引用

IEEE International Conference on Image Processing

作者： Jun Chen Wei Yu Xin Tian Jun Huang Jiayi Ma School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Electronic Information School Wuhan University Wuhan China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

As a vital technology in the field of image processing, numerous visible and infrared fusion methods have emerged with the aim of generating a single image containing salient targets and abundant details. However, owing to the influence of target motion or camera shake, source images may suffer from motion blur, resulting in blurred edges and unrecognizable objects. To address this issue, this paper bridges the gap between deblurring and fusion tasks and proposes a joint motion deblurring and fusion network for visible and infrared image (MDbFusion). On the one hand, we innovatively merge motion deblurring task into network design, which effectively ensures the capacity of MDbFusion to process images in the extreme condition. On the other hand, an Adaptive Weight Module (AWM) is designed to calculate contribution between visible and infrared features, which solves the channel contrast between two tasks, greatly reducing the complexity of network. Extensive experiments demonstrate that the MDb-Fusion outperforms state-of-the-art (SOTA) fusion algorithms in terms of preserving texture details and quantitative metrics. Furthermore, we also compare with a two-step fusion strategy that first deblurring then fusion, both with SOTA methods. The results reveal superiority of our framework in coupling and reciprocity between two tasks.

关键词： measurement Couplings Adaptive systems Image edge detection Cameras complexity theory Decoding

来源：评论

学校读者我要写书评

暂无评论

A new image denoising method based on steer ketnel regression

A new image denoising method based on steer ketnel regressio...

引用

2020 Jiangsu Annual Conference on automation, JACA 2020

作者： Shi, Gongbiao Chai, Lin Jin, Lizuo Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781839535635

In this paper, we propose a new image pyramid denoising model based on the iterative steer kernel regression (ISKR) method. By introducing an image pyramid to generate images at multiple scales, it can filter out large-scale noise on low-resolution images and preserve details on the high-resolution image, and then we fuse the denoised images of multiple resolutions into a high-quality image by up-sampling noise residual. This method can improve denoising performance efficiently. and reduce the cost of calculation. Experiments show that this model reduces calculation by about 58% compared with the ISKR method while ensuring a good denoising effect. © 2020 Institution of engineering and Technology. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Blendnet: Metric-Based Method for Few-Shot Image Classification

SSRN

引用

SSRN 2022年

作者： Yang, Jiming Da, Feipeng Southeast University School of Automation Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Image classification task often requires a massive amount of data. Learning to adapt when little data is available could be difficult. In this work, a framework named BlendNet is proposed for few-shot learning. Unlike conventional metric-based methods, a classifier blending features from different levels is proposed to assist the framework to obtain better accuracy and generalization performance. To alleviate the variance of the network for classifying the same class of objects, an data augmentation method is exploited to obtain the image representation robustly. Extensive experiments are conducted to validate our method under the meta-learning paradigm using few-shot classification datasets. The experiments demonstrate that our proposed framework provides competitive results on both Omniglot and mini -ImageNet benchmarks. Our code is available at https: // *** / tyolm / BlendNet . © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Hierarchical control Scheme for VSC-MTDC System with multiple Renewable Energy Sites Based on Optimal Power Flow and Droop Scheme 6

Hierarchical Control Scheme for VSC-MTDC System with multipl...

引用

6th IEEE Conference on Energy Internet and Energy System Integration, EI2 2022

作者： Raza, Asif Huang, Qi Li, Jian Bamisile, Olusola Dongsheng, Cai Raza, Ghalib University of Electronic Science & Technology of China Sichuan Provincial Key Lab of Power System Wide -Area Measurement and Control School of Mechanical and Electrical Engineering China Chengdu University of Technology College of Nuclear and Automation Engineering Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science & Technology of China China University of Electronic Science & Technology of China China Chengdu University of Technology College of Nuclear and Automation Engineering Sichuan China Benazir Bhutto Shaheed University of Technology & Skill Development Khairpur Pakistan

ISBN: (纸本)9798350347159

This paper designs a hierarchical control system to improve control performance in a multi-terminal high voltage direct current based on the voltage source converter (VSC-MTDC) transmission system. In this control scheme, the primary control layer employs droop control, while the secondary control layer has developed optimal power flow control (OPF) for maintaining the variation of DC voltage and regulating the active power, and simultaneously minimizing power loss. In the event of a power disturbance or a change in power generation or consumption in the DC system, based on OPF results a new stable droop operating mode is established to stabilize DC voltage variation and regulate active power in the network. A ±400 kV four-terminal VSC-MTDC test network has been developed by using PSCAD and MATlab simulation tools to assess the proposed control scheme. The primary controller is designed in PSCAD, and the secondary optimum control technique is applied in MATlab. The results of steady-state and transient operating modes demonstrate that the planned control technique can achieve DC voltage regulation and keep active power, and minimize the power losses in the MTDC system. © 2022 IEEE.

关键词： MATlab

来源：评论

学校读者我要写书评

暂无评论

Hot Spot Detection of Photovoltaic Module Infrared Near-field Image based on Convolutional Neural Network 4

Hot Spot Detection of Photovoltaic Module Infrared Near-fiel...

引用

2022 4th International Conference on Energy systems and Electrical Power, ICESEP 2022

作者： Fan, Fu Na, ZhiXiong Zhang, ChangZhi Li, HaoRan Tong, ChaoLiu School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China State Grid e-commerce Co. Ltd Beijing100053 China State Grid Tianjin Electric Power Company Tianjin300010 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

With the installation and use of large-scale photovoltaic systems around the world, the detection of photovoltaic system operation and maintenance has become increasingly important. This research uses a convolutional neural network training model to detect and classify the infrared near-field images of photovoltaic modules from small-scale photovoltaic plants in the laboratory. This model classifies the images into two categories: with and without hot spots, with a classification accuracy of 96.58%. The experimental results show that the convolutional neural network training model has a good classification result. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Finite-time robust control for transformerless H-bridge cascaded STATCOM with star configuration

引用

Journal of control and Decision 2021年第2期8卷 106-115页

作者： Xingyu Lv Bangjun Lei Shumin Fei Foreign Language Teaching Center Guizhou Institute of TechnologyGuiyangPeople’s Republic of China Key Laboratory of Power Dig Data of Guizhou Province School of Electrical and Information EngineeringGuizhou Institute of TechnologyGuiyang 550003People’s Republic of China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast UniversityNanjingPeople’s Republic of China

This article presents a finite-time robust control(FTRC)of a transformerless STATCOM based on a cascaded multilevel H-bridge converter(CMHC)with star *** FTRC is first proposed for the current loop control of a CMHC-based transformerless STATCOM by using the finite time robust control *** the parameters,perturbations and external disturbances into account and using coordinate transformation method,the nonlinear dynamic model of the CMHC-based transformerless STATCOM is transformed into a standard nonlinear port-controlled dissipative Hamiltonian(PCDH)*** on the PCDH structure,an FTRC is designed for the CMHC-based transformerless STATCOM to improve the transient stability and oscillation damping of power ***,the simulation results demonstrate that the FTRC has better dynamic performance and strong robustness in comparison with the passivity-based control of the CMHC-based transformerless STATCOM.

关键词： Cascaded H-bridge converter transformerless STATCOM finite time robust control oscillations damping transient stability

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：