检索结果-内蒙古大学图书馆

6th Annual learning for Dynamics and control conference

作者： Tang, Wentao North Carolina State Univ Dept Chem & Biomol Engn Raleigh NC 27695 USA

This work proposes a data-driven approach for bifurcation analysis in nonlinear systems when the governing differential equations are not available. Specifically, regularized regression with barrier terms is used to learn a homeomorphism that transforms the underlying system to a reference linear dynamics - either an explicit reference model with desired qualitative behavior, or Koopman eigenfunctions that are identified from some system data under a reference parameter value. When such a homeomorphism fails to be constructed with low error, bifurcation phenomenon is detected. A case study is performed on a planar numerical example where a pitchfork bifurcation exists.

关键词： Bifurcation Nonlinear Dynamics Conjugacy Koopman Eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

data-driven Spectral Submanifold Reduction for Nonlinear Optimal control of High-Dimensional Robots

Data-Driven Spectral Submanifold Reduction for Nonlinear Opt...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Alora, John Irvin Cenedese, Mattia Schmerling, Edward Haller, George Pavone, Marco Stanford Univ Dept Aeronaut & Astronaut Stanford CA 94305 USA Swiss Fed Inst Technol Inst Mech Syst CH-8092 Zurich Switzerland

ISBN: (纸本)9798350323658

Modeling and control of high-dimensional, nonlinear robotic systems remains a challenging task. While various model- and learning-based approaches have been proposed to address these challenges, they broadly lack generalizability to different control tasks and rarely preserve the structure of the dynamics. In this work, we propose a new, data-driven approach for extracting control-oriented, low-dimensional models from data using Spectral Submanifold Reduction (SSMR). In contrast to other data-driven methods which fit dynamical models to training trajectories, we identify the dynamics on generic, low-dimensional attractors embedded in the full phase space of the robotic system. This allows us to obtain computationally-tractable models for control which preserve the system's dominant dynamics and better track trajectories radically different from the training data. We demonstrate the superior performance and generalizability of SSMR in dynamic trajectory tracking tasks vis-a-vis the state of the art, including Koopman operator-based approaches.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A Mechanism-Based data-driven Interval Energy Flow Calculation Method for Integrated Energy systems via Affine Arithmetic-Based Optimization

引用

ieee TRANSACTIONS ON SUSTAINABLE ENERGY 2024年第3期15卷 1562-1575页

作者： Tian, Hang Zhao, Haoran Xin, Sixiao Li, Haoran Wang, Ruiqi Liu, Shuai Shandong Univ Sch Elect Engn Jinan 250100 Peoples R China Shandong Elect Power Engn Consulting Co Ltd Jinan 250013 Peoples R China State Grid Shandong Integrated Energy Serv Co Ltd Jinan 250061 Shandong Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250100 Shandong Peoples R China

The multiple energy flows (MEF) in an integrated energy system (IES) have distinct physical properties, complex interaction mechanisms, and abundant sources of uncertainties, posing higher challenges for dispatchers to perceive system states from the present to a specific future. To accurately and efficiently quantify the impact of uncertainties on MEF, this paper proposes an affine arithmetic-based interval energy flow (IEF) calculation method, realized by a mechanism-based data-driven methodology. Firstly, an improved affine arithmetic-based optimization model of the electrical network is proposed, which implements data-driven quadratic approximation to guarantee the tractability of the optimization model. Next, affine arithmetic-based optimization models of gas and heating networks are realized by combining mathematical derivation and machine learning assistance. Additionally, the spatial branch-and-bound (SBB) algorithm guarantees the global optimality of each optimization process, facilitating computations in both grid-connected and islanded operational modes. Finally, numerical results on two IES study cases demonstrate that the proposed method outperforms other candidates, exhibiting superiority in terms of both speed and accuracy.

关键词： Optimization methods Mathematical models Arithmetic Uncertainty Voltage Load flow Iterative methods Integrated energy system multiple energy flow affine arithmetic data-driven

来源：评论

学校读者我要写书评

暂无评论

A data-driven Adaptive control Approach for Enhancing the Dynamic Response of VSGs in Varying Grid Conditions

引用

ieee TRANSACTIONS ON POWER DELIVERY 2025年第3期40卷 1421-1433页

作者： Fahad, Shah She, Buxin Yin, Junjie Li, Fangxing Cui, Hantao Bo, Rui Missouri Univ Sci & Technol Dept Elect & Comp Engn Rolla MO 65409 USA Parcif Northwest Natl Lab Optimizat & Control Grp Richland WA 99354 USA Pacific Northwest Natl Lab Optimizat & Control Grp Richland WA 99354 USA Univ Tennessee Knoxville Dept Elect Engn & Comp Sci Knoxville TN 37996 USA North Carolina State Univ Dept Elect & Comp Engn Raleigh NC 27606 USA Missouri Univ Sci & Technol Dept Elect & Comp Engn Rolla MO 65409 USA

Conventionally, a virtual synchronous generator (VSG) is designed for islanded mode (IM) operation to meet specific operational requirements such as the rate of change of frequency (RoCoF). However, the operation of VSG designed for IM may not meet the operational and control criteria in grid connected mode (GCM) when the grid conditions vary. In addition, conventional VSG control technology does not consider the influence of the presynchronization scheme when connected to a weak grid, which degrades the RoCoF in IM. To overcome the aforementioned challenges, the proposed study presents a twin-delayed deep deterministic policy gradient (TD3) algorithm to improve the seamless transition performance of VSG from IM to GCM and vice versa. In the first step, the VSG-based power system model is used as a foundation for problem formulation of the proposed TD3 algorithm. Secondly, a reward function is designed according to the performance requirements, i.e., frequency and RoCoF requirements, of the VSG in order to guide the training of the agent in varying load, power reference, and grid conditions. Finally, the superiority of the proposed algorithm over existing methods is validated in MATLAB/SIMULINK and RTDS based real-time simulation environment.

关键词： Impedance Mathematical models Transient analysis Training Real-time systems Reactive power Grid forming Voltage control Power system stability Power harmonic filters data-driven control virtual synchronous generator (VSG) grid conditions deep reinforcement learning microgrid

来源：评论

学校读者我要写书评

暂无评论

Machine learning modeling and predictive control of nonlinear boiler-turbine unit 3

Machine learning modeling and predictive control of nonlinea...

引用

3rd International conference on Smart Grids and Energy systems, SGES 2024

作者： Chen, Zhuo Hao, Yongsheng Xiao, Ming Wu, Guoquan Wu, Zhe School of Energy and Environment Southeast University Nanjing China Department of Chemical and Biomolecular Engineering National University of Singapore Singapore

ISBN: (纸本)9798331539634

The boiler-turbine unit (BTU) is extensively utilize-ed in power generation owing to its high reliability and operation flexibility. However, the control design of BTU system remains challenging due to its intricate dynamic properties, such as wide range of nonlinearities, large inertia, and strong coupling in multivariable systems. More challengingly, it is generally difficult and time-consuming to derive an accurate nonlinear model to capture the BTU dynamics and facilitate controller design. In this regard, machine learning methods show great potential in classical engineering fields, such as modeling nonlinear dynamic systems. In this article, a machine learning based model predictive control (MPC) scheme is presented for the nonlinear BTU. The machine learning method is first adopted to model the BTU using the input and output data directly, which can also be used to model a large class of nonlinear dynamic systems. Then, this data-driven model is deployed as a predictive model in the MPC for optimal control of the nonlinear BTU. Finally, a series of simulations are performed to validate the proposed method, including RNN training and testing, open-loop prediction simulation and closed-loop control simulation. © 2024 ieee.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Stochastic Nonlinear Model Predictive control with Look-ahead Deep Reinforcement learning for Autonomous Vehicle Motion control

Adaptive Stochastic Nonlinear Model Predictive Control with ...

引用

2024 International conference on Intelligent Robots and systems

作者： Zarrouki, Baba Wang, Chenyang Betz, Johannes Tech Univ Munich Chair Automot Technol Munich Germany Tech Univ Munich TUM Sch Engn & Design Professorship Autonomous Vehicle Syst D-85748 Garching Germany Munich Inst Robot & Machine Intelligence MIRMI Munich Germany

ISBN: (纸本)9798350377712;9798350377705

Propagating uncertainties through nonlinear system dynamics in the context of Stochastic Nonlinear Model Predictive control (SNMPC) is challenging, especially for high-dimensional systems requiring real-time control and operating under time-variant uncertainties such as autonomous vehicles. In this work, we propose an Adaptive SNMPC (aSNMPC) driven by Deep Reinforcement learning (DRL) to optimize uncertainty handling, constraints robustification, feasibility, and closed-loop performance. To this end, our SNMPC uses Polynomial Chaos Expansion (PCE) for efficient uncertainty propagation, limits its propagation time through an Uncertainty Propagation Horizon (UPH), and transforms nonlinear chance constraints into robustified deterministic ones. We conceive a DRL agent to proactively anticipate upcoming control tasks and to dynamically reduce conservatism by determining the most suitable constraints robustification factor kappa, and to enhance feasibility by choosing optimal UPH length T-u. We analyze the trained DRL agent's decision-making process and highlight its ability to learn context-dependent optimal parameters. We showcase the enhanced robustness and feasibility of our DRL-driven aSNMPC through the real-time motion control task of an autonomous passenger vehicle when confronted with significant time-variant disturbances while achieving a minimum solution frequency of 110Hz. The code used in this research is publicly accessible as open-source software: https://***/bzarr/TUM-control

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Flexible Imitation learning System Based on the Lyapunov Energy Function of the Neural Networks 25

A Flexible Imitation Learning System Based on the Lyapunov E...

引用

25th ieee International conference on Industrial Technology, ICIT 2024

作者： Zheng, Wenxu Li, Jinkun Guo, Jing Du, Yushi School Of Automation Guangdong University Of Technology Guangzhou China Shanghai Aerospace Control Technology Institute Shanghai China

ISBN: (纸本)9798350340266

Endowing robots with the capability to learn skills from human demonstrations is cutting-edge research. Traditional data-driven neural networks are typically employed to learn functions that represent dynamical systems for model skills. Despite the effectiveness of these networks, it has been difficult to guarantee that the learned function has a unique minimum. Although some algorithms attempt to improve it by imposing strong constraints, they cannot capture demonstration prefer-ences well due to structural limitations. In this paper, the specially designed residual network is introduced into the Lyapunov function and dynamical systems, ensuring that the system has a unique minimum during data-driven learning. Due to the residual network's ability to learn identity mapping, we have incorporated feature guidance in the network's input, leading to a significant improvement in the learning performance of the neural network. Experimental results demonstrate that our system outperforms traditional algorithms on the LASA handwritten dataset. © 2024 ieee.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

data-driven Inverse Cooperative Game control via Off-Policy Q-learning 43

Data-Driven Inverse Cooperative Game Control via Off-Policy ...

引用

43rd Chinese control conference (CCC)

作者： Wang, Mi Wu, Huai-Ning Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Peng Cheng Lab Shenzhen 518000 Peoples R China

ISBN: (纸本)9798350366907;9789887581581

In this article, the data-driven inverse cooperative differential game (ICDG) control problem is investigated. First, an excitation signal is selected to fully excite the system, and the system state and control input data is collected. Accordingly, the optimality condition of the cooperative differential game in the sense of Q-function is developed and the off-policy Q-learning technique is used to formulate the ICDG control as a problem of solving an algebraic equation. Second, the least-squares solution to the algebraic equation can be obtained provided that a rank condition is satisfied. Finally, a simulation example is provided, in which the cooperative driving behavior of two drivers is identified by using the proposed ICDG algorithm.

关键词： data-driven inverse differential game least-squares off-policy Q-learning

来源：评论

学校读者我要写书评

暂无评论

Blynk-Powered IoT System with Machine learning for Personalized Plant Care 8

Blynk-Powered IoT System with Machine Learning for Personali...

引用

8th International conference on Inventive systems and control, ICISC 202

作者： Pappula, Madhavi Myneni, Jaswanth Chowdary Gandra, Manasa Tadigadapa, Raghavendra Akella, Bala Krishna Murthy Lakireddy Balireddy College of Engineering AI&DS AP Mylavaram India

ISBN: (纸本)9798350386578

This research explores the development of a prototype Internet of Things (IoT)-enabled smart irrigation system and investigates its potential integration with machine learning (ML). The primary mechanism, constructed using Blynk, facilitates real-time sensor data monitoring (temperature, humidity, and moisture) and enables manual irrigation control via a mobile application. The secondary mechanism includes the integration of Machine learning (ML) model, facilitating data-driven predictions for optimal watering schedules. This ML integrated IoT system has the potential to revolutionize irrigation practices, promoting water conservation and potentially enhancing plant health through precise watering based on real-time sensor data and historical trends. © 2024 ieee.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

learning control Affine Neural NARX Models for Internal Model control Design

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 8137-8149页

作者： Xie, Jing Bonassi, Fabio Scattolini, Riccardo Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20156 Milan Italy Uppsala Univ Dept Informat Technol S-75105 Uppsala Sweden

This paper explores the use of control Affine Neural Nonlinear AutoRegressive eXogenous (CA-NNARX) models for nonlinear system identification and model-based control design. The idea behind this architecture is to match the known control-affine structure of the system to achieve improved performance. Coherently with recent literature of neural networks for data-driven control, we first analyze the stability properties of CA-NNARX models, devising sufficient conditions for their incremental Input-to-State Stability ( $\delta$ ISS) that can be enforced at the model training stage. The model's stability property is then leveraged to design a stable Internal Model control (IMC) architecture. The proposed control scheme is tested on a real Quadruple Tank benchmark system to address the output reference tracking problem. The results achieved show that (i) the modeling accuracy of CA-NNARX is superior to the one of a standard NNARX model for given weight size and training epochs, (ii) the proposed IMC law provides performance comparable to the ones of a standard Model Predictive controller (MPC) at a significantly lower computational burden, and (iii) the delta ISS of the model is beneficial to the closed-loop performance. Note to Practitioners-Many engineering systems, such as robotic manipulators and chemical reactors, are described by control Affine (CA) models, characterized by onlinear dynamics where the control variable enters in a linear way. If only this structural information is available without any additional knowledge, for instance on the order of the system or on the value of its parameters, a black-box identification approach can be followed to estimate the model from data. For these reasons, in this paper we propose a modeling and control design method suited for this class of systems. Specifically, we assume that the system is described by a CA-Neural Nonlinear AutoRegressive eXogenous (CA-NNARX) model. Then, the estimated model is used to design a stable I

关键词： control affine neural networks internal model control model predictive control control affine neural networks internal model control model predictive control

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：