检索结果-内蒙古大学图书馆

Multi-agent reinforcement learning system framework based on topological networks in Fourier space

APPLIED SOFT COMPUTING 2025年 174卷

作者： Sun, Licheng Ding, Ao Ma, Hongbin Beijing Inst Technol Sch Automation Beijing Peoples R China Beijing Inst Technol Key Lab Complex Syst Intelligent Control & Decis Beijing 100081 Peoples R China

Currently, multi-agent reinforcement learning (MARL) has been applied to various domains such as communications, network management, power systems, and autonomous driving, showcasing broad application scenarios and significant research potential. However, in complex decision-making environments, agents that rely solely on temporal value functions often struggle to capture and extract hidden features and dependencies within long sequences in multi-agent settings. Each agent's decisions are influenced by a sequence of prior states and actions, leading to complex spatiotemporal dependencies that are challenging to analyze directly in the time domain. Addressing these challenges requires a paradigm shift to analyze such dependencies from a novel perspective. To this end, we propose a Multi-Agent Reinforcement Learning system framework based on Fourier Topological Space from the foundational level. This method involves transforming each agent's value function into the frequency domain for analysis. Additionally, we design a lightweight weight calculation method based on historical topological relationships in the Fourier topological space. This addresses issues of instability and poor reproducibility in attention weights, along with various other interpretability challenges. The effectiveness of this method is validated through experiments in complex environments such as the StarCraft Multi-Agent Challenge (SMAC) and Google Football. Furthermore, in the Non-monotonic Matrix Game, our method successfully overcame the limitations of non-monotonicity, further proving its wide applicability and superiority. On the application level, the proposed algorithm is also applicable to various multi-agent system domains, such as robotics and factory robotic arm control. The algorithm can control each joint in a coordinated manner to accomplish tasks such as enabling a robot to stand upright or controlling the movements of robotic arms.

关键词： Reinforcement learning Multi-agent Deep learning Fourier space

来源：评论

学校读者我要写书评

暂无评论

LLM-Driven Cognitive Modeling for Personalized Travel Generation

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年

作者： Ge, Shichao Ye, Peijun Zhang, Renrui Zhou, Min Dong, Hairong Wang, Fei-Yue Beijing Jiaotong Univ Sch Automation & Intelligence Beijing 100044 Peoples R China Chinese Acad Sci Inst Automation Beijing 100190 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Shandong Univ Sci & Technol Coll Elect Engn & Automation Qingdao 266590 Peoples R China Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Traditional cognitive travel modeling typically employs a unified cognitive model to simulate representative travel behaviors, which may usually result in a weak characterization of user heterogeneity in paths, modes, and other factors. Large language model (LLM), by contrast, has significantly enhanced the anthropomorphic and personalized features of intelligent systems. To integrate their advantages, this article proposes LLM-driven cognitive modeling to generate more diverse and personalized travel demands. The new method sufficiently exploits LLM such as the llama as a basis and provides personalized travel plans so that more heterogenous travel demands could be generated. Additionally, introducing LLM into cognitive modeling can significantly reduce the time of model development, thus accelerating the research or engineering deployment. By calibrating and testing with one month's data from public transportation (buses and subways) in Beijing, our method, compared to traditional cognitive models, not only achieves better accuracy in reproducing typical travel patterns, but also generates more diverse ones, providing a more comprehensive input for computational experiments on traffic management and control strategies.

关键词： Computational modeling Decision making Accuracy Planning automation Computer architecture Traffic control Memory modules Cognition Adaptation models Agent-based model (ABM) cognitive model large language model (LLM) travel behavior

来源：评论

学校读者我要写书评

暂无评论

Real-Time Caustic Ratio Prediction in Alumina Digestion Process for Closed-Loop Operation: A Cloud-Edge Deep Learning Approach

引用

IEEE TRANSACTIONS ON automation SCIENCE AND ENGINEERING 2025年 22卷 10787-10800页

作者： Yu, Liyi Yu, Wen Jia, Yao Chai, Tianyou Northeastern Univ State Key Lab Synthet Automation Proc Ind Shenyang 110819 Peoples R China Natl Polytech Inst Dept Control Automatico CINVESTAV IPN Mexico City 07360 Mexico

The current control of alumina digestion process (ALDP) relies on infrequent manual assays for caustic ratio, leading to open-loop operation between assays and suboptimal performance. This paper proposes a novel cloud-edge collaboration (CEC) architecture utilizing deep learning for real-time caustic ratio prediction, enabling closed-loop operation at all times. Our method combines slow-sampled assays with fast-sampled process measurements. An autoregressive moving average with extra inputs (ARMAX) model is used for feature extraction, while an improved bidirectional gated recurrent unit (I-BiGRU) that incorporates a multi-head attention (MHA) mechanism bridges data gaps through prediction. A soft-collaboration mechanism ensures smooth model updates at the edge, enabling operators to make informed control decisions. Theoretical analysis guarantees the convergence of prediction errors. Real-world data from a large-scale alumina plant demonstrates the superior performance of our prediction method compared to the baseline methods. Additionally, industrial experiments validate the effectiveness of the CEC architecture in supporting human operators for ALDP closed-loop operation. Note to Practitioners-This paper was motivated by the challenges of achieving closed-loop operation in the alumina digestion process. The concept of cloud-edge collaboration (CEC) architecture with deep learning offers a powerful solution for various industrial scenarios that rely on infrequent manual measurements, where real-time monitoring of key performance indexes is essential. CEC can continuously predict these values, bridging the gaps between slow, accurate assays and frequent, less precise sensor data. This approach allows for closed-loop operation based on real-time predictions, potentially improving production efficiency and yield. The ability to handle data gaps makes our method applicable to processes with inherent measurement challenges. By implementing CEC in various industries, pr

关键词： Real-time systems Slurries Production Process control Temperature measurement Predictive models Cloud computing Deep learning Accuracy Sodium Alumina digestion process caustic ratio cloud-edge collaboration real-time prediction stable learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resilient Consensus of Second-Order Multiagent Networks With a Time-Varying Malicious Agent Set

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2025年第5期70卷 3308-3315页

作者： Liu, Ze-Qiang Liu, Zhi-Wei He, Ding-Xin Ye, Lintao Chi, Ming Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Wuhan 430074 Peoples R China

We address the problem of resilient consensus in second-order multiagent networks (MANs) with a time-varying set of malicious agents. Existing research typically assumes a static set of malicious agents. However, in real-world scenarios, network attacks and recoveries may lead to dynamic changes in the roles of agents. To overcome this challenge, a novel adaptive weighted subsequence reduction (AWSR) is proposed for resilient consensus in MANs with a dynamic malicious agent set. Based on the AWSR approach, a resilient consensus algorithm is designed for second-order MANs. Graph-theoretic conditions in the context of network robustness are derived to ensure resilient consensus in the considered MAN. We also extend the algorithm and analysis to MANs with communication delays. Finally, simulation experiments are conducted to demonstrate the effectiveness of the proposed algorithms.

关键词： Heuristic algorithms Safety Vehicle dynamics Switches Topology Robustness Delays Network topology Convergence Buildings Adaptive weighted subsequence reduction (AWSR) communication delays dynamic malicious agent set multiagent network (MAN) resilient consensus

来源：评论

学校读者我要写书评

暂无评论

Fault Detection for Piecewise Systems via a New Event-Triggered Mechanism

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第6期55卷 3802-3813页

作者： Wang, Xiao-Lei Ma, Zongzheng Deng, Chao Wang, Yu-Long Peng, Chen Shanghai Univ Sch Mechatron Engn & Automation Shanghai Key Lab Power Stn Automation Technol Shanghai 200444 Peoples R China Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing 210023 Peoples R China

In this article, the problem of piecewise fault detection (FD) for continuous-time piecewise linear (PWL) system with measurement outliers via new event-triggered (ET) mechanisms is investigated. First, piecewise FD observer with adaptive saturation of output errors is designed to mitigate the effect of outliers on the residual signals, such that false alarms are avoided through the established FD scheme. Then, based on the presented piecewise FD observer, a new ET design scheme that depends on the different regions where the states of the PWL system and piecewise FD observer are located is proposed, and an ET FD method is studied through the ET mechanisms. Unlike the existing results, the established FD scheme can effectively avoid false alarm caused by outliers, and the piecewise FD observer is designed separately from the new ET mechanisms, while co-design is necessary in the existing results. Finally, the effectiveness of the presented scheme is demonstrated by simulation examples.

关键词： Observers Power system stability control systems Load modeling Fault detection Event detection automation Vectors Switching systems Stability criteria Event-triggered (ET) mechanisms false alarm fault detection (FD) piecewise observer

来源：评论

学校读者我要写书评

暂无评论

Observer-based event-triggered formation tracking control for second-order multi-agent systems in constrained region

引用

Science China(Information Sciences) 2025年第2期68卷 151-169页

作者： Fenglan SUN Zhonghua XU Wei ZHU ■ KURTHS Key Lab of Intelligent Analysis and Decision on Complex Systems School of ScienceChongqing University of Posts and Telecommunications Key Lab of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of AutomationChongqing University of Posts and Telecommunications Department of Complexity Science Potsdam Institute for Climate Impact Research Institute of Physics Humboldt University of Berlin

In this paper, an event-triggered time-varying formation tracking control for a class of second-order nonlinear multiagent systems(MAS) operating within a constrained region is investigated. To mitigate the negative effects of external unknown disturbance, a novel disturbance observer with performance guarantees is proposed, enabling precise disturbance *** the artificial potential field(APF) method, a repulsive potential function is introduced to prevent inter-agent collisions as well as collisions with environmental obstacles. To reduce continuous communication and frequent system updates, a sliding mode technique is incorporated into the formation tracking controller, utilizing an event-triggered mechanism. The controller is also applicable to the formation control of MAS in switching-constrained regions. The achievement of the specified timevarying geometric formation is rigorously demonstrated through the Lyapunov framework. Numerical simulations are presented to validate the effectiveness of the theoretical results.

关键词： formation tracking control region constraints repulsive potential function event-triggered mechanism

来源：评论

学校读者我要写书评

暂无评论

A TFEM-Transformer Model for Lithium-Batteries Remaining Useful Life Prediction 16th

A TFEM-Transformer Model for Lithium-Batteries Remaining Use...

引用

16th International Conference on Modelling, Identification and control, ICMIC 2024

作者： Nie, Yixin Ren, Yanhui Wang, Anqi Xiang, Gang Qu, Chen Yang, Fan Department of Automation Tsinghua University Beijing100084 China Beijing Aerospace Automatic Control Institute Beijing100854 China National Key Lab on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789819617760

With the widespread application of lithium batteries, the focus on battery performance evaluation and safety has increased. Accurate prediction of battery degradation and remaining useful life is now a crucial research topic. Scholars have improved prediction accuracy by integrating multiple parameters related to battery degradation or combining various prediction models. However, environmental noise, sensor limitations, and faults can impact the quantity and quality of available feature sequences, rendering these methods partially ineffective. This paper proposes an optimized Transformer prediction model based on a Temporal Feature Enhancement Module (TFEM). By decomposing long-sequence signals and accurately capturing temporal features across different frequency bands through convolution, the model significantly improves the accuracy of future degradation process assessments and remaining useful life predictions of batteries, even with a single prediction model and a limited number of feature sequences. The proposed TFEM exhibits strong adaptability and can be easily integrated into other temporal prediction models to enhance prediction accuracy. The prediction model demonstrates high generalizability and robustness, achieving favorable prediction results even in scenarios involving short sequence predictions or a limited number of feature sequences. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Consensus of discrete-time heterogeneous multi-agent systems in noisy environments without velocity transmission

引用

ASIAN JOURNAL OF control 2025年第0期

作者： Chen, Jiali Zong, Xiaofeng Hou, Xuping Wang, Zi-Xuan China Univ Geosci Sch Automat Wuhan Peoples R China Hubei Key Lab Adv Control & Intelligent Automation Wuhan Peoples R China Minist Educ Engn Res Ctr Intelligent Technol GeoExplorat Wuhan Peoples R China

This paper investigates consensus control of discrete-time heterogeneous multi-agent systems with multiplicative noise. As the frequent absence of velocity sensors in real industrial environments, a control protocol is developed using absolute velocity and relative position measurement information. Then, the consensus control issue is reformulated as the stability issue of stochastic difference equations. By choosing an appropriate Lyapunov function, the above stability issue is studied, and the sufficient conditions for leader-free and leader-following discrete-time heterogeneous multi-agent systems to achieve both mean-square and almost-sure consensus are derived, respectively. Finally, numerical simulations are provided to validate the effectiveness of the main results.

关键词： consensus discrete-time heterogeneous multi-agent systems leader-following leader-free multiplicative noise

来源：评论

学校读者我要写书评

暂无评论

Optimal Output Synchronization of Euler-Lagrange Systems With Uncertain Time-Varying Quadratic Cost Functions

引用

IEEE TRANSACTIONS ON CYBERNETICS 2025年第4期55卷 1648-1658页

作者： Jiang, Liangze Wu, Zheng-Guang Wang, Lei Xu, Yong Che, Wei-Wei Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China Beijing Inst Technol Sch Automation Beijing 100081 Peoples R China Northeastern Univ State Key Lab Synthet Automation Proc Ind Shenyang 110819 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China

In this article, we study the optimal output synchronization problem (OOSP) for uncertain networked Euler-Lagrange (EL) systems. Specifically, the system outputs are expected to be synchronized at the solution of an uncertain distributed time-varying quadratic optimization problem, where each local time-varying cost function includes uncertain parameters. From a centralized perspective, we first develop a controller with adaptive control gains to guide the output of a double-integrator system toward the time-varying optimal solution. By employing the modified average estimators, we extend the centralized design to a distributed implementation to address the OOSP for uncertain EL systems. Using matrix trace properties and composite Lyapunov analysis, we prove that the system outputs can asymptotically converge to the desired time-varying optimal solution. Two examples are used to verify the proposed designs.

关键词： Cost function Time-varying systems Uncertainty Synchronization Vectors Multi-agent systems Electronic mail Location awareness Laplace equations Costs Distributed optimization Euler-Lagrange (EL) system optimal output synchronization time-varying cost function uncertainties

来源：评论

学校读者我要写书评

暂无评论

Grid-connection damping strategy for grid-forming VSG based on angular frequency lead-lag feedforward compensation

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2025年 167卷

作者： Shi, Rongliang Liang, Chuanfeng Li, Junhui Zhong, Zhixian Bai, Xinyuan Guilin Univ Technol Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Adv Mfg & Automation Technol Guilin 541006 Peoples R China Northeast Elect Power Univ Key Lab Modern Power Syst Simulat & Control & Rene Minist Educ Jilin 132011 Peoples R China

The primary frequency modulation coefficient of the grid-forming virtual synchronous generator (GFVSG) is coupled with the virtual damping coefficient, which leads to the problem that it is difficult to take into account both the dynamic oscillation and the steady-state deviation of the grid-connected active power (GCAP). To address this issue, an improved GFVSG grid-connected damping strategy based on angular frequency lead-lag feedforward compensation is proposed in this paper. This strategy introduces the angular frequency lead-lag feedforward compensation link into the GCAP closed-loop control loop of GFVSG, and improves both the GCAP dynamic and steady state response performances of GFVSG through reasonable adjustment of the lead-lag compensation parameters. Finally, according to the comparison results of simulation and experimental tests, it can be seen that the proposed grid-connected damping strategy can effectively solve the GCAP dynamic oscillation and steady-state deviation problems existing in GFVSG under the step disturbances of active power command and grid frequency.

关键词： Grid-forming Virtual Synchronous Generator (GFVSG) Dynamic oscillation Steady-state deviation Grid-connected active power (GCAP) Lead-lag feedforward compensation

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：