检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Fabian Immel Alessandro Moia Haohao Hu Intelligent Systems and Production Engineering FZI Research Center for Information Technology Karlsruhe Germany Robert Bosch GmbH Gerlingen-Schillerhoehe Germany Institute of Measurement and Control Systems Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

This work proposes NavPathNet, a graph neural network based trajectory prediction system capable of accurately predicting the trajectory of a two-wheeler with onboard sensors for up to 6 seconds using the vehicle state and only navigation map information. Possible paths are generated from the local road network in a regular navigation map using Bézier curves and a multimodal prediction captures the different possibilities of the road network. A kinematic model integrated into the network allows to give guarantees on physical realism and on motion constraints, essential for safety-relevant *** proposed system was trained and evaluated on an in-house e-bike data set and was able to reach a top 1 final displacement error of 2 m for four seconds and 3.8 m for six seconds of prediction time, significantly outperforming other baselines. The improvement in prediction quality compared to purely physical models opens up new possibilities for driver assistance systems in connected vehicles.

关键词： Connected vehicles Navigation Intelligent vehicles Roads Kinematics Predictive models Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deployment Method to Improve the Generalizability of Recurrent Neural Network

A Deployment Method to Improve the Generalizability of Recur...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Yi Hu Shuai Han Shiji Wang Cheng Li Communication Research Center Harbin Institute of Technology China Beijing Aerospace Measurement & Control Technology CO.LTD Beijing China Faculty of Engineering and Applied Science Memorial University Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The widespread adoption of deep learning models has inspired an urgent need for their generalization capabilities. Despite their impressive performance on training data, achieving high accuracy on deployed untouched data remains a daunting challenge. To address this problem, improving the model’s adaptability to new samples is imperative. In this paper, we delve into the metrics of deep learning models, pointing out that the upper bound of the generalization error is a quantitative measure of their generalization ability. Outlining methods to enhance this ability, we subsequently improve the LSTM model for modulation recognition using the identified upper bound on the generalization error and the outlined enhancement strategy, significantly improving the accuracy. Finally, an outlook on future research is provided.

关键词： Deep learning Wireless communication Adaptation models Upper bound Accuracy Recurrent neural networks measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Particle manipulation behind a turbid medium based on the intensity transmission matrix

引用

Photonics Research 2022年第10期10卷 2293-2301页

作者： KAIGE LIU HENGKANG ZHANG SHANSHAN DU ZEQI LIU BIN ZHANG XING FU QIANG LIU Key Laboratory of Photonics Control Technology Ministry of EducationTsinghua UniversityBeijing 100084China Department of Precision Instrument State Key Laboratory of Precision Measurement Technology and InstrumentsTsinghua UniversityBeijing 100084China Beijing Institute of Control Engineering Beijing 100190China Beijing Institute of Electronic System Engineering Beijing 100854China

Although optical tweezers can manipulate tiny particles,the distortion caused by the scattering medium restricts their ***-shaping techniques such as the transmission matrix(TM)method are powerful tools to achieve light focusing behind the scattering *** this paper,we propose a method to focus light through a scattering medium in a large area based on the intensity transmission matrix(ITM).Only relying on the intensity distribution,we can calculate the ITM with the number of measurements equal to that of the control *** of the diffraction limit,our method guarantees high energy usage of the light *** on this method,we have implemented particle manipulation with a high degree of freedom on single and multiple *** addition,the manipulation range is enlarged more than 20 times(compared to the memory effect)to 200μm.

关键词： scattering matrix intensity

来源：评论

学校读者我要写书评

暂无评论

A Double Node Thin-Film Thermocouples for In-Situ measurement

A Double Node Thin-Film Thermocouples for In-Situ Measuremen...

引用

2022 International Conference on Automation, Robotics and Computer engineering, ICARCE 2022

作者： Ma, Rong Zhang, Meiju Zhang, Zhongkai Huang, Manguo Liang, Xiaobo Liu, Jiangjiang Liu, Zhaojun Tian, Bian Xi'An Jiaotong University State Key Laboratory for Mechanical Manufacturing Systems Engineering Xi'an China Aviation Key Laboratory of Science and Technology on Special Condition Monitoring Sensor Technology Beijing Changcheng Aeronautic Measurement and Control Technology Research Institute Beijing China

ISBN: (纸本)9781665475488

The design, fabrication, testing and implementation of a new high-performance tungsten-rhenium thin film thermocouple are introduced. In this paper, tungsten-rhenium TFTCs are taken as the research object, after simulation analysis in COMSOL software and design, it is made by screen-printing technology and magnetron sputtering. This kind of thin film thermocouple primarily utilizes two kinds of electrode materials with varying composition combination, mainly tungsten with 5% rhenium and tungsten with 26% rhenium. Furthermore, high-temperature annealing is performed to maintain the mechanical properties and thus improve thermoelectric performance. The results demonstrate that the performance is reliable in the temperature range of 150-600 C° with a repeatability of 2.02%, providing application value for high-temperature in-situ sensing. © 2022 IEEE.

关键词： Thermocouples

来源：评论

学校读者我要写书评

暂无评论

A long prediction horizon fcs-mpc algorithm with disturbance preview for three-phase inverters

A long prediction horizon fcs-mpc algorithm with disturbance...

引用

2023 Jiangsu Annual Conference on Automation, JACA 2023

作者： He, Xianghui Huang, Saijin Li, Guanjun Li, Haoyuan Wang, Xiangyu School of Automation Southeast University No. 2 Si Pai Lou Nanjing Jiangsu210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China Jiangsu Engineering Technology Research Center for Energy Storage Conversion Application China Electric Power Research Institute Nanjing Jiangsu210003 China

ISBN: (纸本)9781839539848

This paper derives an efficient control algorithm to deal with the output voltage tracking control problem of threephase inverters with multiple disturbances (including parametric perturbations of filter, abrupt disturbances caused by load switching and harmonic disturbances brought by unbalanced loads and nonlinear loads). This accomplishment is realized through the long prediction horizon finite-control-set model predictive control (FCS-MPC) and the integration of a composite disturbance observer (CDO) and a disturbance preview model into the sphere decoding algorithm (SDA). This integration facilitates the estimation and prediction of future disturbance behaviors within the inverter system, which addresses the poor disturbance-rejection limitations inherent in conventional SDA approaches employed in previous studies. The algorithm also improves the dynamic performances of the output voltage. Simulations studies are illustrated to demonstrate the feasibility and effectiveness of the proposed control algorithm. Based on the presented results, the algorithm achieves good disturbance rejection capability and maintains small tracking error. © The Institution of engineering & technology 2023.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

One-Shot Three-Dimensional measurement Based on Spectral Interferometry Using a Digital Micromirror Device

One-Shot Three-Dimensional Measurement Based on Spectral Int...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Jinxu Zhang Liheng Shi Yingying Gu Donglai Zhang Lu Yin Guanhao Wu Department of Precision Instrument State Key Laboratory of Precision Measurement Technology and Instruments Tsinghua University Beijing China Space Optoelectronic Measurement and Perception Lab. Beijing Institute of Control Engineering Beijing China National Key Laboratory of Space Intelligent Control China Academy of Space Technology Beijing China

We present a one-shot 3D spectral interferometry technique using a digital micromirror device. By encoding the distribution of the spatial light field, this approach enables 3D imaging of step structures within 27 ms.

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Optical interferometry Three-dimensional displays Imaging Surface emitting lasers measurement by laser beam Encoding Microcavities

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Strategy for Electric Vehicle Charging Considering Wind Power Fluctuation

引用

Journal of engineering Science and technology Review 2021年第3期14卷 103-110页

作者： Yang, Anyun Sun, Hongbin Zhang, Xiao School of Electrical Engineering Changchun Institute of Technology Changchun130012 China National and Local Joint Engineering Research Center for Smart Distribution Network Measurement Control and Safe Operation Technology Changchun130012 China Department of Energy Technology Aalborg University Aalborg East9220 Denmark

Electric vehicles (EVs) can inhibit the wind power fluctuations in the generalized form of energy storage. However, optimizing the charging process of EVs under wind power fluctuations is difficult because of the uncertainties of wind power output and user demands. A charging control strategy based on deep reinforcement learning (DRL) was proposed in this study to address the influence brought by uncertain environmental factors to the control. This strategy mined the deep relation between perceiving the uncertainties of environmental factors and learning charging laws by virtue of the perceptual and learning abilities of DRL. An immediate reward mechanism that acts upon the environment was constructed from the angle of neural network fitting function. The EV charging control model was expressed as a Markov decision process (MDP) that contain the state, action, and transfer functions and reward and discount factors through temporal discretization. Next, the single-step updating and experience replay mode were combined to construct the DRL algorithm, followed by the comparative convergence experiment with the reinforcement learning (RL) algorithm that expressed the reward function in mathematical form. In the end, the agent obtained through training was used for the verification of the calculated example. Results show that the constructed RL algorithm is converged by 8,500 episodes earlier. The charging control strategy based on DRL meets the charging requirements when the proportion of optimization objectives is 0.5 and 0.9, and users are allowed to change the allowed charging time temporarily. This study demonstrates that the charging control strategy based DRL can optimize the EVs charging process under many uncertain factors. © 2021 School of Science, IHU. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Constraint-Following Based Adaptive Robust control for Underactuated Mechanical Systems

Constraint-Following Based Adaptive Robust Control for Under...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Cui Wei Ye-Hwa Chen Yanling Wei Institute of Intelligent Manufacturing Nanjing Tech University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta GA USA Key Laboratory of Measurement and Control of Complex System of Engineering School of Automation Southeast University Nanjing China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

This paper introduces an adaptive robust control approach tailored for underactuated mechanical systems encountering matched and mismatched uncertainty, employing a constraint-following methodology. The control strategy unfolds in two phases: initially, a nominal control scheme is devised neglecting uncertainty and deviations in initial conditions from constraints. Subsequently, uncertainty is categorized into matched and mismatched components, ensuring that mismatched uncertainties remain unobservable. Leveraging the structural characteristics of the uncertainty bound, a novel segmented adaptive law is proposed and seamlessly integrated into the adaptive robust control framework. By employing the Lyapunov minimax approach, the method ensures uniform boundedness and uniform ultimate boundedness simultaneously, thereby ensuring approximate adherence to constraints for underactuated mechanical systems facing both matched and mismatched uncertainties alongside initial condition deviations.

关键词： Robust control Uncertainty Adaptive systems Costs Automation Nonlinear dynamical systems Mechanical systems Closed loop systems Robots

来源：评论

学校读者我要写书评

暂无评论

Low-carbon economic dispatch of integrated energy system with carbon capture power plant and multiple utilization of hydrogen energy

引用

Frontiers in Energy Research 2024年 12卷

作者： Wang, Jiarui Ji, Xiu Meng, Xiangdong Bai, Yang Li, Meiyue State Grid Jilin Electric Power Co. Ltd. Changchun China National Local Joint Engineering Research Center for Smart Distribution Grid Measurement and Control with Safety Operation Technology Changchun Institute of Technology Changchun China

In the context of "dual carbon", in order to promote the consumption of renewable energy and improve energy utilization efficiency, a low-carbon economic dispatch model of an integrated energy system containing carbon capture power plants and multiple utilization of hydrogen energy is proposed. First, introduce liquid storage tanks to transform traditional carbon capture power plants, and at the same time build a multi-functional hydrogen utilization structure including two-stage power-to-gas, hydrogen fuel cells, hydrogen storage tanks, and hydrogen-doped cogeneration to fully exploit hydrogen. It can utilize the potential of collaborative operation with carbon capture power plants;on this basis, consider the transferability and substitutability characteristics of electric heating gas load, and construct an electric heating gas comprehensive demand response model;secondly, consider the mutual recognition relationship between carbon quotas and green certificates, Propose a green certificate-carbon trading mechanism;finally establish an integrated energy system with the optimization goal of minimizing the sum of energy purchase cost, demand response compensation cost, wind curtailment cost, carbon storage cost, carbon purchase cost, carbon trading cost and green certificate trading compensation. Optimize scheduling model. The results show that the proposed model can effectively reduce the total system cost and carbon emissions, improve clean energy consumption and energy utilization, and has significant economical and low-carbon properties. Copyright © 2025 Wang, Ji, Meng, Bai and Li.

关键词： Carbon capture and storage

来源：评论

学校读者我要写书评

暂无评论

Grip strength forecast and rehabilitative guidance based on adaptive neural fuzzy inference system using sEMG

引用

Personal and Ubiquitous Computing 2022年第4期26卷 1215-1224页

作者： Jiang, Du Li, Gongfa Sun, Ying Kong, Jianyi Tao, Bo Chen, Disi Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Institute of Precision Manufacturing Wuhan University of Science and Technology Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China School of Computing University of Portsmouth PortsmouthPO1 3HE United Kingdom

In order to resolve the problem of unstable control of force in human–computer interaction based on surface EMG signals, the adaptive neural fuzzy inference system is designed to achieve the grip strength assessment. As we know, the acquisition of surface EMG signal is non-invasive, which provides a better evaluation index for rehabilitation training in the medical process. By establishing the relationship between grip force and surface electromechanical signals, the effect of rehabilitation training can be evaluated directly while reducing the types of sensors used. Firstly, the experimental equipment are introduced, which are utilized to carry out simultaneous acquisition of surface EMG signals and forces. Then, the traditional features of sEMG and the corresponding algorithms are illustrated, based on this, supplementing the energy eigenvalue with wavelet analysis and fuzzy entropy. In which, fuzzy entropy is effective in characterizing muscle fatigue that can effectively reduce the impact of muscle fatigue on force assessment. Finally, combining fuzzy logic implication and neural network, the adaptive neural fuzzy inference system is designed, which is trained by extracted feature vectors. The experimental result shows the method used in this paper can effectively predict the grip force. Further, force prediction based on sEMG can be used to guide rehabilitation therapy in virtual space, combined with an electrical stimulator. © 2019, Springer-Verlag London Ltd., part of Springer Nature.

关键词： Eigenvalues and eigenfunctions

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：