检索结果-内蒙古大学图书馆

Reduction of data amount in data-driven design of linear quadratic regulators

control Theory and technology 2024年第4期22卷 532-542页

作者： Shinsaku Izumi Xin Xin School of Systems Engineering Kochi University of TechnologyKamiKochi782-8502Japan School of Automation Southeast Universityand Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of EducationNanjing210096JiangsuChina

This paper discusses the data-driven design of linear quadratic regulators,i.e.,to obtain the regulators directly from experimental data without using the models of *** particular,we aim to improve an existing design method by reducing the amount of the required experimental *** the data amount leads to the cost reduction of experiments and computation for the data-driven *** present a simplified version of the existing method,where parameters yielding the gain of the regulator are estimated from only part of the data required in the existing *** then show that the data amount required in the presented method is less than half of that in the existing method under certain *** addition,assuming the presence of measurement noise,we analyze the relations between the expectations and variances of the estimated parameters and the *** a result,it is shown that using a larger amount of the experimental data might mitigate the effects of the noise on the estimated *** results are verified by numerical examples.

关键词： Data-driven design Linear quadratic regulators Linear systems Riccati equation Stochastic properties

来源：评论

学校读者我要写书评

暂无评论

Research on Identification Method of Toroidal Propeller

Research on Identification Method of Toroidal Propeller

引用

2024 International Conference on measurement, communication, and Virtual Reality, MCVR 2024

作者： Han, Chuang Hu, Aiai Wu, Haibin Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application Harbin University of Science and Technology Harbin China School of Measurement - Control Technology and Communication Engineering Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781510691773

With the continuous development of marine science and technology, propeller shapes are developing in a more complex direction. Among them, the toroidal propeller represents the latest research progress in propeller technology. This design features a ring-shaped geometry for the blades, which are similar to the catenary curve of a hanging chain. This propeller offers the advantages of higher efficiency and lower noise. In this paper, starting from the geometric shape analysis study of toroidal propeller, we introduce the geometric parameters such as wheelbase, outboard angle, lateral inclination angle among others, derive the mathematical formula of the coordinates of toroidal propeller in detail, simulate the modulation waveform and spectrogram of the toroidal propeller, and compare with those of the ordinary propeller, and according to the experimental data, the geometric shape of toroidal propeller can be recognized by using the proposed method. This lays a firm foundation for further research on the physical properties and scientific problems of toroidal propellers. © 2025 SPIE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Emotion Prediction for Movie and Television scene images

引用

The Journal of China Universities of Posts and Telecommunications 2024年第3期31卷 43-55页

作者： Su Zhibin Zhou Xuanye Liu Bing Ren Hui State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijing 100024China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of ChinaBeijing 100024China School of Information and Communication Engineering Communication University of ChinaBeijing 100024China

For the task of content retrieval,analysis and generation of film and television scene images in the field of intelligent editing,fine-grained emotion recognition and prediction of images is of great *** this paper,the fusion of traditional perceptual features,art features and multi-channel deep learning features are used to reflect the emotion expression of different levels of the *** addition,the integrated learning model with stacking architecture based on linear regression coefficient and sentiment correlations,which is called the LS-stacking model,is proposed according to the factor association between multi-dimensional *** experimental results prove that the mixed feature and LS-stacking model can predict well on the 16 emotion categories of the self-built image *** study improves the fine-grained recognition ability of image emotion by computers,which helps to increase the intelligence and automation degree of visual retrieval and post-production system.

关键词： fine-grained emotion prediction movie and television scene images stacking model linear regression

来源：评论

学校读者我要写书评

暂无评论

Combined Classification of Hyperspectral and LiDAR Data based on Dual-Channel Cross-Transformer 5

Combined Classification of Hyperspectral and LiDAR Data base...

引用

5th International Conference on Video, Signal and Image Processing, VSIP 2023

作者： Zhou, Binbin Wang, Qingyan Zhang, Junping Wang, Yujing School Of: Measurement-Control And Communication Engineering Harbin University Of Science And Technology Harbin150080 China School Of: Electronics And Information Engineering Harbin Institute Of Technology Harbin150001 China

ISBN: (纸本)9798400709272

In the face of complex scenes, single-modal dominant classification tasks encounter limitations in performance due to insufficient information. On the other hand, joint classification of multimodal remote sensing data faces challenges such as data sample differences and lack of correlation in physical features between modalities, which can impact classification performance. To fully integrate the heterogeneous information of multimodal data and improve classification performance, we propose a dual-channel cross-transformer feature fusion extraction network. The framework leverages self-attention mechanisms to aggregate features within each modality, and the feature fusion module based on cross-modal attention fully considers the complementary information between modalities. Classification tasks are performed using the fused spatial-spectral features obtained from the joint representation of modalities. Extensive experiments conducted on the Houston and MUUFL datasets demonstrate the effectiveness of the proposed model compared to existing methods. © 2023 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Design of Double-Loop Current Transformer Based on Magnetic Field Incomplete Cancellation

引用

CSEE Journal of Power and Energy Systems 2025年第2期11卷 772-782页

作者： Wenbo Li Xiaojun Tang Youshui Lu Ling Yan Yi Wu Mingzhe Rong Department of Measurement and Control Technology&Instrumentation School of Electrical EngineeringXi'an Jiaotong UniversityXi'an 710000China State Key Laboratory of Electrical Insulation&Power Equipment School of Electrical EngineeringXi'an Jiaotong UniversityXi'an 710000China

Electromagnetic current transformer is one of the important pieces of equipment used in AC power system measurement. Due to continuous improvement of current level to be measured in the power system, ordinary single-loop magnetic core structure cannot meet industrial needs of wide measuring range with high accuracy, while it even has a magnetic saturation problem when measured current is reaching the limit. Most existing methods expand measuring range and increase antisaturation ability of the magnetic core by either opening an air gap in the magnetic core or increasing number of turns of primary and secondary windings, but it will bring additional problems such as volume and heat dissipation of the transformer. To solve such issues, in this paper, we proposed a magnetic core structure of double-loop current transformer based on incomplete magnetic field cancellation principle. Calculation formula of air gap size and theoretical error are analyzed. We provide a theo-retical analysis of working characteristics, amplitude error and phase error throughout a three-dimensional simulation model of transformer. In addition, we evaluate performance through a series of comparison experiments. Results demonstrate our double-loop current transformer can maintain good linear relationship between primary and secondary current while ensuring measurement accuracy at 0.2 level. With the same volume, it has a wider range of rated current measurements and a certain anti-saturation ability.

关键词： Current difference coefficient double-loop core incomplete magneticfield cancellation

来源：评论

学校读者我要写书评

暂无评论

Remaining Life Prediction Method of Rolling Bearing Based on TD3 Optimization Model Updating Strategy 16

Remaining Life Prediction Method of Rolling Bearing Based on...

引用

16th IEEE International Conference on Electronic measurement and Instruments, ICEMI 2023

作者： Wang, Yujing Jiao, Guangpeng Kang, Shouqiang Xie, Jinbao Sun, Yulin School of Measurement-Control and Communication Engineering Harbin University of Science and Technology Harbin China School of Physics and Electronic Engineering Hainan Normal University Haikou China

ISBN: (纸本)9798350327144

To address the problems of model degradation and low prediction accuracy in the of update procedure the rolling bearing life prediction model, the updating strategy of twin delayed deep deterministic policy gradient(TD3) is suggested to optimize the prediction model, and it applied to rolling bearing remaining useful life prediction. Continuous wavelet transform is used to build a dataset by converting the rolling bearing vibration data into two-dimensional time-frequency spectrum diagram. Deep reinforcement learning is introduced to design the elements of state, action, reward value and loss function, which are employed to training of the prediction model, this model is composed convolutional neural network (CNN) and bidirectional long short-term memory. The delayed update and soft update techniques of the TD3 algorithm are used to reduce the update frequency of the CNN feature network. A new loss function is proposed to establish a new model updating strategy for solving the prediction model degradation problem. The experimental study using the PHM2012 dataset and the finding indicate that, in comparison to the compared methodologies, the suggested prediction method with model optimization strategy can reduce the root mean square error and mean square error by more than 23.8% and 20.8% respectively, reducing the prediction error by at least 18.6% and improve the scores by more than 0.213. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Multi-Pedestrian Tracking by Decoupling Confidence Weighting and Hierarchical Appearance Embedding Updates 4

Multi-Pedestrian Tracking by Decoupling Confidence Weighting...

引用

4th International Conference on communication technology and Information technology, ICCTIT 2024

作者： Zeng, Guopei Wang, Luping Sun Yat-sen University School of Electronics and Communication Engineering Shenzhen China Zhejiang Aerospace Runbo Measurement and Control Technology Co. Ltd Zhejiang China

ISBN: (纸本)9798331528973

The advent of powerful object detectors has led to the widespread adoption of the 'tracking-by-detection' paradigm in multi-object tracking (MOT). However, challenges such as association errors during occlusions continue to hinder tracking performance. To address this issue, we propose three key improvements. First, we leverage the confidence scores generated by a detector with decoupled heads to weight the cost matrix. Second, we introduce a height-constrained intersection-over-union (IoU) distance metric. Finally, we classify the appearance features of objects in the current frame into two levels - high and low - based on their respective confidence scores. These features are then matched and updated against stored appearance embeddings from previous frames. Extensive comparative and ablation experiments conducted on the MOT17 dataset demonstrate that the proposed method significantly improves tracking performance in multi-object tracking scenarios. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Research on the variation of dielectric properties of oil-paper insulation for power equipment over a wide temperature range

引用

High Voltage 2024年第3期9卷 648-658页

作者： Mingze Zhang Muhe Yu Wen Zhou Yilin Liang Shengjie Lei Yunbo Shi Limin Qu Key Laboratory of Engineering Dielectrics and Its Application Ministry of Education Harbin University of Science and TechnologyHarbinChina School of Measurement and Communication Engineering Harbin University of Science and TechnologyHarbinChina Electric Power Research Institute State Grid Heilongjiang Electric Power Company LimitedHarbinChina

The main part of oil-immersed power equipment is oil-paper *** lower ambient temperatures,transformer oil will become *** a result,compared to those at room temperature or operating temperature,the frequency domain dielectric properties of oil-paper insulation at low temperatures are drastically *** evaluating the insulation condition of electrical equipment,it is essential to accurately determine their dielectric *** paper described the FDS test,the DC conductivity test,and the transformer oil viscosity test,which was carried out in a laboratory environment for different ageing of oil-immersed pressboard and transformer oil at 233–373 *** ef-fects of temperature on the dielectric properties at the competing mechanisms of polarisation and conductivity loss were clarified based on variations of the FDS *** the viscosity change of ageing transformer oil at low temperatures,the Arrhenius and VFT viscosity equations were used to achieve a fitting calculation in the different temperature *** on the molecular/ion transition model in the force field and electric field,the characterisation relationships between the dynamic viscosity,DC conductivity,and test temperature of transformer oil were *** limita-tions of conventional transformer oil equivalent dielectric relaxation models over a wide temperature range were finally clarified by combining the test findings of the DC con-ductivity over a wide temperature range with observed and simulated *** paper provides an essential theoretical reference when using the FDS test to diagnose the insulation performance of oil-immersed power equipment in extremely cold regions.

关键词： insulation viscosity immersed

来源：评论

学校读者我要写书评

暂无评论

Contrastive Clustering for Unsupervised Recognition of Interference Signals

引用

Computer Systems Science & engineering 2023年第8期46卷 1385-1400页

作者： Xiangwei Chen Zhijin Zhao Xueyi Ye Shilian Zheng Caiyi Lou Xiaoniu Yang The School of Communication Engineering Hangzhou Dianzi UniversityHangzhou310018China The Science and Technology on Communication Information Security Control Laboratory Jiaxing314001China

Interference signals recognition plays an important role in anti-jamming *** the development of deep learning,many supervised interference signals recognition algorithms based on deep learning have emerged recently and show better performance than traditional recognition ***,there is no unsupervised interference signals recognition algorithm at *** this paper,an unsupervised interference signals recognition method called double phases and double dimensions contrastive clustering(DDCC)is ***,in the first phase,four data augmentation strategies for interference signals are used in data-augmentation-based(DA-based)contrastive *** the second phase,the original dataset’s k-nearest neighbor set(KNNset)is designed in double dimensions contrastive *** addition,a dynamic entropy parameter strategy is *** simulation experiments of 9 types of interference signals show that random cropping is the best one of the four data augmentation strategies;the feature dimensional contrastive learning in the second phase can improve the clustering purity;the dynamic entropy parameter strategy can improve the stability of DDCC *** unsupervised interference signals recognition results of DDCC and five other deep clustering algorithms show that the clustering performance of DDCC is superior to other *** particular,the clustering purity of our method is above 92%,SCAN’s is 81%,and the other three methods’are below 71%when jammingnoise-ratio(JNR)is−5 *** addition,our method is close to the supervised learning algorithm.

关键词： Interference signals recognition unsupervised clustering contrastive learning deep learning k-nearest neighbor

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Robotic Assembly Method for Large Planar Workpieces Using Laser Displacement Sensors and Monocular Vision

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第17期49卷 155-172页

作者： Cao, Xiaobing Xu, Yicen Yao, Yonghong Chen, Sheng School of Control Technology Wuxi Institute of Technology Wuxi Jiangsu214121 China School of Intelligent Equipment and Automotive Engineering Wuxi Institute of Commerce Wuxi Jiangsu214153 China School of Communication and Electronic Engineering East China Normal University Shanghai200062 China

To address the challenges associated with large planar workpieces, such as the side window glass of a train, this paper proposes a practical, intelligent robotic assembly method that utilizes laser displacement sensors (LDSs) and monocular vision. The laser point cloud data is fitted to the equation of the plane of the side window optimally, allowing for the calculation of its plane coefficients and unit normal vector (UNV) using the Lagrange multiplier method. The robot's end flange is adjusted to ensure the camera imaging plane is along with the window plane at a specified distance. Monocular vision is employed to capture the pose features of the upper right corner of the window, facilitating a compensation method for precise assembly. The experimental results show that the robot achieved a positioning accuracy of less than 0.5mm and an orientation accuracy within 1 degree, confirming the effectiveness of the proposed method. In the experiment, the maximum displacement deviation in the X direction is about ± 0.4mm, the maximum offset in the Y and Z directions is about ± 0.3mm, the maximum rotation deviation in the X axis is about 0.6 °, and the minimum rotation deviation in the Y axis is about 0.8 °. All deviations meet the requirements of ± 1 ° attitude correction and ± 0.5mm displacement accuracy, and have good reliability. This method solves the practical problem of assembling large planar workpieces with integrated LDS and monocular vision. This technology involves using laser point cloud data to fit the precise plane equation of the window, determining alignment parameters through Lagrange multiplier method, and adjusting the posture of the end flange of the robot. Monocular vision further assists in extracting positional features, achieving precise real-time posture correction and alignment. This system proposes an effective and low-cost automation that reduces manual intervention and alleviates typical problems of remote processing of large workpieces. © 20

关键词： Lagrange multipliers

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：