检索结果-内蒙古大学图书馆

Two-Dimensional Model-Free Optimal Tracking control for Batch Processes With Packet Loss

ieee TRANSACTIONS ON control OF NETWORK systems 2023年第2期10卷 1032-1045页

作者： Shi, Huiyuan Wen, Xin Jiang, Xueying Su, Chengli Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China Liaoning Petrochem Univ Sch Informat & Control Engn Fushun 113001 Peoples R China Northeastern Univ Coll Informat Sci & Engn State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China

Aiming at the 2-D batch processes with unknown parameters and packet loss under the network transmission, a novel data-dependent 2-D off-policy algorithm with compensation of packet loss is developed for realizing the precise and timely control. First, in order to better compensate for the negative impact of data loss on the system performance, a Smith predictor combined with preceding 2-D data is introduced into the design of the controller. Second, an optimization performance index is defined and a 2-D optimal tracking control problem for the batch process with data loss is constructed. Furthermore, a completely data-driven 2-D off-policy Q-learning algorithm is derived by taking into account the reinforcement learning theory and the dynamic programming method. Only the data in time and batch directions are used to acquire the optimal controller gains, and the data-driven optimal tracking control of batch processes with data loss can also be realized. Ultimately, the unbiasedness and convergence of the proposed algorithm are demonstrated by a strict proof process, and its effectiveness is verified by simulation experiments.

关键词： Batch processes off-policy Q-learning packet loss Smith predictor 2-D

来源：评论

学校读者我要写书评

暂无评论

Soft Sensor Method based on Quality-related Virtual Sample Generation and Sample-weighted learning 13

Soft Sensor Method based on Quality-related Virtual Sample G...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Dong, Shuang Jin, Huaiping Wang, Bin Yang, Biao Liu, Haipeng Kunming University of Science and Technology Faculty of Information Engineering and Automation Department of Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming650500 China

ISBN: (纸本)9798350361674

In process industry, data-driven soft sensor often faces the problem of data shortage in modeling due to factors such as high cost of label samples acquisition and high data repetition rate. The virtual sample generation (VSG) method has been proposed for data augmentation to solve the above problems. Most of the conventional generative models cannot generate virtual samples with labeled data, at the same time, previous data augmentation methods have ignored the quality differences of the generated virtual samples themselves. Thus, this paper proposes a soft sensor method based on quality-related virtual sample generation and sample-weighted learning (QRVSG-SWL). Firstly, this method combines the respective advantages of variational autoencoder (VAE) and generative adversarial network (GAN) to generate labeled virtual samples. Secondly, a prediction model is constructed using virtual samples to calculate the prediction accuracy and distribution differences on real labeled data. Then, sample similarity calculation under supervised latent *** performed. Finally, model learns virtual sample weights. The effectiveness of the proposed method is validated by the industrial chlortetracycline (CTC) fermentation process. © 2024 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyber-Resilience in Electric Vehicle Charging Stations: A Multi-Agent Deep Reinforcement learning Approach

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2024年第11期25卷 18049-18062页

作者： Sepehrzad, Reza Faraji, Mohammad Javad Al-Durra, Ahmed Sadabadi, Mahdieh S. Politecn Milan Dept Elect Engn I-20133 Milan Italy Hamedan Univ Technol Dept Elect Engn Hamadan *** Iran Khalifa Univ Adv Power & Energy Ctr Elect Engn & Comp Sci Dept Abu Dhabi U Arab Emirates Univ Manchester Dept Elect & Elect Engn Manchester M13 9PL England

Electric vehicle charging stations (EVCSs) heavily rely on communication systems, making them vulnerable to cyber uncertainties such as communication delays and False data Injection (FDI) attacks. In this study, the techno-economic evaluation of the EVCS based on the developed and data-driven Takagi-Sugeno-Kang Fuzzy System & Multi-Agent Deep Reinforcement learning (TSKFS&MADRL) method is presented to detect and compensate for cyber uncertainties such as FDI attacks and communication delay. In addition, the proposed approach provides a fast dynamic response and enhances the resilient operation of EVCS in the presence of FDI attacks. First, the target points of hackers such as communication systems and transducer sensors are modeled, and then, using the Euclidean norm theory, weighted least square error method, and residual error technique resulting from comparing measured data with reference values based on probability distribution functions, FDI cyber-attacks are detected. Then, the network control and recovery requirements are enabled by the proposed controller based on the TSKFS&MADRL method. The proposed approach has been implemented in the ieee 33 bus network. The experimental operating cost is 7.33% less than the RL method and 12.15% less than the CNN method. Also, the experimental results of the proposed method show a 40% detection time reduction compared to other methods.

关键词： Cyber-attacks communication system delay electric vehicle charging station false data injection multi-agent deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Agent Coordination among Different Team Attribute Tasks via Contextual Meta-Reinforcement learning 13

Adaptive Multi-Agent Coordination among Different Team Attri...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Huang, Shangjing Zhao, Zijie Zhu, Yuanheng Zhao, Dongbin Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350361674

In the realm of Multi-Agent Reinforcement learning (MARL), the challenge of ensuring effective coordination in different multi -agent teams remains a significant hurdle. Existing methods often fall short in generalizing learned policies to novel team compositions, sizes, and capabilities. Addressing this gap, our study focuses on systems with variable and obscure attribute compositions, harnessing a context-based meta-reinforcement learning framework. The approach is twofold: context inference and context-based decision-making. Agents interpret historical data to identify the system's attribute composition, guiding their collective efforts. The accuracy of these inferences is crucial, prompting us to integrate contrastive learning to refine the context inference network via unsupervised training. In the process of decision-making, agents integrate the inferred context with the observation features to select the optimal strategy. Our empirical results underscore the method's efficacy in bolstering decision-making efficiency and precision amidst attribute diversity, marking a significant stride in adaptive teaming for robust multi-robot deployments in dynamic real-world scenarios. © 2024 ieee.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Destination Floors-Oriented Group Elevators Dispatching Algorithm Based on Q-learning and Simulated Annealing Method 13

Destination Floors-Oriented Group Elevators Dispatching Algo...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Liang, Rongxi Peng, Yunjian Zhang, Kun School of Automation Science and Engineering South China University of Technology Guangzhou510640 China

ISBN: (纸本)9798350361674

Optimal dispatching strategies wield a pivotal influence on improving the operational performance of modern hybrid group elevators, which directly contributes to the heightened operational efficiency of the elevators and an improved traveling experience for passengers. Existing elevator dispatching algorithms are struggling to cope with the intricacies and diversities present in real-world scenarios, especially in instances of peak hours in superstructures. Designing an elevator destination floor group dispatching algorithm has posed intricate challenges due to the complexity and non-linearity of elevator systems and unpredictability of the passenger flow. This paper proposes a novel algorithm for elevator destination floor group dispatching that skillfully combines the Q-Iearning algorithm and the simulated annealing algorithm in alignment with current state-of-the-art investigations within the domain. Numerical simulations are conducted to verify the effectiveness of the proposed composite algorithm in reducing the average waiting time of passengers comparing to the traditional proximity principle and conventional dispatching algorithm. © 2024 ieee.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Pruning-Based Knowledge Transfer Method for Power System Scheduling 13

Pruning-Based Knowledge Transfer Method for Power System Sch...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Yan, Zhen Tang, Hao Fang, Daohong Tan, Qi Wang, Song Wang, Tongwen School of Electrical Engineering and Automation Hefei University of Technology China State Grid Anhui Electric Power Co. Ltd China

ISBN: (纸本)9798350361674

In order to enhance the learning optimization efficiency of deep reinforcement learning algorithms in the scenario of unit shutdown and maintenance, this study delves into knowledge transfer issues arising from the reduction of target task state and action vector dimensions compared to the source task. A dimensionality reduction transfer method for deep reinforcement learning based on neural network pruning is proposed. Firstly, a method for calculating the information richness of neural network nodes is introduced, utilizing L1 norm and information entropy. Subsequently, guided by the richness of information, the significance of each neural network node in the source task to the target task is analyzed, enabling effective network pruning. Furthermore, a mapping relationship between the neural networks of the target task and the source task is established, facilitating the transfer of deep reinforcement learning network parameters. Finally, through numerical simulations, the effectiveness of the proposed method is validated by comparing the transfer effects of different transfer methods, pruning techniques, and pruning rates. © 2024 ieee.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Error Corrected References for Accelerated Convergence of Low Gain Norm Optimal Iterative learning control

引用

ieee TRANSACTIONS ON AUTOMATIC control 2024年第9期69卷 5836-5851页

作者： Owens, David H. Chu, Bing Zhengzhou Univ Dept Automat Zhengzhou 450001 Peoples R China Univ Sheffield Dept Automat Control & Syst Engn Sheffield S1 3JD England Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ England

To reduce the need for high gains (reduced control weighting) for fast convergence in norm optimal iterative learning control (NOILC), this article presents a simple data-driven mechanism for accelerating the convergence of low gain feedback NOILC controllers. The method uses a modification to the reference signal on each NOILC iteration using the measured tracking error from the previous iteration. The basic algorithm is equivalent to a gradient iteration combined with an NOILC iteration. The choice of design parameters is interpreted in terms of the spectrum of the error update operator and the systematic annihilation of spectral components of the error signal. The methods apply widely, including continuous and discrete-time end point, intermediate point, and signal tracking. The effects of parameter choice are revealed using examples. A robustness analysis is presented and illustrated by frequency-domain robustness conditions for multi-input, multi-output discrete-time tracking, and robustness conditions for end-point problems for state-space systems. Finally, the algorithm is extended to embed a number of gradient iterations within a single NOILC iteration. This makes possible the systematic manipulation of the spectrum, providing additional acceleration capabilities with the theoretical possibility of arbitrary fast convergence.

关键词： Convergence Robustness Aerospace electronics Heuristic algorithms Process control Iterative learning control Convolution Iterative learning control (ILC) performance optimization

来源：评论

学校读者我要写书评

暂无评论

AMING:Adaptive-learning Mechanism Based Missing-Value Imputation Networks Using GAN in Industrial Processes 13

AMING:Adaptive-Learning Mechanism Based Missing-Value Imputa...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Zhang, Jiale Yuan, Xiaofeng Wang, Kai Wang, Yalin Yang, Chunhua Gui, Weihua School of Automation Central South University Changsha410083 China

ISBN: (纸本)9798350361674

In industrial production, uncontrollable factors can lead to the inability to collect or transmit data, resulting in the widespread presence of missing values in industrial datasets. These missing data may contain crucial information for production and serve as a vital source for diagnosing equipment malfunctions or issues. Incomplete datasets directly impact subsequent modeling, prediction, and optimization tasks. However, traditional imputation methods struggle to capture complex data distributions and structures, making them unsuitable for production tasks that require high imputation accuracy. Due to its proficiency in simulating data distributions, generative networks have emerged as effective tools for handling missing or corrupted data. The classic GAIN model introduces a prompting mechanism, providing fixed prompts to the discriminator, but this may lead to issues such as model degradation, pattern collapse, and convergence difficulties. In this paper, we propose a novel unsupervised adaptive imputation framework based on GANs, referred to as AMING. It aims to impute missing data in industrial production processes in an unsupervised adaptive manner. Furthermore, we introduce an adaptive learning mechanism framework that dynamically provides learning information to the discriminator during the training process. Finally, we conduct experimental validation on a hydrocracking dataset, demonstrating the superior performance of the AMING method. © 2024 ieee.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

data-driven Linear Quadratic Gaussian using LightGBM Algorithm for Batch Distillation Column

Data-Driven Linear Quadratic Gaussian using LightGBM Algorit...

引用

ieee International conference on Automatic control and Intelligent systems (I2CACIS)

作者： Mahayana, Dimitri Nasution, Muhammad Alifsyah Putra Mubarak, Muhammad Fadhli Rusmin, Pranoto Hidaya Inst Teknol Bandung Sch Elect Engn & Informat Bandung Indonesia

ISBN: (纸本)9798350372113;9798350372106

The batch distillation column plant inherently is highly nonlinear system due to its adherence to physical principles, with only a single sensor designated for measuring the output. Based on these conditions, a traditional control approach that can be employed is Linear Quadratic Gaussian (LQG). However, conventional LQG methods have certain constraints. To address these limitations, this research presents a novel data-driven LQG approach using the Light Gradient-Boosting Machine (LightGBM) algorithm for batch distillation column systems. The LightGBM algorithm is used to replace the roles of both the Linear Quadratic Regulator (LQR) controller and Kalman Filter. The dataset sample sizes for training range from 1,000 to 1,000,000. From the simulation, For each LightGBM regressor model produced, one for LQR controller gain and another for Kalman gain, performance metrics such as R-squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) are utilized to assess the training process. The results show that larger sample sizes lead to better LightGBM regressor models. The outcomes suggest that both LightGBM models, created to substitute for the functions of LQR controller gain and Kalman gain, demonstrate the ability to precisely forecast output values using the provided input variables.

关键词： batch distillation column data-driven LQG LightGBM algorithm

来源：评论

学校读者我要写书评

暂无评论

A data-driven Based Blind Path Recognizing and Tracking control Strategy for a Guided Quadruped Robot 13

A Data-Driven Based Blind Path Recognizing and Tracking Cont...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Liu, Shida Sun, Yunlong Ji, Honghai Wang, Li School of Electrical and Control Engineering North China University of Technology Beijing100000 China Ministry of Education Key Laboratory of Marine Intelligent Unmanned China

ISBN: (纸本)9798350361674

This study addresses the motion control issues of a guiding quadruped robot and proposes a novel data-driven approach for blind path recognition and tracking. The proposed approach consists of two parts, including blind path recognition and robot tracking control. In terms of visual principles, the guiding quadruped robot identifies blind paths based on color using the Otsu threshold segmentation algorithm, combined with Canny edge detection and Hough transform for precise positioning of the blind path. Next, this study presents a model-free adaptive control method utilizing a dynamic linearization technique to follow the identified blind path. The controller is configured with a pseudo partial derivative (PPD) parameter. The proposed method enables accurate recognition and tracking of blind paths by the robot, thereby achieving precise following of blind paths by the guiding quadruped robot. The control aspect of the proposed method relies on a model-free strategy, eliminating the requirement to establish an exact mathematical model of the guiding robot during the controller design process. Instead, the controller can be achieved solely using input and output data of the robot. The proposed method was applied to a real guiding quadruped robot experimental platform, and the experimental results demonstrated a 96.24% accuracy in blind path recognition and an average deviation angle of 0.17 degree in tracking control. The effectiveness of this approach has been validated. © 2024 ieee.

关键词： Multipurpose robots

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：