检索结果-内蒙古大学图书馆

An enhanced algorithm for cell-level anomaly segmentation in photovoltaic solar panels using electroluminescence imaging

引用

Energy 2025年 331卷

作者： Ruiyao Duan Yongjian Wang Xisong Chen Shihua Li School of Automation Southeast University Nanjing 210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 PR China Institute for Automatic Control and Complex System University of Duisburg–Essen Duisburg 47057 Germany

Electroluminescence imaging is a crucial diagnostic tool for assessing the quality and performance of photovoltaic (PV) modules. However, current research often focuses on defect detection in PV modules, neglecting the need for detailed segmentation at the individual cell level. To address the limitations of existing methods in recognizing complex defects and suppressing background noise, this paper proposes a novel semantic segmentation algorithm (CAAK-Net), capable of identifying anomalies at the cell level of photovoltaic panels. To enhance network performance, CAAK-Net uses K-Net as a baseline and incorporates the Convolutional Block Attention Module (CBAM), Attention Refinement Module (ARM), and Atrous Spatial Pyramid Pooling (ASPP) modules. Experimental results comparing CAAK-Net with mainstream segmentation networks demonstrate its superior segmentation performance, particularly in recognizing defect edges and small-area attached defects. Additionally, we establish a quantitative correlation model between detection errors and PV system efficiency losses, pioneering the translation of pixel-level segmentation accuracy into measurable operational costs, thereby providing an economic assessment framework for industrial PV inspection. Furthermore, the network exhibits a certain degree of robustness in noisy environments, showcasing its segmentation advantages in diverse defect scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Output feedback based high-order sliding mode control design of electrohydraulic system using an exact differentiator

Output feedback based high-order sliding mode control design...

引用

control Technology and Applications (CCTA),

作者： Hao Sun Zongxuan Sun Shihua Li Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing PR China University of Minnesota-Twin Cities Minneapolis Minnesota USA

ISBN: (纸本)9781665436441

Electrohydraulic systems, which have been widely used in a broad range of applications, are a typical nonlinear system with uncertainties. The presence of nonlinearities, parameter variations degrades the performance of linear controllers, such as the PID controller. As one of the most robust control strategies, sliding mode control methods attract the attention of researchers and are applied to electrohydraulic systems. However, for many applications, only the piston position measurement information is available. Owing to the existence of the nonlinear orifice equation, the observer design is a challenging task and satisfactory performance is not guaranteed in the existing literature. Therefore, an output feedback based high-order sliding mode control (HOSMC) design of electrohydraulic systems is proposed in this paper. By using an exact differentiator, the derivatives of the tracking error are obtained and used to construct the HOSMC. Compared to the conventional sliding mode control (SMC), the HOSMC can achieve a finite-time convergence and improved tracking accuracy. To verify the tracking performance, a simulation is performed on a camless engine valve actuation system.

关键词： Robust control Uncertainty Switching frequency Simulation Position measurement Valves Electrohydraulics

来源：评论

学校读者我要写书评

暂无评论

Cooperative control Based on Distributed Attack Identification and Isolation

Cooperative Control Based on Distributed Attack Identificati...

引用

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

作者： Hailing Liu Dalin Huang Ya Zhang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (数字)9781728177090

ISBN: (纸本)9781728177106

This paper studies the secure consensus control of multi-agent systems where some agents are injected into malicious attacks and compromised. We focus on the distributed detection and identification of attacks on agents and the realization of consensus of agents against attacks. Firstly, we design monitors that can perform precise distributed attack detection. Then, we propose a distributed attack identification algorithm by constructing distributed observers. After that, a cooperative controller is proposed which ensures the normal control of systems by means of isolating the agents which are attacked. Finally, we validate our results through simulation examples.

关键词： Multi-agent systems Monitoring Sensors Sensor systems Security Observers Data models

来源：评论

学校读者我要写书评

暂无评论

MADDPG Algorithm for Coordinated Welding of Multiple Robots

MADDPG Algorithm for Coordinated Welding of Multiple Robots

引用

作者： Weibin Chen Lei Hua Leixin Xu Benshun Zhang Mengmeng Li Tao Ma Yang-Yang Chen School of Automation Southeast University Robot Department Jiangsu Automation Research Institute School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University

This paper deals with the coordinated welding problem of multi-robot systems by applying a deep reinforcement learning algorithm which is called multi-agent deep deterministic policy gradient(MADDPG).It is assumed that the states and actions of robots are continuous and each robot can only get local information of its neighbors.A novel reward composed of trajectory optimization,coordinated welding and collision avoidance is designed,which yield multi-robot systems to arrive the welding targets quickly,achieve the simultaneous welding for a weld line and avoid collision among *** results are provided to demonstrate the effectiveness of the proposed control algorithm.

关键词： Deep multi-agent reinforcement learning MADDPG Coordinated welding

来源：评论

学校读者我要写书评

暂无评论

QMIX Algorithm for Coordinated Welding of Multiple Robots

QMIX Algorithm for Coordinated Welding of Multiple Robots

引用

作者： Liangchuang Liao Yang-Yang Chen School of Electronic Science & Engineering Southeast University Robot Department Jiangsu Automation Research Institute School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University

This paper considers the coordinated welding control based on deep multi-agent reinforcement *** discrete-time states and actions with local observation for the welding robots and the characteristics of the weld lines(e.g.,the starting points of the weld lines and the ending points of the weld lines) are defined,which is suitable to use the monotonic value function factorisation for deep multi-agent reinforcement learning(QMIX) algorithm.A novel reward composed of trajectory optimization,collision avoidance and the task done is designed,which is proved by the simulation in the grid-world environment.

关键词： Deep multi-agent reinforcement learning Welding robots QMIX

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-dimensional Taylor Network control for Cement Calciner Outlet Temperature

Adaptive Multi-dimensional Taylor Network Control for Cement...

引用

IEEE Information Technology, Networking, Electronic and Automation control Conference

作者： Mao-Qi Zhang Hong-Sen Yan Lin-Wei Yu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

This paper focuses on the problem of adaptive multi-dimensional Taylor network control (adaptive MTN) for cement calciner outlet temperature. Firstly, we establish a mathematical model for the cement calciner system, and the model structure is designed as a multi-input single-output data-driven form with time-delay. Secondly, the cross-correlation method and the recursive least squares method are used to identify the model parameters. Thirdly, based on gradient descent method, MTN controller is designed to implement the online update of network weights. Finally, experiment results are given to illustrate the effectiveness of the proposed control strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wind Speed Data Repairing Method Based on Bidirectional Prediction

Wind Speed Data Repairing Method Based on Bidirectional Pred...

引用

Power Electronics, Computer Applications (ICPECA), IEEE International Conference on

作者： Xincheng Shen Yi Qu Shaoxiong Huang Zhi Li Kaifeng Zhang Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China State Grid Anhui Electric Power Co. Ltd Hefei China

ISBN: (数字)9781728190044

ISBN: (纸本)9781728190051

In order to repair the lost data in distributed wind power system, this paper puts forward a wind speed data repairing model based on a new bidirectional prediction method. This model consists of two one-way prediction models. In each prediction model, the original wind speed data are decomposed into several intrinsic mode functions (IMFs) and a residue signal by ensemble empirical mode decomposition (EEMD) method. Then the Savitzky-Golay (SG) filter is used to reduce noise for high-frequency IMFs. Next the long short-term memory (LSTM) model and autoregressive integrated moving average (ARIMA) model are combined to predict low-frequency IMFs and the noise reduction results respectively. At the end, all those forecast results are added and form a one-way result. By weighted average of two one -way results, the repairing result is calculated. The experimental results from multiple prediction cases show that this method can get more accurate results.

关键词： Wind speed Distributed databases Predictive models Maintenance engineering Wind power generation Data models Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Robotic Arm control System Based on Brain-Muscle Mixed Signals

Research Square

引用

Research Square 2021年

作者： Cheng, Li-Wei Li, Duan-Ling Yu, Gong-Jing Zhang, Zhong-Hai Yu, Shu-Yue Key Laboratory of Measurement and Control of Complex Engineering Systems China School of Modern Post School of Automation Beijing University of Posts and Telecommunications Beijing100876 China Beijing Aerospace Measurement & Control Technology Co. Ltd. Beijing100041 China

Aiming at the existing problems of BCI (brain computer interface), such as single input signal source, low accuracy of feature recognition, and less output control instructions, this paper proposes a robotic arm control system based on EEG (electroencephalogram) and EMG (electromyogram) mixed signals. The system flow is as follows: Firstly, the EMG signal of the unilateral arm and the EEG signal of the left and right hand motor imagery is collected synchronously. Then the collected EEG and EMG signals are extracted and classified, and the corresponding classification instructions are obtained. Finally, the multi-instruction real-time control of the robotic arm is realized under the classification instruction. The experimental verification results show that: The 10 subjects all realized the real-time multicommand control of the robotic arm, and the average recognition accuracy of each action reached more than 94%. The proposed system enriches the diversity of hybrid BCI and provides a theoretical basis and application foundation for the extended application of BCI in robotic arm control. © 2021, CC BY.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Distributed PV Identification Based on High-Precision Bus Data Analysis

Distributed PV Identification Based on High-Precision Bus Da...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

作者： Shen, Xincheng Huang, Shaoxiong Li, Zhi Zhang, Kaifeng Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Center State Grid Anhui Electric Power Co. Ltd. Department of Dispatch Hefei China

ISBN: (纸本)9781728168531

With the rapid development of distributed photovoltaic (PV), it is necessary to study its low-cost output identification technology. In this paper, a low-cost PV output identification method is proposed by using feature extraction. This paper analyzes the high-precision bus data, and uses harmonic analysis, wavelet analysis and Ensemble Empirical Mode Decomposition (EEMD) to extract the operating features of PV output. Then this paper screens these extracted features with the correlation between features and PV output, the stability of the features at different times and the difference of features in different signals. The appropriate features are selected for PV output identification, and its identification accuracy is calculated. The experimental results show that with the method of the Ensemble Empirical Mode Decomposition, an appropriate operating feature can be extracted. This feature can identify the distributed PV output in small bus bar when the PV is working stably. © 2020 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Continuous Terminal Sliding-Mode Speed control of Micro Gas Turbine System with Mismatched Disturbances

Finite-Time Continuous Terminal Sliding-Mode Speed Control o...

引用

Chinese Automation Congress (CAC)

作者： Yanjun Sun Long Xu Ning Chen 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 China Electric Power Research Institute Nanjing China

ISBN: (纸本)9781665426480

The micro gas turbine system acts as a key role in distributed renewable generation systems due to its flexibility, versatility, and low emissions. This paper focuses on the micro gas turbine speed control problem, which primarily determines the fuel flow for the turbine under variable load conditions. Due to nonlinear factors in MGTS, such as the coupling between systems parameters, and external disturbances such as electric load variation, it is a challenge to realize accurate speed control. In this paper, a continuous terminal sliding-mode control law based on a finite-time disturbance observer is designed for micro gas turbine control system. In this method, the integral of high-frequency switching function is introduced to control law. It guarantees the continuity of control signal and alleviates the chattering problem. Besides, the linear sliding mode surface is replaced by a full-order terminal sliding mode surface, and it obtains finite-time convergence and smaller speed tracking error. Furthermore, disturbance estimates are used in control law to eliminate the adverse effect of disturbances on control performance, which improves disturbance rejection ability. Finally, simulation comparison with conventional sliding-mode control validates the advantages of the composite controller.

关键词： Renewable energy sources Simulation Velocity control Switches Load management Disturbance observers Fuels

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：