检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Feng, Fuxiang Cong, Runmin Wei, Shoushui Zhang, Yipeng Li, Jun Kwong, Sam Zhang, Wei The School of Control Science and Engineering Shandong University Jinan250061 China The Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan250061 China The University of California Los Angeles United States The Hubei Key Laboratory of Intelligent Geo-Information Processing The School of Computer Science China University of Geo-sciences Wuhan430078 China The Lingnan University Hong Kong

Reconstructing Hyperspectral Images (HSI) from RGB images can yield high spatial resolution HSI at a lower cost, demonstrating significant application potential. This paper reveals that local correlation and global continuity of the spectral characteristics are crucial for HSI reconstruction tasks. Therefore, we fully explore these inter-spectral relationships and propose a Correlation and Continuity Network (CCNet) for HSI reconstruction from RGB images. For the correlation of local spectrum, we introduce the Group-wise Spectral Correlation Modeling (GrSCM) module, which efficiently establishes spectral band similarity within a localized range. For the continuity of global spectrum, we design the Neighborhood-wise Spectral Continuity Modeling (NeSCM) module, which employs memory units to recursively model the progressive variation characteristics at the global level. In order to explore the inherent complementarity of these two modules, we design the Patch-wise Adaptive Fusion (PAF) module to efficiently integrate global continuity features into the spectral features in a patch-wise adaptive manner. These innovations enhance the quality of reconstructed HSI. We perform comprehensive comparison and ablation experiments on the mainstream datasets NTIRE2022 and NTIRE2020 for the spectral reconstruction task. Compared to the current advanced spectral reconstruction algorithms, our designed algorithm achieves State-Of-The-Art (SOTA) performance. Copyright © 2025, The Authors. 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

Two-Stage Virtual Inertia control Strategy with Coordination of Energy Storage system

Two-Stage Virtual Inertia Control Strategy with Coordination...

引用

Electrical Engineering and Mechatronics Technology (ICEEMT), IEEE International Conference on

作者： Yening Lai Zhaohui Qie Yongji Cao Hengxu Zhang Zhimin Gao Hao Qin Jian Zhang Xuening Cao State Grid Electric Power Research Institute NARI Group Corporation Nanjing China Academy of Intelligent Innovation Shandong University Jinan China Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Shandong University Jinan China

To address the lack of effective cooperative control of each inertia support resource, the principles of cooperative inertia control in the power system with a high percentage of renewable energies are studied and the problems of cooperative inertia control are summarized. To make the wind turbine generator (WTG) participate in inertia response based on rotor kinetic energy method and the photovoltaic (PV) unit participate in inertia response based on capacitive energy storage method. The inertia response stage enables the energy storage system (ESS) based on sag control to collaborate with the WTG and PV unit for inertia support, and the frequency recovery stage enables ESS based on fuzzy control to improve the frequency response performance. The fuzzy control rules are formulated to propose a virtual inertia cooperative control method for the WTG, PV unit, and ESS. A case study is conducted to verify the effectiveness of the proposed strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phenomenological Modeling and End-Point Trajectory Tracking control of a Flexible Beam with Pneumatic Soft Actuators

Phenomenological Modeling and End-Point Trajectory Tracking ...

引用

IEEE International Conference of intelligent Robotic and control Engineering (IRCE)

作者： Xuefeng Sun Qingxin Meng Jundong Wu Mingliang Zhu School of Automation China University of Geosciences Wuhan Hubei China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan Hubei China

As the basic construction of flexible mechanical systems, the flexible beam and its control problem have attracted widespread attention in recent years. This paper takes a flexible beam with pneumatic soft actuators (FBPSA) as the research object and studies its phenomenological modeling and end-point trajectory tracking control strategy. Firstly, we develop an experimental platform for the FBPSA and perform tests on it, gathering its input and output data. Using these collected data, we analyzed the motion characteristics of the FBPSA. Subsequently, a phenomenological model is established to describe the motion characteristics of the system, and the parameters of this model are identified through a large amount of the collected experimental data. Then, a combined feedforward-feedback control strategy is proposed to achieve the end-point trajectory tracking control of the system. Finally, three sets of experiments are carried out to verify the accuracy of the established model and the effectiveness and superiority of the control strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of echo state network with multi-objective optimization algorithm and l1 regularization

Design of echo state network with multi-objective optimizati...

引用

第34届中国控制与决策会议

作者： Zhanhong Wu Cuili Yang Beijing University of Technology Faculty of Information TechnologyBeijing Key Laboratory of Computational Intelligence and Intelligent SystemEngineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education

In this paper,a new approach for optimizing the structure and prediction error of echo state network（ESN） is *** is a kind of recurrent neural network with simple training and strong generalization *** is an important structure of ESN,which determine network ***,multi-objective optimization algorithm is used to optimize network structure and training error ***,a local search algorithm based on l regularization is used to accelerate *** experiment results of time series prediction and standard classification show that MESN can improve the network prediction performance while sparse network structure.

关键词： Echo state network multi-objective optimization algorithm l1 regularization

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on Syllable-Level Feature Extraction

SSRN

引用

SSRN 2023年

作者： Rehman, Abdul Liu, Zhen-Tao Wu, Min Cao, Wei-Hua Jiang, Cheng-Shan 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

Speech emotion recognition systems have high computational requirements for deep learning models and low generalizability mainly because of the poor reliability of emotional measurements across multiple corpora. To solve these problems, we present a speech emotion recognition system based on a reductionist approach of decomposing and analyzing syllable-level ***-spectrogram of an audio stream is decomposed into syllable-level components, which are then analyzed to extract statistical features. The proposed method uses formant attention, noise-gate filtering, and rolling normalization contexts to decrease contextual differences and increase focus the attention on the structure of a formant. A set of syllable-level formant features is extracted and fed into a single hidden layer neural network that makes predictions for each syllable as opposed to the conventional approach of using a sophisticated deep learner to make sentence-wide *** syllable level predictions help to lower the aggregated error in utterance level cross-corpus predictions. The experiments on IEMOCAP (IE), MSP-Improv (MI), and RAVDESS (RA) databases show that the method archives better than the state-of-the-art cross-corpus unweighted accuracy of 47.6% for IE to MI and 56.2% for MI to IE. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Method for Selecting Optimal Access Point of Offshore Wind Farm Integrated by VSC-HVDC 6

Method for Selecting Optimal Access Point of Offshore Wind F...

引用

6th International Conference on Power and Renewable Energy, ICPRE 2021

作者： Tan, Zukuang Liu, Yutian Liu, Xiaoming Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Jinan China Economic and Technology Research Institute State Grid Shandong Electric Power Company Jinan China

ISBN: (纸本)9781665449618

Because of the rapid growth of offshore wind farm (OWF) capacity, voltage-source-converter-based high-voltage direct-current (VSC-HVDC) transmission scheme is becoming a competitive transmission scheme. This paper presents a method for selecting the optimal access point of offshore wind farm integrated with VSC-HVDC. The method takes into account capability of wind power accommodation, voltage support from onshore VSCs, voltage fluctuation caused by the change of wind power, vulnerability of power system transmission networks, and construction costs. This multi-objective decision-making problem is suggested to be solved based on the theory of information entropy and fuzzy analytic hierarchy process (FAHP) method. The method is applied in Shandong Province where is developing offshore wind power rapidly to select an optimal access point by the use of PSS/E. The results demonstrate the effectiveness of the proposed method for selecting the access point of the OWF. © 2021 IEEE.

关键词： Offshore wind farms

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of Frequency Dynamics in Real Power system 7

Quantitative Analysis of Frequency Dynamics in Real Power Sy...

引用

7th Asia Conference on Power and Electrical Engineering, ACPEE 2022

作者： Qin, Hao Cao, Yongji Zhang, Hengxu Gao, Zhimin Yang, Dong Ma, Huan Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Jinan China Technical University of Denmark Department of Electrical Engineering Kgs. Lyngby Denmark State Grid Shandong Electric Power Company State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (纸本)9781665418195

As the proportion of renewable energy sources increases, the randomness and volatility of the frequency increase, and its dynamic behaviors are becoming more complex. In order to clearly characterize the frequency fluctuation characteristics of the power system, the long-term statistical characteristics are analyzed based on the measured data. The bimodal normal distribution is used, and the measured frequency is decomposed into continuous and short-time-scale components using the moving average method. Based on historical data, the derivation law of the frequency fluctuation characteristics of regional power system is explored, and it is found that the frequency fluctuation characteristics of different regions continue to differentiate, and the characteristics of the sending-end power system frequency being higher than the rated frequency and relatively drastic fluctuations are becoming more and more obvious. © 2022 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Virtual Inertia control Strategy for Photovoltaic Power Generation Based on Improved Incremental Conductance Method 7

Virtual Inertia Control Strategy for Photovoltaic Power Gene...

引用

7th Asia Conference on Power and Electrical Engineering, ACPEE 2022

作者： Gao, Zhimin Cao, Yongji Zhang, Hengxu Qin, Hao Yang, Dong Ma, Huan Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Jinan China Technical University of Denmark Department of Electrical Engineering Kgs. Lyngby Denmark Institute State Grid Shandong Electric Power Company State Grid Shandong Electric Power Research Jinan China

ISBN: (纸本)9781665418195

The large-scale integration of renewable energy units such as wind and photovoltaic power has greatly reduced the equivalent rotational inertia of the power system. PV arrays are static generating elements and have no inertial response without additional control. In order to improve the stability of renewable energy grid operation, this paper proposes a virtual inertia control strategy for photovoltaic power generation by improving the incremental conductance method. This paper firstly introduces the working principle and model of the PV array, and then improves the incremental conductance method based on PI controller to propose PV power generation power reserve control strategy. The PV output is changed for inertial support based on droop control and virtual inertia control by detecting grid frequency changes. Simulation results show that this control strategy results in a better inertial response of the photovoltaic power system. © 2022 IEEE.

关键词： Power control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sensing Modeling of Dielectric Elastomer Sensors Based on GRU Neural Network

Dynamic Sensing Modeling of Dielectric Elastomer Sensors Bas...

引用

IEEE International Conference of intelligent Robotic and control Engineering (IRCE)

作者： Mingyi Zhang Peng Huang Yawu Wang School of Automation China University of Geosciences Wuhan Hubei China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan Hubei China

Dielectric elastomer sensor (DES) is a flexible sensor that can perform free bending deformation, thus it has broad application prospects in the fields of medical electronics, wearable devices, soft robots, etc. Previous studies have mostly focused on exploring the static sensing characteristics of the DES. Considering that the DES may be used in dynamic conditions, it is very meaningful to study its dynamic sensing characteristics to broaden its application ranges. In this paper, a dynamic sensing model of the DES is established based on the gate recurrent unit (GRU) neural network. Firstly, the structure of the DES and the construction of the experimental system are introduced. In addition, the dynamic sensing characteristics of the DES are analyzed by conducting several sets of experiments, which shows that the DES has significant rate-dependent hysteresis nonlinearities, multivalued mapping and memory characteristics. After that, the dynamic sensing model of the DES is built based on the GRU neural network to describe the above dynamic sensing characteristics. Next, the dynamic displacement and force sensing models of the DES are trained according to the dynamic displacement-capacitance and dynamic force-capacitance experimental data, respectively. Finally, several experiments are performed to verify the effectiveness and generalization ability of the established dynamic sensing model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What Matters for 3D Scene Flow Network

arXiv

引用

arXiv 2022年

作者： Wang, Guangming Hu, Yunzhe Liu, Zhe Zhou, Yiyang Tomizuka, Masayoshi Zhan, Wei Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Mechanical Systems Control Laboratory University of California Berkeley United States

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://***/IRMVLab/3DFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

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：