检索结果-内蒙古大学图书馆

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Fang, Zihan Hou, Yanxu Li, Jun Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Shenzhen Research Institute Southsast University Shenzhen518057 China

ISBN: (纸本)9781665437127

To promote the work capacity and efficiency in a weakly structured logistics sorting scene, a pick-And-Throw method based on reinforcement learning is proposed. First, a D N-based learning algorithm is used to obtain a picking feasibility distribution map for guiding an optimal picking action. Second, Deep Deterministic Policy Gradient (DDPG) algorithm is utilized to train a throwing policy. The throwing policy outputs a throwing velocity of the end-effector of a robot to throw the picked object to a target area. In addition, a memory pool optimization algorithm is also proposed to enhance the convergence of the throwing policy. Experiments are conducted in both simulation and real scenarios and results demonstrate that the proposed method can improve the sorting efficiency and expand the sorting space significantly. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Parallel Algorithm for Solving General Colored Traveling Salesman Problems 36

A Parallel Algorithm for Solving General Colored Traveling S...

引用

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Ding, Penghui Xu, Xiangping Li, Jun Ministry of Education Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518057 China

ISBN: (纸本)9781665437127

A colored traveling salesman problem (CTSP) is a generalization of the well-known multiple traveling salesman problem. It utilizes colors to differentiate the accessibility of its cities to ward its salesmen. All the existing algorithms for solving CTSP are serial ones. This paper presents for the first time a parallel algorithm framework for solving general CTSP. Then, an improved variable neighborhood search algorithm is proposed by using this algorithm framework. Finally, extensive simulations are conducted in various test cases. The results show that the algorithm proposed is superior to the compared serial algorithms in terms of convergence and solution quality. © 2021 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

An Autoencoder with a Memory Module for Video Anomaly Detection 36

An Autoencoder with a Memory Module for Video Anomaly Detect...

引用

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Tang, Wei Feng, Yunjian Li, Jun Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518057 China

ISBN: (纸本)9781665437127

With the rise of deep convolutional neural networks (CNNs), considerable attention has been paid to video anomaly detection (VAD). Autoencoders are a popular type of framework for VAD, and many existing VAD methods are based on it. However, these methods take an assumption of closed-world VAD, i.e., do not comprehensively consider the diversity of normal patterns. Besides, a competent CNN allows the autoencoder to reconstruct or predict abnormal video frames proficiently, resulting in missing anomalies. To mitigate these drawbacks, we propose an Autoencoder with a Memory Module (AMM) to realize video anomaly detection by predicting video frames. AMM consists of three modules: An encoder, a decoder, and a memory module. First, the consecutive frames are fed into the encoder to yield latent spatial features. Then, the features are utilized to retrieve corresponding memory items in the memory module to generate memory mapping features. Finally, the memory mapping features are adopted in the decoder for predicting the next frame. To match the queries against memory items accurately, we propose a memory triplet loss, which takes into account both size and angle discrepancies between the queries and memory items. At the training stage, AMM utilizes the memory triplet loss, a prediction loss, and multi-scale structure similarity measure. Moreover, the modes of retrieving and updating memory items are ameliorated by a scaled dot product model, which can alleviate vanishing gradient problems to a certain extent. Extensive experiments are conducted on three benchmark public datasets, and the results demonstrate the superior performance of AMM. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Nonsmooth Observer Based on Friction Model Compensation for Sensorless Permanent Magnet Synchronous Motor

A Nonsmooth Observer Based on Friction Model Compensation fo...

引用

Chinese control Conference (CCC)

作者： Zaishan Zhang Wenwu Zhu Ke Yu Xiangyu Wang Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Electrical Engineering and Automation Hefei University of Technology Hefei China

In this paper, a nonsmooth observer considering friction compensation is proposed for the sensorless permanent magnet synchronous motor (PMSM) to estimate the rotor position and speed. Friction is one of the main factors affecting the tracking accuracy of the motor at low speed, especially in the back and forth motion of the motor. Firstly, based on the Stribeck friction model, a nonlinear friction model of the motor is established. Secondly, a nonsmooth observer with friction compensation is designed to estimate the position and speed of the rotor, and the lumped disturbance of the system at the same time. Further, the stability analysis of this nonsmooth observer is given. Finally, the effectiveness of the proposed method is verified by the simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Observer Based Integral Terminal SMC for Converter-Driven Motor systems with Mismatched Disturbances

Finite-Time Observer Based Integral Terminal SMC for Convert...

引用

Chinese Automation Congress (CAC)

作者： Zhongding Zhang Zeyu Guo Zuo Wang Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Shenzhen Research Institute Southeast University Shenzhen China

Converter-driven motor systems play crucial roles in contemporary industrial applications owning to the advantages of smooth starting and stepless speed regulation. For such fourth-order systems with both immeasurable states and mismatched disturbances, a finite-time control solution is proposed to address the speed tracking problem in this paper. Firstly, a finite-time observer is constructed to precisely estimate the immeasurable states and mismatched disturbances. Then, based on integral terminal sliding mode control (ITSMC), a continuous finite-time controller is designed for the systems to achieve both rapid response and superior speed tracking performance. Furthermore, a rigorous global finite-time stability analysis for the closed-loop system is presented. Finally, simulation results validate the effectiveness of the proposed control method. As compared with existing methods, the composite ITSMC algorithm design demonstrates reliable finite-time speed tracking performance and exceptional capability in disturbance rejection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MFANet: Mixed Feature Attention Network for Port Lane Detection

MFANet: Mixed Feature Attention Network for Port Lane Detect...

引用

Chinese control Conference (CCC)

作者： Jinwei Zhang Jinya Su Dewei Yi Jun Yang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education and the School of Automation Southeast University Nanjing China Department of Computing Science University of Aberdeen Aberdeen U.K.

With the advancement of industrial automation and artificial intelligence technology, unmanned port autonomy has gained increasing attention. Port automatic driving technology is a critical component of unmanned autonomous systems, enabling rubber tire gantry cranes (RTGs) to autonomously navigate by detecting port lanes and implementing control commands. In this study, a deep learning-based method is proposed for detecting port lanes in complex port scenes. The method employs the Inception module and attention mechanism to enhance lane feature extraction, and a structural loss is introduced to explicitly constrain the detection results and incorporate the prior characteristics of port lanes. A novel Mixed Feature Attention Network (MFANet) is proposed to implement the method for port lane detection. Experimental results demonstrate that MFANet effectively improves the accuracy of port lane detection while maintaining high computational efficiency. Furthermore, the performance of MFANet is evaluated in a real-world application scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking control of high-order MIMO nonlinear systems with prescribed performance

引用

Frontiers of Information Technology & Electronic engineering 2021年第7期22卷 986-1001页

作者： Xuerao WANG Qingling WANG Changyin SUN School of Automation Southeast UniversityNanjing 210096China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast UniversityNanjing 210096China

In this paper,an observer-based adaptive prescribed performance tracking control scheme is developed for a class of uncertain multi-input multi-output nonlinear systems with or without input saturation.A novel finite-time neural network disturbance observer is constructed to estimate the system uncertainties and external *** guarantee the prescribed performance,an error transformation is applied to transfer the time-varying constraints into a constant ***,by employing a barrier Lyapunov function and the backstepping technique,an observer-based tracking control strategy is *** is proven that using the proposed algorithm,all the closedloop signals are bounded,and the tracking errors satisfy the predefined time-varying performance ***,simulation results on a quadrotor system are given to illustrate the effectiveness of the proposed control scheme.

关键词： Adaptive tracking control Prescribed performance Input saturation Disturbance observer Neural network

来源：评论

学校读者我要写书评

暂无评论

Finite Time Disturbance Observer-Based Tube Model Predictive control for Vehicle Platoon systems with Guaranteed L∞ String Stability

Finite Time Disturbance Observer-Based Tube Model Predictive...

引用

Chinese control and Decision Conference, CCDC

作者： Qian Chen Jinhao Liu Jun Yang Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9781665478977

This paper investigates optimal longitudinal control problems for a vehicle platoon in presence of parameter uncertainties and external disturbances. First, a multi-constraint multi-objective optimization model is developed, where physical limits, safety constraints, driving comfort, and fuel economy are taken into account. To reduce communication burden and avoid network congestion, the preceding vehicle’s acceleration is obtained by employing a finite time disturbance observer (FTDO). As for the parameter uncertainties as well as external disturbances, they are estimated as a lumped disturbance by exploiting a FTDO. Then, under a predecessor following communication topology, a FTDO-based tube model predictive control method with explicit consideration of string stability is contrived. Finally, numerical simulations illustrate the effectiveness and superiority of the proposed control approach.

关键词： Uncertain systems Network topology Fuel economy Numerical simulation Stability analysis Topology Safety

来源：评论

学校读者我要写书评

暂无评论

Pinr: A Physics-Integrated Neural Representation for Dynamic Fluid Scenes

SSRN

引用

SSRN 2024年

作者： Zhao, Ziyu Zhou, Sifan Lu, Xiaobo Zeng, Weili Qian, Jian School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of ASIC and System Fudan University Shanghai China

Recent research based on neural representation has achieved impressive results in dynamic reconstruction. However, reconstructing high-fidelity dynamic fluid scenes from multi-view videos remains challenging due to the complex fluid phenomena such as translucency, scattering, occlusion, and visual ambiguity. In this paper, we present a novel neural representation that simultaneously exploits physics knowledge and differentiable volume rendering techniques to construct a physically plausible neural field. We first propose a simple yet effective state field to separate fluid and non-fluid contents apart, which essentially reduces the amount of computation and appearance ambiguity. To achieve robust optimization and fast convergence, we introduce intermediate velocity in neural representation based on Helmholtz Decomposition to decouple physical quantities (velocity, pressure and density) that are tightly coupled in physical equations. In contrast to previous physics-informed reconstruction methods, we explore a novel solution by introducing a fast and stable fluid solver to update the intermediate velocity to a physically conserved incompressible velocity. This solver is based on a parallelizable multi-scale architecture, which can effectively avoid degenerate solutions. By adopting the proposed physics-aware loss, we achieved better convergence and superior performance in dynamic fluid scenes. Extensive experiments show that the proposed method can achieve state-of-the-art results for reconstructing dynamic fluid scenes, and the performance and efficiency have been significantly improved in different scenarios. © 2024, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Modeling of Photovoltaic modules under shading condition and an error evaluation criterion 4

Modeling of Photovoltaic modules under shading condition and...

引用

2022 4th International Conference on Energy systems and Electrical Power, ICESEP 2022

作者： Lai, GuangZhi Wang, Dong Li, HaoRan Zhao, Yi Ni, WeiChen Wen, JiaHao State Grid e-commerce Co. Ltd Beijing100053 China State Grid Tianjin Electric Power Company Tianjin300392 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

Energy is the focus of recent years. As one of the most representative new energy sources, solar energy has the characteristics of large reserves and no pollution. The main way to use solar energy is photovoltaic (PV) power generation, and the PV module in the PV power generation system is the component that converts solar energy into electric energy. In the actual power generation process, PV modules often receive uneven solar illumination due to the shadow caused by clouds, trees, buildings, etc., resulting in changes in the output characteristics of PV modules and reduced output efficiency. Therefore, modeling of PV modules under shading condition is very important. This paper presents two simple methods for solving the parameters of PV module models, which require few parameters and are easy to obtain. A modeling method of PV modules under shading condition is also presented. And then the modeling method is verified with the experiment result. Finally, an error criterion for PV module modeling under shading condition is proposed to measure the goodness of the modeling. Combining with the two parameter solving methods, the errors of this PV module modeling method under shading condition of the error criterion proposed in this paper are 3.24% and 2.51%, respectively, which meet the requirements for engineering use. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Solar energy

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：