检索结果-内蒙古大学图书馆

Adaptive Regulated Sparsity Promoting Approach for data-driven Modeling and control of Grid-Connected Solar Photovoltaic Generation

引用

ieee TRANSACTIONS ON SUSTAINABLE ENERGY 2025年第1期16卷 560-572页

作者： Zhang, Zhongtian Khazaei, Javad Blum, Rick S. Lehigh Univ Dept Elect & Comp Engn Bethlehem PA 18015 USA

This paper introduces a new statistical learning technique based on sparsity promotion for data-driven modeling and control of solar photovoltaic (PV) systems. Compared with conventional sparse regression techniques that might introduce computational complexities when the number of candidate functions increases, an innovative algorithm, named adaptive regulated sparse regression (ARSR) is proposed. The ARSR adaptively regulates the hyperparameter weights of candidate functions to best represent the dynamics of PV systems. This method allows for the application of different sparsity-promoting hyperparameters for each state variable, whereas the conventional approach uses the same hyperparameter for all state variables, which may result in not excluding all the unrelated terms from the dynamics. Consequently, the proposed method can identify more complex dynamics with greater accuracy. Utilizing this algorithm, open-loop and closed-loop models of single-stage and two-stage PV systems are obtained from measurements and are utilized for control design purposes. Moreover, it is demonstrated that the proposed data-driven approach can be successfully employed for fault analysis studies, which distinguishes its capabilities from other data-driven techniques. Finally, the proposed approach is validated through real-time simulations.

关键词： Power system dynamics Adaptation models Nonlinear dynamical systems Voltage control Mathematical models Analytical models Heuristic algorithms data-driven modeling Photovoltaic systems Adaptive systems Adaptive regulated sparse regression (ARSR) closed-loop data-driven modeling photovoltaic (PV) systems single-stage PV two-stage PV

来源：评论

学校读者我要写书评

暂无评论

data-driven Combined Longitudinal and Lateral control for the Car Following Problem

引用

ieee TRANSACTIONS ON control systems TECHNOLOGY 2025年第3期33卷 991-1005页

作者： Cui, Leilei Chakraborty, Sayan Ozbay, Kaan Jiang, Zhong-Ping MIT Cambridge MA 02139 USA NYU Tandon Sch Engn Dept Elect & Comp Engn Control & Networks Lab Brooklyn NY 11201 USA NYU C2SMARTER Ctr Tandon Sch Engn Dept Civil & Urban Engn Brooklyn NY 11201 USA NYU Dept Elect & Comp Engn Dept Civil & Urban Engn Control & Networks LabTandon Sch Engn Brooklyn NY 11201 USA

This article studies the problem of data-driven combined longitudinal and lateral control of autonomous vehicles (AVs) such that the AV can stay within a safe but minimum distance from its leading vehicle and, at the same time, in the lane. Most of the existing methods for combined longitudinal and lateral control are either model-based or developed by purely data-driven methods such as reinforcement learning. Traditional model-based control approaches are insufficient to address the adaptive optimal control design issue for AVs in dynamically changing environments and are subject to model uncertainty. Moreover, the conventional reinforcement learning approaches require a large volume of data, and cannot guarantee the stability of the vehicle. These limitations are addressed by integrating the advanced control theory with reinforcement learning techniques. To be more specific, by utilizing adaptive dynamic programming (ADP) techniques and using the motion data collected from the vehicles, a policy iteration algorithm is proposed such that the control policy is iteratively optimized in the absence of the precise knowledge of the AV's dynamical model. Furthermore, the stability of the AV is guaranteed with the control policy generated at each iteration of the algorithm. The efficiency of the proposed approach is validated by the integrated simulation of SUMO and CommonRoad.

关键词： Adaptation models Vehicle dynamics Mathematical models Transportation Roads Reinforcement learning Nonlinear dynamical systems Electronic mail Dynamic programming Accuracy Adaptive dynamic programming (ADP) combined longitudinal and lateral control connected vehicles

来源：评论

学校读者我要写书评

暂无评论

data-Model Hybrid-driven Safe Reinforcement learning for Adaptive Avoidance control Against Unsafe Moving Zones

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2025年 PP卷 PP页

作者： Wang, Ke Mu, Chaoxu Zhang, Anguo Sun, Changyin Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230026 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China

With the gradual application of reinforcement learning (RL), safety has emerged as a paramount concern. This article presents a novel data-model hybrid-driven safe RL (SRL) scheme to address the challenge of avoidance control in the operation domain containing multiple moving unsafe zones. First, the avoidance problem is transformed into the optimal control problem of an augmented system by encoding a barrier function (BF) term into the cost function. Then, using the idea of integral RL (IRL), an adaptive learning algorithm is proposed for generating safe control policies, in which the actor-critic neural network (NN) structure is established with the aid of state-following (StaF) kernel function. The policy iteration process is executed by this structure;specifically, the critic network undergoes gradient-descent adaptation, while the actor network employs gradient projection updating. Particularly, via a state extrapolation technique, both real-time experience and simulated experience are utilized in the learning process. Next, closed-loop stability and weight convergence are theoretically substantiated. Finally, the effectiveness of the proposed scheme is demonstrated on a single integrator system, a nonlinear numerical system, and a unicycle kinematic system;besides, its advantages over the existing control methods are illustrated by comparisons.

关键词： Safety Optimal control Cost function Artificial neural networks Kernel Adaptation models Reinforcement learning Mathematical models Extrapolation data models Actor-critic neural network (NN) adaptive dynamic programming (ADP) avoidance control policy iteration safe reinforcement learning (SRL) state extrapolation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optimization of Transportation Networks Using Big data-driven Reinforcement learning

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2025年

作者： Wang, Xin Rani, Shalli Cao, Xia Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Chitkara Univ Inst Engn & Technol Rajpura 140401 Punjab India China Med Univ Shengjing Hosp Dept Data Ctr Shenyang 110004 Peoples R China Northeastern Univ Sch Comp Sci & Engn Shenyang 110169 Peoples R China

The dynamic optimization of large-scale transportation networks presents significant challenges due to their complexity, stochasticity, and the need for real-time decision-making. In conventional methods, there is often a failure to employ fully the resources of big data present in cities, thus not being able to respond appropriately to fluctuations in traffic conditions. This paper introduces a novel enhanced big data-driven reinforcement learning (EBD-RL) algorithm for dynamic optimization of transportation networks, addressing these challenges by leveraging advanced machine learning techniques and heterogeneous data sources. We propose a hierarchical control framework that decomposes the global optimization problem into manageable sub-problems while maintaining network-wide coordination. The EBD-RL algorithm incorporates prioritized experience replay and adaptive exploration strategies to improve learning efficiency and stability in high-dimensional state spaces. Experiments on a realistic urban network show that our method is superior to six state-of-the-art methods. Results show that EBD-RL reduces total travel time by up to 30% compared to the best baseline under various traffic demands and connected autonomous vehicle penetration rates. Furthermore, the algorithm exhibits enhanced resilience to traffic incidents, achieving up to 33% faster network recovery time in severe disruption scenarios. These findings highlight the potential of big data-driven reinforcement learning approaches to significantly improve the efficiency, adaptability, and resilience of modern urban transportation systems.

关键词： Transportation Optimization Vehicle dynamics Big data Reinforcement learning Real-time systems Heuristic algorithms Roads Traffic control Streams Dynamic optimization transportation networks big data reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Group Formation Tracking of Heterogeneous Multiagent systems Using Reinforcement learning

引用

ieee TRANSACTIONS ON control OF NETWORK systems 2025年第1期12卷 497-509页

作者： Wang, Yuhan Wang, Zhuping Zhang, Hao Yan, Huaicheng Tongji Univ Shanghai Res Inst Intelligent Autonomous Syst Shanghai 201210 Peoples R China Natl Key Lab Autonomous Intelligent Unmanned Syst Shanghai 201210 Peoples R China Frontiers Sci Ctr Intelligent Autonomous Syst Mini Shanghai 201210 Peoples R China Tongji Univ Coll Elect & Informat Engn Dept Control Sci & Engn Shanghai 201804 Peoples R China Key Lab Adv Control & Optimizat Chem Proc Minist E Shanghai 200237 Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

This article introduces a novel distributed control protocol to address the problem of output group formation tracking for heterogeneous multiagent systems. In contrast to the existing group formation control protocols that rely on the system matrices, our approach leverages input-state data to design the optimal control gains in the framework of off-policy reinforcement learning. Specifically, an event-triggered distributed consensus estimator is proposed to estimate the leaders' system matrices and the convex hulls spanned by the leaders while ensuring the exclusion of Zeno behavior. Based on the proposed estimator, we establish an approximate optimal distributed control protocol for each follower to achieve output group formation tracking, which can be solved by the designed data-driven policy iteration algorithm. Finally, a numerical example is provided to show the efficacy of the proposed control approach.

关键词： Protocols Formation control Vectors control systems Network systems Optimal control Symmetric matrices Decentralized control System dynamics Event detection data-driven policy iteration heterogeneous multiagent systems (MASs) optimal control output group formation

来源：评论

学校读者我要写书评

暂无评论

data-driven Optimal Tracking control for Discrete-Time Nonlinear systems With Unknown Dynamics Using Deterministic ADP

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2025年第1期36卷 1184-1198页

作者： Song, Shijie Gong, Dawei Zhu, Minglei Zhao, Yuyang Huang, Cong Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu 611731 Peoples R China

This article aims to solve the optimal tracking problem (OTP) for a class of discrete-time (DT) nonlinear systems with completely unknown dynamics. A novel data-driven deterministic approximate dynamic programming (ADP) algorithm is proposed to solve this kind of problem with only input-output (I/O) data. The proposed algorithm has two advantages compared to existing data-driven deterministic ADP algorithms for the OTP. First, our algorithm can guarantee optimality while achieving better performance in the aspects of time-saving and robustness to data. Second, the near-optimal control policy learned by our algorithm can be implemented without considering expected control and enable the system states to track the user-specified reference signals. Therefore, the tracking performance is guaranteed while simplifying the algorithm implementation. Furthermore, the convergence and stability of the proposed algorithm are strictly proved through theoretical analysis, in which the errors caused by neural networks (NNs) are considered. At the end of this article, the developed algorithm is compared with two representative deterministic ADP algorithms through a numerical example and applied to solve the tracking problem for a two-link robotic manipulator. The simulation results demonstrate the effectiveness and advantages of the developed algorithm.

关键词： Approximate dynamic programming (ADP) data-driven neural network (NN) optimal tracking problem (OTP)

来源：评论

学校读者我要写书评

暂无评论

Combining data-driven and Event-driven for Online learning Predictive control in Power Converters

引用

ieee TRANSACTIONS ON POWER ELECTRONICS 2025年第1期40卷 563-573页

作者： Liu, Xing Qiu, Lin Fang, Youtong Wang, Kui Li, Yongdong Rodriguez, Jose Shanghai Dianji Univ Coll Elect Engn Shanghai 201306 Peoples R China State Key Lab High Speed Maglev Transportat Techno Qingdao 266111 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China Zhejiang Univ Univ Illinois Urbana Champaign Inst Hangzhou 310027 Peoples R China Tsinghua Univ Dept Elect Engn State Key Lab Power Syst Beijing 100084 Peoples R China Univ San Sebastian Santiago Fac Engn Santiago 8420524 Chile

The combination of data-driven and event-driven opens up the possibility of alleviating the long-standing research challenges for power converters in classical finite control-set model predictive control, i.e., model parametric uncertainties and unnecessary switching loss. Inspire by this, we will launch a major study on the problem of designing online learning predictive controller. Unlike most prior works in this area, it can be accomplished by an integrated data-driven and event-driven design framework. To be more precise, the design procedures rely on a combination of developing a data-driven model-free adaptive predictive control, introducing an online reinforcement learning technique, and leveraging an event-driven mechanism. Furthermore, we also provide extensions to robust model-free predictive control design based on input-output data and against unknown uncertainties under low switching frequency operation, while avoiding a priori knowledge of model information and weighting factors. Finally, we illustrate our approach and highlight its advantages on a numerical example, and the results presented are promising and motivate further research in this field.

关键词： control systems Predictive models Predictive control Uncertainty Switches Standards Robustness Finite control-set model predictive control (FCS-MPC) low switching frequency (SF) power converters robust model-free predictive control (MFPC) weighting factors

来源：评论

学校读者我要写书评

暂无评论

data-driven Distributed Robust Monitoring and control Optimization for Interconnected systems

引用

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第2期21卷 1399-1408页

作者： Wang, Hao Luo, Hao Qiao, Xinyu Huo, Mingyi Xu, Xiaoyi Harbin Inst Technol Dept Control & Simulat Ctr Harbin 150001 Peoples R China Univ Shanghai Sci & Technol Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China

This article proposes a projection-aided robust distributed monitoring and control optimization approach for interconnected systems with disturbances. The disturbances and state coupling between subsystems are a challenge in achieving accurate distributed process monitoring using data-driven techniques. To address the problems, a distributed adaptive residual generator uses the average consensus algorithm to perform data fusion on the subsystem residual generator to implement disturbance decoupling process monitoring. The key to implementing this process is to use input and output data disturbance in the perturbed orthogonal complementary space to drive the adaptive residual generator. Then, using the projection technique, the residual signal in the disturbance space drives the distributed learning of plug-and-play (PnP) controller parameters. The average consensus algorithm ensures that the subsystem PnP controller parameter gradient consistency converges to the centralized design. The feasibility and effectiveness of the proposed approach are verified and demonstrated through a simulation.

关键词： Monitoring Interconnected systems Generators Optimization Observers Aerospace electronics Accuracy Distributed databases Computational modeling Principal component analysis data-driven (DD) distributed monitoring disturbance rejection control interconnected systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Melt Pool Homogenization Through Geometry-Informed control in Laser Powder Bed Fusion Using Reinforcement learning

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 2986-2997页

作者： Park, Bumsoo Chen, Alvin Mishra, Sandipan Rensselaer Polytech Inst Dept Mech Aerosp & Nucl Engn Troy NY 12180 USA

This paper presents a real-time geometry-informed control strategy to homogenize melt pool measurements in laser powder bed fusion (L-PBF) using reinforcement learning. The learning control strategy incorporates geometric information of the scan path as well as in-situ melt pool measurements to compute the laser power signal for reducing in-process melt pool inhomogeneities. First, we design and validate a data-driven model to train the reinforcement learning agent in simulation, with the goal of reducing the amount of experimental data needed for training. Using this simulation-based training approach has the added benefit of avoiding unsafe or infeasible experiments, an issue that is often encountered in training the reinforcement learning agent. After training, the learned control strategy attenuates the 1-norm error by 37% and standard deviation by 39% in simulation. We then deploy this learned control strategy in an experimental test bed for a new scan geometry. In this test scenario, the policy achieves a 30% reduction in error, and a 36% reduction in melt pool signal variation, thereby illustrating the potential of reinforcement learning in real-time geometry-agnostic control for L-PBF. Finally, we demonstrate that the reinforcement learning agent delivers the same level of performance as a model-based feedforward controller with PID feedback, with 20x less computational time for a single geometry.

关键词： Geometry Power lasers Real-time systems Process control Prediction algorithms Training Reinforcement learning Laser powder bed fusion (L-PBF) reinforcement learning sim-to-real learning data-driven model metal additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Efficient Reward Shaping for Multiagent systems

引用

ieee TRANSACTIONS ON control OF NETWORK systems 2025年第1期12卷 687-699页

作者： Donge, Vrushabh S. Lian, Bosen Lewis, Frank L. Davoudi, Ali Univ Texas Arlington Dept Elect Engn Arlington TX 76010 USA Auburn Univ Dept Elect & Comp Engn Auburn AL 36849 USA

In this article, we address the reward-shaping problem of large-scale multiagent systems (MASs) using inverse reinforcement learning (IRL). The learning MAS does not have prior knowledge of the cost function of the target MAS and aims to reconstruct it based on the target's demonstrations. We propose a scalable model-free IRL algorithm for a large-scale MAS, where dynamic mode decomposition (DMD) extracts dynamic modes and builds a projection matrix. This significantly reduces the data required while retaining the system's essential dynamic information. The proofs of the algorithm's convergence, stability, and nonuniqueness of the state reward weight are presented. The efficacy of our method is validated with a large-scale consensus network, by comparing the required data sizes and computational time for reward shaping with and without DMD.

关键词： Artificial neural networks Heuristic algorithms Optimal control control systems Network systems Dimensionality reduction Stability criteria data-driven control dynamic mode decomposition (DMD) inverse reinforcement learning (IRL) large-scale system optimal 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：