检索结果-内蒙古大学图书馆

2023 China Automation Congress, CAC 2023

作者： Liu, Ruohan Ren, Chunping Li, Degen Liu, Yongli School of Electrical and Control Engineering Safety Engineering College Heilongjiang University of Science and Technology Harbin China School of Mechanical Engineering Heilongjiang University of Science and Technology Harbin China Heilongjiang University of Science and Technology Academic Theory Research Department Harbin China School of Mining Engineering Heilongjiang University of Science and Technology Harbin China

ISBN: (纸本)9798350303759

In order to improve the response speed and control accuracy of the tunneling machine control system, and to address the limitations of traditional algorithms that are prone to falling into local extremum and weak generalization ability during the solving process, a PSO-BP neural network PID adaptive control method for tunneling machines is proposed. The weights of the BP neural network are optimized by the global search ability of the PSO algorithm. The neural network outputs the fitness values of the PID parameters, and the initial weights of the neural network are updated. The PID parameters are adjusted in realtime. The results show that the unit Step response curve of the system reaches the stable state of the system after 0.85 s in the traditional PID control, while the PSO-BP neural network PID controller only needs 0.4 s to be stable, and the overshoot of the PSO-BP neural network PID controller is far less than that of the traditional PID controller. Therefore, the PSO BP neural network PID controller has good dynamic and static characteristics, which can maximize the generalization ability of the traditional BP neural network and ensure the Rate of convergence and learning ability. © 2023 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Numerical study on aero-optical imaging deviations of vehicles at different altitudes

引用

Optoelectronics Letters 2022年第2期18卷 97-102页

作者： XU Liang ZHANG Ziye WANG Tao WU Jianhui CHEN Xi Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems School of Electrical Engineering and AutomationTianjin University of TechnologyTianjin 300384China School of Intelligent Systems Engineering Sun Yat-sen UniversityGuangzhou 510006China China Academy of Launch Vehicle Technology Beijing 100076China

When the vehicle is flying in the atmosphere at high speed, the optical head and the atmosphere will have severe friction, thus forming a complex flow field, which makes the target image shift in the optical imaging system. The influence of altitude on aero-optical imaging deviation is studied in this paper. The geometric modeling and mesh generation of a typical blunt nosed high-speed vehicle were carried out, and the three-dimensional(3 D) flow field density was obtained by a large amount of computational fluid dynamic calculation. In order to complete the optical calculation, the backward ray tracing method and the backward ray tracing stop criterion were used. The results show that as the height increases, the imaging deviation decreases gradually, and the imaging deviation slope increases and tends to be flat and close to zero.

关键词： calculation deviation backward

来源：评论

学校读者我要写书评

暂无评论

Chaos Suppression of Power System Based on Finite-time Adaptive Sliding Mode control 20

Chaos Suppression of Power System Based on Finite-time Adapt...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Wang, Hongjun Li, Shuyi Zhao, Hui Yue, Youjun Tianjin University of Technology Key Laboratory of Control Theory and Application for Complex Systems in Tianjin Binshui Xidao Extension 391 Tianjin300384 China Tianjin Agricultural University College of Engineering and Technology 22 Jinjing Road Tianjin300384 China

ISBN: (纸本)9798350320831

Under certain conditions, the power system will produce chaotic oscillation, which may impact the safety and stability of the power grid. Under the action of inductive load, the power system will generate a certain amount of reactive power. Excessive reactive power will lead to the deviation of the voltage phase angle of the power system. Usually, reactive compensation equipment is used to absorb the reactive power in the power system and adjust the voltage phase angle. In this article, the dynamics analysis of chaotic oscillation of the second-order power system model (SOPSM) is firstly carried out, and a global adaptive sliding mode controller based on finite time is designed by comprehensively using backstepping, fixed-time controller and adaptive sliding mode control methods (ASM), which not only realizes the suppression of chaotic oscillation of the power system, but also reduces the computational burden and improves the convergence speed of the system, Finally, MATLAB/Simulink numerical simulation shows that the designed controller can quickly restore the power system from chaotic state to equilibrium state, thus verifying the effectiveness and efficiency of the controller. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG signals based on CNN-Transformer model 20

Classification of EEG signals based on CNN-Transformer model

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Liu, Jianwei Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Brain-computer interfaces (BCI) based on EEG have attracted extensive research and attention worldwide, while motor imagery (MI), mental arithmetic (MA), and P300 event-related potentials are a few of the more commonly used *** Transformer(ViT) is a new Transformer model that has superior global processing power compared to Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).In this study, we propose a hybrid CNN-Transformer based model that uses CNN to convolve EEG signals in time and space, followed by ViT for global processing, and finally optimizes the model using 10-run × 10-fold cross-validation and validates it on a publicly available dataset of 29 subjects. Final accuracies of 87.23% and 90.79% were achieved on the MI and MA tasks, respectively. Compared to other literature, the model achieved higher classification accuracies. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Fatigue Driving Detection of EEG Signals by LSTM Deep Neural Network with LPSD and DE 20

Fatigue Driving Detection of EEG Signals by LSTM Deep Neural...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Zhang, Hao Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Fatigue driving detection has always been an urgent social problem to be solved, and many complex factors increase the difficulty of detection. Nowadays, more scholars choose to use multi-channel EEG signals for fatigue detection, which is accompanied by the development of deep learning networks. Here, we propose the deep Long Short Term Memory (LSTM) neural network with the Differential Entropy (DE) and Logarithm Power Spectrum Density (LPSD). We first divide the EEG signal into 8-s Hanning windows with 50% overlap, and then use the Short Time Fourier Transform(STFT) on the extracted time window to obtain 50 frequency sub-bands. Finally, LPSD and DE features are extracted from the frequency offspring obtained from the STFT and input into the deep LSTM neural network. The network can choose to learn more task related information by adding soft attention and extract effective time information from EEG signals,thereby improving the model's performance in detecting driving fatigue. In addition, we also collected EEG signals from 8 subjects in both awake and fatigued states,and used the PERCLOS index to judge the degree of fatigue. Using the collected dataset, we compared the effectiveness of the deep LSTM neural network with five other methods. The results indicate that the deep LSTM neural network has a better classification accuracy of 93.12%. It proves that the network has good performance in fatigue detection of EEG signals. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Predictive Path-following control for Tilt-quadrotor UAV based on Fully-actuated System Approaches

Predictive Path-following Control for Tilt-quadrotor UAV bas...

引用

Fully Actuated System theory and Applications (CFASTA), Conference on

作者： Lixue Xu Xiubo Wang Ping He Yan Wang Department of Control Science and Engineering Harbin Institute of Technology Harbin P. R. China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin P. R. China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This study focuses on predictive path-following control (PPFC) for a tilt-quadrotor UAV based on fully-actuated system (FAS) approaches. Rooted in the fundamental principle of tilt-quadrotor UAV model mechanics, the dynamic model of the tilt-quadrotor UAV is derived into a FAS model with multiple degree of freedoms. Concurrently, the PPFC-FAS control scheme is proposed for tilt-quadrotor UAV path-following, the path-following problem is transformed into a trajectory tracking problem with the tilt-quadrotor FAS model and parameterized path. If the cost function and the penalty function in the predictive performance index satisfies the certain conditions, the convergence of path-following errors is guaranteed. Finally, the simulation results verify the effectiveness and efficiency of the proposed PPFC-FAS control scheme.

关键词： Trajectory tracking Simulation Reliability theory Autonomous aerial vehicles Trajectory Performance analysis Indexes

来源：评论

学校读者我要写书评

暂无评论

control of Proton Exchange Membrane Fuel Cell Intake System:A High-Order Fully Actuated System Approach

Control of Proton Exchange Membrane Fuel Cell Intake System:...

引用

第43届中国控制会议

作者： Ganxin Li Fuxing Yao He Kong Yahui Zhang Jinwu Gao Yunfeng Hu Xiaohong Jiao Guilin Wen State Key Laboratory of Crane Technology Yanshan University Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern Uni.of Sci.and Tech. Department of Control Science and Engineering Jilin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The air supply system of the proton exchange membrane fuel cell(PEMFC) has complex characteristics such as multiple inputs and multiple outputs, strong nonlinear coupling, and internal and external disturbances. controlling the airflow and cathode pressure in coordination is a great challenge. To deal with this challenge, this paper designs a novel strategy based on high-order fully actuated(HOFA) systems theory. First, the fourth-order underactuated system of PEMFC is transformed into an HOFA system, and an extended state observer is designed to estimate unmodeled dynamics and unknown disturbances and then, based on the characteristics of the HOFA system, a parametric control law is designed to control the airflow and cathode pressure in coordination. Finally, the effectiveness of the HOFA system is validated on a PEMFC air supply system test bench,and the results suggest that our designed strategy can realize accurate and coordinated control of the airflow and cathode pressure,outperforming some existing advanced methods.

关键词： Proton exchange membrane fuel cell Air supply control High-order fully actuated system approaches Extended state observer

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification of Riemannian Tangent Spaces Based on MI-BCI 20

Machine Learning Classification of Riemannian Tangent Spaces...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Zhao, Chunli Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Motor imagery brain-computer interfaces (BCIs) have been extensively used in stroke rehabilitation, particularly in China where stroke incidence is high. The application of BCI to control prostheses and robotic arms has shown promising results in improving the quality of life for stroke patients. However, a major challenge in this field is improving the accuracy of motor imagery (MI) classification. Several previous studies have reported that stroke patients exhibit atypical patterns of even-trelated desynchronization (ERD) and event-related synchronization (ERS) activation during motor imagery (MI) tasks. It has been suggested that the brain regions affected by stroke may show reduced excitability and relative insensitivity to external interference compared to those of healthy individuals. Therefore, this study proposes that the classification accuracy of stroke patients in the same MI task would be higher compared to that of healthy volunteers. In this study, we employed a feature extraction algorithm that combines the Filter Bank Common Spatial Pattern (FBCSP) and Riemann geometric mean distance methods to compare the classification accuracy of five different classifiers, with the objective of identifying the most suitable classifier for our analysis. The obtained results revealed that the K-Nearest Neighbors (KNN) classifier yielded the highest accuracy, reaching 87.5% for stroke patients and 85% for healthy volunteers, respectively. In addition to accuracy, we also utilized Kappa values as evaluation metrics, which yielded Kappa results of 0.619 and 0.613 for stroke patients and healthy volunteers, respectively. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis of control moment gyroscope based on a new CNN scheme using attention-enhanced convolutional block

引用

Science China(Technological Sciences) 2022年第11期65卷 2605-2616页

作者： ZHAO HaoTian LIU Ming SUN YiYong CHEN Zhang DUAN GuangRen CAO XiBin Research Center of Satellite Technology School of AstronauticsHarbin Institute of TechnologyHarbin 150001China School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China Department of Automation TsinghuaUniversityBeijing 100084China Control Theory and Guidance Technology School of AstronauticsHarbin Institute of TechnologyHarbin150001China

control moment gyroscope(CMG)is a typical attitude control system component for satellites and mobile robots,and the online fault diagnosis of CMG is crucial because it determines the stability and accuracy of the attitude control *** paper develops a data-driven CMG fault diagnosis scheme based on a new CNN *** this design,seven types of fault signals are converted into spectrum datasets through short-time Fourier transformation(STFT),and a new CNN network scheme called AECB-CNN is proposed based on attention-enhanced convolutional blocks(AECB).AECB-CNN can achieve high training accuracy for the CMG fault diagnosis datasets under different sliding window ***,simulation results indicate that the proposed fault diagnosis method can achieve an accuracy of nearly 95%in 1.28 s and 100%in 2.56 s,respectively.

关键词： fault diagnosis control moment gyroscope CNN scheme attention-enhanced convolutional block

来源：评论

学校读者我要写书评

暂无评论

Model predictive control for autonomous ground vehicles:a review

引用

Autonomous Intelligent Systems 2021年第1期1卷 32-48页

作者： Shuyou Yu Matthias Hirche Yanjun Huang Hong Chen Frank Allgöwer State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China Department of Control Science and Engineering Jilin UniversityChangchunChina Institute for Systems Theory and Automatic Control University of StuttgartPfaffenwaldring 9Stuttgart 70569Germany Institute of Intelligent Vehicles Tongji UniversityShanghaiChina College of Electronic and Information Engineering Tongji UniversityShanghaiChina

This paper reviews model predictive control(MPC)and its wide applications to both single and multiple autonomous ground vehicles(AGVs).On one hand,MPC is a well-established optimal control method,which uses the predicted future information to optimize the control actions while explicitly considering *** the other hand,AGVs are able to make forecasts and adapt their decisions in uncertain ***,because of the nature of MPC and the requirements of AGVs,it is intuitive to apply MPC algorithms to *** are interesting not only for considering them alone,which requires centralized control approaches,but also as groups of AGVs that interact and communicate with each other and have their own controller *** calls for distributed control ***,a short introduction into the basic theoretical background of centralized and distributed MPC is ***,it comprehensively reviews MPC applications for both single and multiple ***,the paper highlights existing issues and future research directions,which will promote the development of MPC schemes with high performance in AGVs.

关键词： Model predictive control Autonomous intelligent system Autonomous ground vehicle

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：