检索结果-内蒙古大学图书馆

第34届中国控制与决策会议

作者： Linyan Han Haibo Du Shihua Li School of Automation Southeast UniversityKey Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education School of Electrical Engineering and Automation Hefei University of Technology

This paper focuses on the development of a control scheme capable of tracking contact forces ***,the nonlinear observer,admittance control and adaptive sliding mode control are integrated into a single *** the force sensor is absent,a nonlinear observer,which serves as a reaction force observer,can be used to estimate the contact ***,in order to track the force profile explicitly,admittance control is introduced to transform the desired contact force into the desired position *** adaptive sliding mode controller is designed to track the desired position and meanwhile compensate the estimation errors of contact forces caused by nonlinear *** stability of the whole system under the proposed controller can be guaranteed by the Lyapunov ***,several simulations are reported to demonstrate the effectiveness of the proposed approach.

关键词： Lyapunov Adaptive Sliding Mode control for Force Tracking Using Nonlinear Observer

来源：评论

学校读者我要写书评

暂无评论

Hotspot detection of photovoltaic modules in infrared thermal image based on saliency analysis

Hotspot detection of photovoltaic modules in infrared therma...

引用

Chinese control and Decision Conference, CCDC

作者： Yiye Wang Yu Shen Chenxi Li Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing P.R. China

ISBN: (纸本)9781665478977

With the increasing awareness of environmental protection, the solar photovoltaic (PV) industry has been developing dramatically in recent years. PV module is an important part of PV power generation system. In all the defect types of PV modules, hotspots occur more frequently and cause more serious damage. Therefore, it is necessary to detect hotspots. An approach is proposed using saliency analysis method for hotspot detection, combing the cognitive property about visual saliency and the temperature property of hotspots. Not only does this approach not require manual threshold setting, but also it does not require a large number of learning samples. This approach can also achieve the defect diagnosis and hotspot location when compared with the electrical characterization method. The infrared thermal (IRT) images trained in experiments are obtained using the thermographic camera FLIR Vue Pro with the unmanned aerial vehicle from a PV plant in Jiangsu, China. Altogether 135 IRT images are collected and 1020 PV modules are extracted from these images. Experiments have proved great accuracy and robustness when using the proposed method to detect hotspots.

关键词： Photovoltaic systems Industries Visualization Temperature Image edge detection Manuals Cameras

来源：评论

学校读者我要写书评

暂无评论

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultra-Short-Term PV Power Forecasting

PVTimesNet: A Hybrid Deep Learning Method for Enhancing Ultr...

引用

Chinese Automation Congress (CAC)

作者： Ji Wu Kai Wang Wenwen Ma Jingxin Zhang Shibo Wang China Electric Power Research Institute Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing China State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate ultra-short-term photovoltaic (PV) power forecasting is crucial for the real-time scheduling of grid systems. However, the inherent variability of solar energy makes this task extremely challenging. To enhance PV power forecasting, this paper introduces a novel hybrid model named PVTimesNet, designed to harness the strengths of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) for effective feature extraction. PVTimesNet consists of two parallel branches: the CNN1d branch, which captures correlations between multiple variables and adjacent time steps, and the LSTM branch, which learns the temporal dependencies within the PV power sequences. The features extracted by both branches are then concatenated and passed through a fully connected layer to generate multi-step PV power forecasts. Experimental results demonstrate that for forecast horizons of 1 to 4 hours, the proposed model significantly outperforms individual models and other CNN-LSTM hybrid structures. Additionally, it exhibits superior performance compared to related methods for longer forecast horizons.

关键词： Photovoltaic systems Deep learning Wind speed Predictive models Feature extraction Hybrid power systems Convolutional neural networks Forecasting Wind forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Short-Term Wind Power Forecasting Method With Self-Supervised Contrastive Learning-Based Feature Extraction Model

A Short-Term Wind Power Forecasting Method With Self-Supervi...

引用

International Youth Conference on Energetics (IYCE)

作者： Nanyang Zhu Kaifeng Zhang Ying Wang Huiping Zheng Yanxia Pan Xueting Cheng Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing Jiangsu China State Grid Shanxi Electric Power Research Institute Shanxi China State Grid Shanxi Electric Power Company Shanxi China

ISBN: (数字)9798350372380

ISBN: (纸本)9798350372397

It is significant and challenging to forecast wind power through the knowledge learned from the historical meteorological variables and wind power itself. So far, this knowledge has been learned based on supervised learning, which is insufficient in capturing semantic dependencies between variables and cannot provide a stability model. This work proposed an unsupervised representation learning-based short-term wind power prediction method using sequences contrastive technique. This representation learning model is mainly composed of the input encoder module, feature extraction module, contrastive learning module, and regression module. The feature extraction module which fuses multiple encoders can extract abundant feature vectors from the multi-source embedding of the input encoder module. The loss function in the contrastive learning module attempts to distinguish positive pairs and negative pairs that are generated from the feature extraction module. Eventually, the regression model uses the fully learned representation matrix for the power estimation. In order to explore the feasibility of this method in wind power prediction, the benefits under different prediction intervals are studied separately through some classic evaluation criteria, and comparing the proposed representation learning-based forecasting with other state-of-the-art methods. The results show that the knowledge learned from this model can generate improved performance with reliability and effectiveness with a 6-hour prediction horizon, and allow the development of short-term wind power forecast.

关键词： Representation learning Supervised learning Stability criteria Contrastive learning Wind power generation Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Attentive online sequential extreme learning machine for nonlinear dynamic process monitoring

Attentive online sequential extreme learning machine for non...

引用

第34届中国过程控制会议

作者： Jingxin Zhang Yuying Cao Hai Zhou Department of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education Department of Automation Southeast University New Energy Research Center China Electric Power Research Institute

This paper provides a new monitoring method based on the attention mechanism and online sequential extreme learning machines(OS-ELM) for nonlinear dynamic process,referred as attentive ***-ELM provides the prediction of outputs and the update of parameters by sequential *** cope with nonlinearity,the attention mechanism is utilized to map data to a high-dimensional feature *** effect of the attention mechanism and the single hidden layer feedforward network trained with OS-ELM work collaboratively in monitoring the real-time process data to detect possible *** addition,fault detection rate and false alarm rate are adopted to evaluate the monitoring *** effectiveness of the proposed method is illustrated by a typically complicated industrial system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval

arXiv

引用

arXiv 2023年

作者： Lu, Xin Chen, Shikun Cao, Yichao Zhou, Xin Lu, Xiaobo School of Automation Southeast University 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

In recent years, hashing methods have been popular in the large-scale media search for low storage and strong representation capabilities. To describe objects with similar overall appearance but subtle differences, more and more studies focus on hashing-based fine-grained image retrieval. Existing hashing networks usually generate both local and global features through attention guidance on the same deep activation tensor, which limits the diversity of feature representations. To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval. Specifically, an Attention Dispersion Loss (ADL) is designed to force the descriptors to attend to various local regions and capture diverse subtle details. Moreover, we propose a Stepwise Interactive External Attention (SIEA) to mine critical attributes in each descriptor and construct correlations between fine-grained attributes and objects. The attention mechanism is dedicated to learning discrete attributes, which will not cost additional computations in hash codes generation. Finally, the compact binary codes are learned by preserving pairwise similarities. Experimental results demonstrate that AGMH consistently yields the best performance against state-of-the-art methods on fine-grained benchmark datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Precise GPS-Denied UAV Self-Positioning via Context-Enhanced Cross-View Geo-Localization

arXiv

引用

arXiv 2025年

作者： Xu, Yuanze Dai, Ming Cai, Wenxiao Yang, Wankou School of Automation The Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Jiangsu Province Nanjing210096 China Advanced Ocean Institute of Southeast University Jiangsu Province Nantong226019 China Stanford University StanfordCA94305 United States

Image retrieval has been employed as a robust complementary technique to address the challenge of Unmanned Aerial Vehicles (UAVs) self-positioning. However, most existing methods primarily focus on localizing objects captured by UAVs through complex part-based representations, often overlooking the unique challenges associated with UAV self-positioning, such as fine-grained spatial discrimination requirements and dynamic scene variations. To address the above issues, we propose the Context-Enhanced method for precise UAV Self-Positioning (CEUSP), specifically designed for UAV self-positioning tasks. CEUSP integrates a Dynamic Sampling Strategy (DSS) to efficiently select optimal negative samples, while the Rubik’s Cube Attention (RCA) module, combined with the Context-Aware Channel Integration (CACI) module, enhances feature representation and discrimination by exploiting interdimensional interactions, inspired by the rotational mechanics of a Rubik’s Cube. Extensive experimental validate the effectiveness of the proposed method, demonstrating notable improvements in feature representation and UAV self-positioning accuracy within complex urban environments. Our approach achieves state-of-the-art performance on the DenseUAV dataset, which is specifically designed for dense urban contexts, and also delivers competitive results on the widely recognized University-1652 benchmark. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Maximum power point tracking of photovoltaic array based on improved Particle Swarm Optimization Algorithm 4

Maximum power point tracking of photovoltaic array based on ...

引用

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

作者： Lai, GuangZhi Li, HaoRan Zhang, ChangZhi Zhang, YiHao Wang, ZhiJin State Grid e-commerce Co. Ltd Beijing10053 China State Grid Tianjin Electric Power Company China School of Automation Southeast University Jiangsu Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

With the vigorous development of the photovoltaic industry, how to improve the efficiency of photovoltaic power generation has become an important issue, among which partial shadow occlusion is an important reason affecting the efficiency. The efficiency of photovoltaic power generation can be effectively improved by adopting the maximum power point tracking method (MPPT), but the traditional MPPT method is not ideal in the partial shadow occlusion of the photovoltaic array. To solve this problem, this paper proposes an improved particle swarm optimization method to effectively improve the tracking efficiency of MPPT when multiple peaks appear in the photovoltaic arrays power curve (P-V) under the partial shadow. The proposed method improves the learning factor of the traditional particle swarm optimization algorithm and designs the initial position of the particles according to the characteristics of the photovoltaic array. By adding the particle elimination mechanism, the number of particles changes dynamically, and the tracking speed of the algorithm for the maximum power of the photovoltaic array is improved. Through the result of the simulation, it is not difficult to get the conclusion that the improved particle swarm optimization algorithm can effectively improve the performance of the photovoltaic system under partial shadows. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

AMG: A Depression Detection Model with Autoencoder and Multi-Head Graph Convolutional Network

AMG: A Depression Detection Model with Autoencoder and Multi...

引用

Chinese control Conference (CCC)

作者： Han-Guang Wang Qing-Hao Meng Li-Cheng Jin Jian-Bang Wang Hui-Rang Hou Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin China China Southern Power Grid Company Limited Guangzhou China

Depression is a common chronic mental disorder characterized by high prevalence, recurrence, suicide rate, disability rate and heavy disease burden. Depression assessment based on questionnaires is subjective, therefore, a novel framework to is hereby designed to detect depression automatically and obj ectively. The framework first utilizes a two-way autoencoder to extract the hidden features from the original differential entropy features. The new features are used to generate the channel connectivity graph, using the multi-head attention mechanism. Next, the new features and graphs are input into the graph convolutional network (GCN) to aggregate spatial information. Finally, the output from GCN is passed to a fully connected layer and a soft layer to obtain the predicted label. Experiments are performed on Multimodal Open Dataset for Mental-disorder Analysis dataset. A final accuracy of 88.68% and a cross entropy loss of 2.4532 are obtained, when using ten-fold cross validation, outperforming other traditional machine learning methods including SVM, KNN, decision tree.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Uplink Spectrum Efficiency and UAV Trajectory in Cell-Free UAV Networks

Joint Optimization of Uplink Spectrum Efficiency and UAV Tra...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Jian He Chunyu Pan Qian Chen The Key Laboratory of Information and Communication Systems Ministry of Information Industry and the Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin China

The flexible mobility characteristics of unmanned aerial vehicle (UAV) lead to frequent handover and inter cell interference issues in traditional cellular based UAV assisted communication systems. Establishing cell-free UAV (CF-UAV) networks without cell boundaries will effectively alleviate this problem and has been an important research. However, the movement of the UAV results in time-varying channels. Therefore, the joint dynamic and reasonable UAV trajectory optimization and power allocation are very important for in CF-UAV networks. The expression of pilot transmission, channel estimation, uplink transmission spectrum efficiency (SE) have been derived based on the assumption of Rician channel between UAVs and access point (AP). SE optimization algorithm for CF-UAV networks combined with the Angle search and multi-UAV trajectory optimization strategy has been proposed in this paper. Simulation results show that the proposed algorithm performs better performance than comparison schemes, which SE improves by 37% compared with Angle search.

关键词：

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：