检索结果-内蒙古大学图书馆

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Wang, Jichen Jin, Feng Zhao, Jun Wang, Wei Dalian Univ Technol Key Lab Intelligent Control & Optimizat Ind Equip Minist Educ Dalian 116024 Peoples R China Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China

ISBN: (纸本)9798350321050

In the production process of steel enterprise, reasonable scheduling of byproduct energy plays a significant role in reducing operation cost, environmental pollution and improving energy utilization. In this study, a two-stage optimal scheduling method is proposed to solve the problem. The optimal scheduling of coupled gas-steam-electricity system and production scheduling of steelmaking-refining-continuous casting are introduced into this method. The minimum energy purchase cost and carbon emission cost are considered as the objective functions in the optimal scheduling of coupled gas-steam-electricity system. Through the proper adjustment of production plan, the distribution structure of energy is optimized and the space for energy optimization is expanded, which is more profitable to reduce the operation cost of enterprise. The proposed method has been validated with actual operation data of a large domestic steel enterprise, the optimization results show that the total cost of the enterprise can be reduced by 20.75% compared to the actual operating cost of the enterprise and 1.52% compared to the general optimization method, providing support for conducting steel enterprises to save energy and reduce emission, as well as reduce cost and increase efficiency.

关键词： Steel industry Integrated energy system Energy scheduling Production scheduling

来源：评论

学校读者我要写书评

暂无评论

learning to Boost the Performance of Stable Nonlinear systems

IEEE OPEN JOURNAL OF CONTROL SYSTEMS

引用

ieee OPEN JOURNAL OF control systems 2024年 3卷 342-357页

作者： Furieri, Luca Galimberti, Clara Lucia Ferrari-Trecate, Giancarlo Ecole Polytech Fed Lausanne CH-1015 Lausanne Switzerland

The growing scale and complexity of safety-critical control systems underscore the need to evolve current control architectures aiming for the unparalleled performances achievable through state-of-the-art optimization and machine learning algorithms. However, maintaining closed-loop stability while boosting the performance of nonlinear control systems using data-driven and deep-learning approaches stands as an important unsolved challenge. In this paper, we tackle the performance-boosting problem with closed-loop stability guarantees. Specifically, we establish a synergy between the Internal Model control (IMC) principle for nonlinear systems and state-of-the-art unconstrained optimization approaches for learning stable dynamics. Our methods enable learning over specific classes of deep neural network performance-boosting controllers for stable nonlinear systems;crucially, we guarantee L-p closed-loop stability even if optimization is halted prematurely. When the ground-truth dynamics are uncertain, we learn over robustly stabilizing control policies. Our robustness result is tight, in the sense that all stabilizing policies are recovered as the L-p -gain of the model mismatch operator is reduced to zero. We discuss the implementation details of the proposed control schemes, including distributed ones, along with the corresponding optimization procedures, demonstrating the potential of freely shaping the cost functions through several numerical experiments.

关键词： control systems Stability criteria Numerical stability Costs Artificial neural networks Vectors Cost function Closed-loop stability distributed control internal model control learning for control optimal control uncertain systems

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Method Based on Conditional Generative Adversarial Network integrating Multi-scale CNN 12

Network Intrusion Detection Method Based on Conditional Gene...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Geng, Zhiqiang Xi, Xiang Hu, Xuan Han, Yongming Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 10029 Peoples R China Minist Educ China Engn Res Ctr Intelligent PSE Beijing 10029 Peoples R China

ISBN: (纸本)9798350321050

data imbalance is a key problem existing in most network traffic datasets that restricts the performance of intrusion detection. In addition, traditional intrusion detection methods are insufficient to extract features of network traffic effectively, which result in low detection accuracy. Therefore, a novel intrusion detection method based on the conditional Generative Adversarial Network (CGAN) integrating the improved Multi-scale Convolution Neural Network (MSCNN) is proposed to deal with the problem of data imbalance and improve the classification performance. In the level of data, the CGAN is applied to generate minority network traffic samples to decrease the false alarm rate of intrusion detection. In the level of the neural network, the MSCNN of novel structure adapt to the network traffic is applied to promote the detection performance by using multiple convolution kernels for feature extraction. According to the experimental result on UNSW-NB15 and CIC-IDS2017 datasets, the proposed method can detect the network traffic of minority classes effectively, and acquires higher detection accuracy and F1-score compared with other existing methods, which proves the proposed method is advanced in network intrusion detection.

关键词： Network intrusion detection data imbalance conditional generative adversarial network multi-scale convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Modified Deep Deterministic Policy Gradient Based Optimal Speed Tracking Strategy for PMSMs 13

Modified Deep Deterministic Policy Gradient Based Optimal Sp...

引用

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

High Order Sliding Mode Decoupling control of Two-dimensional Linear Motor Based on Proportional Integral Model Free Adaptive control 12

High Order Sliding Mode Decoupling Control of Two-dimensiona...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Jia, Jihui Cao, Rongmin Hou, Zhongsheng Zhou, Huixing Chang, Dehiao Li, Yifan Beijing Informat Sci Technol Univ Sch Automat Beijing 100192 Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China Beijing Jinduo Technol Dev Co Ltd Dept Technol Beijing 100000 Peoples R China

ISBN: (纸本)9798350321050

Two-dimensional linear motor motion systems are nonlinear, multivariate, uncertain and strongly coupled, and easy to be affected by external disturbances. Based on the characteristics of the model free adaptive control (MFAC) does not depend on the controlled system accurate mathematical model and that sliding mode control (SMC) can suppress external disturbances and is insensitive to bounded disturbances, a composite control scheme combining proportional integral model free adaptive control (PIMFAC) and high order sliding mode control (HOSMC) is proposed. A proportional control term is added to the model free adaptive control to further improve the response speed of the two-dimensional linear motor. High-order sliding mode controller compensates for system errors, and the two methods are closely combined to improve the position tracking accuracy of the two-dimensional linear motor and improve the system robustness. An adaptive decoupling control strategy is also used to further decouple the system by designing a discrete expansion state observer (DESO) to estimate and compensate for the coupling between the two axes, unmodelled dynamics and unknown external disturbances. The simulation experimental results show that the proposed scheme can effectively improve the position control accuracy of the two-dimensional linear motor.

关键词： the two-dimensional linear motor proportional integral model free adaptive control (PIMFAC) high order sliding mode control (HOSMC) discrete expansion state observer (DESO) adaptive decoupling control position control accuracy

来源：评论

学校读者我要写书评

暂无评论

MFALC control of Aquaculture Vessel Based on Improved ILOS Guidance Law 13

MFALC Control of Aquaculture Vessel Based on Improved ILOS G...

引用

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

作者： Chen, Xianghao Yao, Wenlong Chi, Ronghu Cui, Zhigang College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China

ISBN: (纸本)9798350361674

To mitigate the impact of lateral deviation in the trajectory control of aquaculture vessels, an improve ILOS guidance law is proposed. Addressing complex sea conditions, unstable weather scenarios, and uncertainties in load, a model-free adaptive learning control (MFALC) method for aquaculture vessel heading control is introduced. Firstly, by incorporating the actual vessel position, desired trajectory, and the improved ILOS guidance law, the desired heading is obtained, and a dynamic linearization model is established solely based on input-output data. Secondly, a Pseudo-Partial Derivative (PPD) estimation algorithm is presented. Subsequently, the MFALC control is designed in conjunction with the PPD algorithm. Finally, the superiority of the proposed control method over traditional PID control is validated through simulations. Simulation results demonstrate that the proposed control method enables rapid and stable trajectory control for aquaculture vessels. © 2024 ieee.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Iterative learning for Nonlinear systems with Variable Pass Lengths: Fault Estimation in the Presence of Actuator Faults 13

Iterative Learning for Nonlinear Systems with Variable Pass ...

引用

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

作者： Gu, Shaodong Chen, Chuang Shi, Jiantao Nanjing Tech University College of Electrical Engineering and Control Science Nanjing211816 China

ISBN: (纸本)9798350361674

This research addresses the faults estimation (FE) of the actuator faults in nonlinear dynamic systems with varying pass lengths. Additionally, the adverse impact of the bounded disturbances and measurement noise on the systems is also considered. A nonlinear iterative learning observer (NILO) is designed to achieve fault estimation. To tackle information loss and redundancy caused by variable pass lengths, a novel enhanced weighted averaging operator for the NILO is proposed. This approach enables fast tracking of fault signals and enhances system robustness. The method ensures the final boundedness of tracking error. Finally, the simulation results are given to verify that the proposed approach is validated by numerical simulation studies. © 2024 ieee.

关键词： Nonlinear analysis

来源：评论

学校读者我要写书评

暂无评论

A Lifetime Management Framework for SOTIF-Oriented Vehicle Dynamics control: A data-driven Approach

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

ieee TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第1期9卷 48-51页

作者： Chen, Jicheng Liang, Jingguo Teng, Siyu Zhang, Hui Wang, Fei-Yue Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China Hong Kong Baptist Univ Kowloon Hong Kong 999077 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Engn Macau 999078 Peoples R China

Current safety of the intended functionality (SOTIF) studies are focused on perception limitations, decision uncertainties, and human-machine interaction, while it tends to overlook the impact of the control system on SOTIF. This letter seeks to address this gap by establishing a lifetime management framework for vehicle dynamics control (VDC) systems. At first, we provide an introduction to the fundamental composition and control architecture of a VDC system. Furthermore, we identify representative hazard scenarios, trigger conditions and performance deficiencies in VDC. Building upon data-driven fault-tolerant control theory, a comprehensive framework consisting of adaptive filter, iterative learning, fault diagnosis and identification, and fault-tolerant control modules is presented. The proposed framework is specifically designed to address trigger conditions such as driving environment variations, integration of multiple control systems, performance degradation due to components aging and maintenance. The framework features online driving state supervision, driving risk measurement, and intervention for mitigation of the SOTIF issues. As a summary of a part of Distributed/Decentralized Hybrid Workshop on Sustainability for Transportation and Logistics (DHW-STL), the letter reports the development of an intelligent vehicle lifetime management framework with a strong focus on SOTIF issues.

关键词： Safety control systems Vehicle dynamics Fault diagnosis Hazards Autonomous vehicles Uncertainty Sustainability safety of the intended functionality (SOTIF) intelligent vehicles adaptive observer data-driven FDI fault tolerant control

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive Optimal control of a DC Motor System Based on Policy Iteration 13

Robust Adaptive Optimal Control of a DC Motor System Based o...

引用

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

作者： Li, Yahui Xu, Dengguo Huang, Jiashun Ma, Yan School of Automation Guangxi University of Science and Technology Liuzhou545616 China School of Physics and Electrical Engineering Liupanshui Normal University Liupanshui553004 China

ISBN: (纸本)9798350361674

In this paper, robust optimal control method is used to deal with the speed regulation of a DC motor. Considering the parameter uncertainty, a state space model of the DC motor system is established. To enable the DC motor to track a predetermined speed, the integral variable of tracking error is augmented to the state variable. The tracking problem is transformed into the robust control problem of augmented uncertain linear systems. Then the robust control problem is converted into solving an optimal control with appropriate performance index. Moreover, a policy iteration algorithm in reinforcement learning is proposed to obtain a robust control law for the uncertain motor system, which enables the system output to asymptotically track an ideal signal. And the convergence of the proposed algorithm for the robust optimal control of uncertain linear systems is proved. The advantage of designing controllers through online policy iteration in reinforcement learning is without knowing the nominal system matrix. Finally, the effectiveness of the algorithm is verified by a numerical simulation example. © 2024 ieee.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Unified Model for Large-Scale Inexact Fixed-Point Iteration: A Stochastic Optimization Perspective

引用

ieee TRANSACTIONS ON AUTOMATIC control 2025年第4期70卷 2435-2449页

作者： Hashemi, Abolfazl Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

Calculating fixed points of a nonlinear function is a central problem in many areas of science and engineering with applications ranging from the study of dynamical systems to optimization and game theory. Fixed-point iteration methods provide a simple way to calculate the fixed point of nonexpansive mappings and they have been studied extensively. Emerging applications, however, necessitate the study of fixed-point calculation under various perturbations. For instance, in the data-driven identification of dynamical systems, the learning is typically erroneous, which in turn impacts the subsequent fixed calculations, which itself is an essential step for control. Motivated by such settings, in this work, we establish a general mathematical modeling framework for the study of inexact fixed-point iteration (FPI) algorithms. In doing so, we leverage and extend the recent advances in the stochastic optimization literature to derive new methods and convergence analysis results. In particular, adopting this view enables us to present a unified mathematical model to study the impact of inexact computations in both expansive and nonexpansive scenarios, a new technical approach for the analysis of inexact FPI methods, and a new inexact FPI method, which under certain assumptions, enjoys a faster convergence rate than traditional FPI algorithms in the expansive case.

关键词： Stochastic processes Optimization Convergence Mathematical models control systems Complexity theory Vectors Signal processing algorithms Reinforcement learning Noise Gradient methods iterative algorithms iterative methods optimization methods optimization models

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：