检索结果-内蒙古大学图书馆

13th IEEE Data Driven control and Learning systems Conference, DDCLS 2024

作者： Fan, Zhong-Xin Tang, Lintao Li, Shihua Liu, Rongjie School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Florida State University Department of Statistics TallahasseeFL32304 United States

ISBN: (纸本)9798350361674

Achieving optimal speed regulation for permanent magnet synchronous motors (PMSMs) remains a challenging task, particularly in selecting the most suitable controller to meet desired objectives. This paper considers the optimal speed tracking problem of PMSMs. We employ a reinforcement learning algorithm to obtain optimal controller with a linear form. The reinforcement learning approach incorporates a critic-actor network structure, which approximates the value function and optimal control, respectively. Specifically, a weight updating method for the critic network is introduced, where the update of the actor network is guided by the critic network. Through data collection and neural network training, dynamic acquisition of the optimal controller gain is achieved. In addition, a novel activation function is implemented in the network, leading to improved control performance concerning dataset size and reduced training time. At final, a real-world PMSM application is presented along with comparisons to demonstrate effectiveness. The desire idea of resulting optimal controllers is not only applicable to linear systems but also capable of approximating arbitrary nonlinear optimal controllers, thus offering practical engineering versatility. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Smooth and Time-optimal Improved-Bezier Trajectory Planning Based on Dynamics for Industrial Robots

Smooth and Time-optimal Improved-Bezier Trajectory Planning ...

引用

第43届中国控制会议

作者： Wei Cai Yahui Gan Fang Fang Bo Zhou Xianzhong Dai School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper presents a smooth and time-optimal improved-Bezier trajectory planning algorithm that addresses the avoidance of solving switching points and solves the problem of discontinuous torque on the basis of the time-optimal path parameterization(TOPP) algorithm. The proposed approach employs the TOPP-RA algorithm with a friction model, to construct the optimal velocity trajectory under the constraints of the geometric paths and joint torques. Moreover, the proposed algorithm utilizes an enhanced Bezier curve instead of the jerk constraint in the trajectory optimization model to achieve a smooth trajectory. The modified Bezier curve optimizes the peaks of the pseudo-velocity curve in the phase plane to change the discontinuity of joint torque. The proposed algorithm ensures absolute time optimality and achieve a s mooth tr ajectory. The results of the MATLAB simulation experiment on a two-link motion system indicate the validity of the proposed algorithm.

关键词： time-optimal smooth trajectory planning improved-Bezier trajectory

来源：评论

学校读者我要写书评

暂无评论

Research on Vibration Suppression for Industrial Robots Based on Dynamic Feedforward control

Research on Vibration Suppression for Industrial Robots Base...

引用

第43届中国控制会议

作者： Bin Huang Yahui Gan Fang Fang Bo Zhou Xianzhong Dai School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

To address the challenges of low position tracking accuracy and high vibrations in mechanical arms controlled by PID closed-loop systems, this paper introduces a torque feedforward control scheme based on dynamic models. The paper initially analyzes the causes of vibrations during robot motion, establishing a mathematical model to quantify the trajectory accuracy and repeatability of vibrations. Subsequently, a torque feedforward control scheme based on dynamic models is designed, and its feasibility is theoretically analyzed. In this motion control scheme, precise dynamic models are utilized to calculate and output the desired torque. The torque values are then converted into motor current values, which are superimposed on the control output of the current loop in the servo to achieve real-time torque compensation. Finally, through simulation experiments, the paper validates that the dynamics-based torque feedforward control effectively suppresses robot vibrations, enhances tracking accuracy,and improves dynamic performance. The findings demonstrate the efficacy of the proposed control strategy in addressing the challenges associated with PID-controlled robotic arm systems.

关键词： Industrial robots feedforward control vibration suppression

来源：评论

学校读者我要写书评

暂无评论

Model Prediction Based Adaptive Variable Impedance control of Manipulator with Passivity

Model Prediction Based Adaptive Variable Impedance Control o...

引用

第43届中国控制会议

作者： Yang Xiao Wenbo Liu Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Aiming at the compliance control of rigid manipulators in human-robot interaction scenarios, a new variable impedance control(VIC) model is proposed to improve the adaptive ability of the manipulator to adjust compliance in different phases of the task. The parameter selection problem is transformed into a controller design problem. Impedance constraints are set by introducing the prior knowledge of the person, information about the state and contact force, and manipulability. The one-step model predictive control(MPC) method is used to search for the optimal solution of impedance parameters, so that the manipulator can adaptively select different balance relations between tracking accuracy and compliance. Moreover, in order to avoid the damage of time-varying impedance parameters to the stability, a tank-based method is implemented to ensure the passivity of the impedance system. Finally, the simulation results verify the effectiveness of the proposed control scheme.

关键词： Variable Impedance control(VIC) Model Predictive control(MPC) Tank-based method Passivity

来源：评论

学校读者我要写书评

暂无评论

Disturbance Rejection control Method Based on Adaptive Composite Disturbance Observer for Permanent Magnet Synchronous Motor

Disturbance Rejection Control Method Based on Adaptive Compo...

引用

第43届中国控制会议

作者： Yu Fang Di Wu Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The vehicle electronic scroll compressors exhibits significant speed fluctuations during low-speed and heavy-load *** periodic fluctuation of load torque leads to speed *** limited sensitivity gain of traditional disturbance observers results in poor performance in suppressing periodic *** response to this issue,this study adopts an adaptive composite disturbance observer to estimate and compensate for load disturbances,in order to reduce speed fluctuations in the low-speed *** adaptive composite disturbance observer has achieved simultaneous and adaptive observation and estimation of periodic and aperiodic slow varying *** adaptive notch filter(ANF) based on variable step-size quantize least mean square(VSQLMS) algorithm is used to estimate the fundamental frequency of periodic *** simulation experiments,the method proposed has improved the control accuracy and dynamic response performance of the system,and has enhanced its robustness.

关键词： Extended State Observer internal model principle ANF multiple disturbance

来源：评论

学校读者我要写书评

暂无评论

End-to-end multi-task reinforcement learning-based UAV swarm communication attack detection and area coverage

引用

Knowledge-Based systems 2025年 316卷

作者： Yu, Jin Zhang, Ya Sun, Changyin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

This paper proposes an innovative end-to-end multi-task reinforcement learning framework designed to enhance the security and operational stability of UAVs in complex communication attacks environments. In scenarios involving multiple UAV coverage, the framework classifies attack types and predicts UAV behaviors, which enables rapid response and compromised data recovery. First, a spatiotemporal attention mechanism is employed to strengthen the network by capturing temporal dependencies in the communication data and improving the recognition of hybird attack mode, thereby facilitating the integration of detection and repair. Second, the causal inference mechanism introduced in this study extracts true causal relationships from interference, which ensures the accuracy and stability of action predictions for area coverage under attack conditions. Finally, the entire process is modeled as a multi-task Markov decision process, optimizing overall decision-making efficiency. Additionally, the dynamic pheromone induction mechanism is proposed to realize the adaptive regional cooperative coverage of multiple UAVs. The experimental results demonstrate that the proposed algorithm can effectively detect hybrid attacks and predict UAV actions, protecting the multi-UAV cooperative area coverage. © 2025

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A distributed finite-time economic dispatch algorithm in smart grid

A distributed finite-time economic dispatch algorithm in sma...

引用

2022 Jiangsu Annual Conference on Automation, JACA 2022

作者： Lin, Luxin Wang, Xiangyu School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

ISBN: (纸本)9781839538476

This paper focuses on the design of an initialization-free distributed finite-time algorithm for the economic dispatch problem in smart grid, where the generation units only communicate with its neighbors to minimize the total cost cooperatively. Firstly, the optimal solution of the economic dispatch problem is analyzed in accordance with the saddle-point dynamics. Then, an initialization-free finite-time algorithm is presented to guarantee the active power generation and the incremental cost converge to the optimal solution in a distributed manner. At last, some numerical simulations are preformed to validate the proposed method. Copyright© JACA 2022 All rights reserved.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Transformer-Based Framework for Solar Irradiance Forecasting under Incomplete Data Scenarios

引用

IEEE Transactions on Industrial Informatics 2024年第6期20卷 8605-8615页

作者： Zhang, Hanjin Li, Bin Su, Shun-Feng Yang, Wankou Xie, Liping Southeast University School of Economics and Management Nanjing210096 China National Taiwan University of Science and Technology Department of Electrical Engineering Taipei106 Taiwan Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518063 China

Accurate prediction of solar irradiance is crucial for the effective utilization of solar energy. However, in real-world scenarios, complex irradiance patterns and prevalent incomplete data pose challenges to precise forecasting, resulting in additional uncertainties and instability. To address these issues, this study proposes a novel irradiance forecasting model that integrates a Mask-Transformer data imputation module and a prediction module centered around the typical patterns representation mechanism. The Mask-Transformer leverages a mask modeling mechanism to model the context of missing data, facilitating accurate estimation of missing values and reducing noise and uncertainty in the input data. The typical patterns representation mechanism comprises a series decomposition module and a feature fusion module, providing the module with the capability to mitigate nonlinearity and nonstationarity in solar irradiance data. This enhancement leads to improved short-term forecasting performance while maintaining long-term forecasting capabilities. Experimental results on two datasets demonstrate that the proposed model exhibits sufficient robustness and accuracy, making it effective in scenarios with incomplete data. © 2005-2012 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning Based Single Temporal Remote Sensing Image Change Detection 12

Multi-task Learning Based Single Temporal Remote Sensing Ima...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Yang, Peixuan Cao, Yichao Lu, Xiaobo College of Software Engineering Southeast University JiangSu NanJing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education JiangSu NanJing China School of Automation Southeast University JiangSu NanJing China

ISBN: (纸本)9798400707988

Change Detection is a classic and fundamental task in remote sensing(RS), and has accomplish remarkable achievement on bitemporal image based methods. However, bitemporal images are very expensive and needs professional researchers to align and label the paired images. Furthermore, most bitemporal image based methods are only semantic-aware not instance-aware, which indicates these methods only use paired images' semantic information. Thus, we propose a method that only needs unpaired RS images with semantic labels. In this paper, we introduce multi-task learning into change detection progress, which comprises four major parts: Boundary-Aware Module, Contextual-Aware Module, Segmentation Module, Change Detection Module. At first, we construct Boundary-Aware Module and Contextual-Aware Module to extract sharp boundary and dense contextual features. Then we feed the feature maps to Change Detection Module and Segmentation Module to accomplish the subtasks. The comprehensive experiments on a single temporal image dataset demonstrate the efficiency of our approach over other bitemporal image based methods, and the experimental results shows our approach is competitive with other methods while all methods was trained on bitemporal image dataset. © 2023 ACM.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

A novel task-oriented framework for dual-arm robotic assembly task

引用

Frontiers of Mechanical engineering 2021年第3期16卷 528-545页

作者： Zhengwei WANG Yahui GAN Xianzhong DAI School of Automation Southeast UniversityNanjing 210096China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationNanjing 210096China

In industrial manufacturing,the deployment of dual-arm robots in assembly tasks has become a ***,making the dual-arm robots more intelligent in such applications is still an open,challenging *** paper proposes a novel framework that combines task-oriented motion planning with visual perception to facilitate robot deployment from perception to execution and finish assembly problems by using dual-arm *** this framework,visual perception is first employed to track the effects of the robot behaviors and observe states of the workpieces,where the performance of tasks can be abstracted as a high-level state for intelligent *** assembly task and manipulation sequences can be obtained by analyzing and reasoning the state transition trajectory of the environment as well as the ***,the corresponding assembly manipulation can be generated and parameterized according to the differences between adjacent states by combining with the prebuilt knowledge of the *** are set up with a dual-arm robotic system(ABB YuMi and an RGB-D camera)to validate the proposed *** results demonstrate the effectiveness of the proposed framework and the promising value of its practical application.

关键词： dual-arm assembly Al reasoning intelligent system task-oriented motion planning visual perception

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：