检索结果-南通市图书馆

An Online Q-Learning Method for Linear-Quadratic Nonzero-Sum Stochastic Differential Games with Completely Unknown Dynamics

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第5期37卷 1907-1922页

作者： ZHANG Bao-Qiang WANG Bing-Chang CAO Ying school of control Science and engineering Shandong University

In this paper, the authors design a reinforcement learning algorithm to solve the adaptive linear-quadratic stochastic n-players non-zero sum differential game with completely unknown dynamics. For each player, a critic network is used to estimate the Q-function, and an actor network is used to estimate the control input. A model-free online Q-learning algorithm is obtained for solving this kind of problems. It is proved that under some mild conditions the system state and weight estimation errors can be uniformly ultimately bounded. A simulation with five players is given to verify the effectiveness of the algorithm.

关键词： Actor-critic algorithm model-free adaptive control nonzero-sum stochastic game reinforcement learning

Value iteration algorithm for continuous-time linear quadratic stochastic optimal control problems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第2期67卷 170-180页

作者： Guangchen WANG Heng ZHANG school of control Science and engineering Shandong University

In this study, we investigate a continuous-time infinite-horizon linear quadratic stochastic optimal control problem with multiplicative noise in control and state variables. Using the techniques of stochastic stability, exact observability, and stochastic approximation, a value iteration algorithm is developed to solve the corresponding generalized algebraic Riccati equation. Unlike the existing policy iteration algorithm, this algorithm does not rely on an initial stabilizing control. Further, this algorithm can also be used to compute policy evaluation steps that arise in the policy iteration algorithm. Herein, a simulation example is provided to validate the obtained results.

关键词： stochastic systems optimal control linear quadratic stochastic problem generalized algebraic Riccati equation value iteration algorithm

Global adaptive output-feedback tracking with prescribed performance for uncertain nonlinear systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 150-164页

作者： Yuan WANG Yungang LIU school of control Science and engineering Shandong University

At present, one typical control strategy for guaranteeing transient and steady-state performance is funnel control and prescribed performance control. The strategy features completely discarding the system nonlinearities, even if they are completely known and available. Such an intrinsic feature requires the controller to produce a larger control effect to eliminate the negative impact caused by the high nonlinearities, leading to a conservative controller. In this paper, we fully take advantage of known information on nonlinearities in control design, instead of completely discarding it as done in funnel control. Particularly, we leverage adaptive techniques(i.e., high-gain dynamic compensation) to deal with unknown system nonlinearities. Meanwhile, we integrate the tools of output feedback, tracking control, and the performance *** such, an adaptive output-feedback scheme is developed for global tracking with spatiotemporal performance specifications: arbitrarily given tracking accuracy and accuracy-ensured time. A simulation example supports the developed approach.

关键词： uncertain nonlinear systems output feedback prescribed performance unknown control direction dynamic high gain global tracking

On the size generalizibility of graph neural networks for learning resource allocation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 239-254页

作者： Jiajun WU Chengjian SUN Chenyang YANG Beihang University school of electronics and Information engineering

Size generalization is important for learning resource allocation policies in wireless systems with time-varying scales. If a neural network for learning a wireless policy is not generalizable to the size of its input, it has to be re-trained whenever the system scale changes, which hinders its practical use due to the unaffordable training costs. Graph neural networks(GNNs) have been shown with size generalization ability empirically when optimizing resource allocation. Yet, are GNNs naturally size generalizable? In this paper,we argue that GNNs are not always size generalizable for resource allocation. We find that the aggregation and activation functions of the GNNs for learning a class of wireless policies play a key role in their size generalization ability. We take the GNN with the mean aggregator, called mean-GNN, as an example to reveal a size generalization condition. To demonstrate how to satisfy the condition, we learn power and bandwidth allocation policies for ultra-reliable low-latency communications and show that selecting or pretraining the activation function in the output layer of mean-GNN can make the GNN size *** results validate our analysis and evaluate the performance of the learned policies.

关键词： size generalization graph neural networks resource allocation permutation equivariance

A comprehensive analysis of DAC-SDC FPGA low power object detection challenge

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 300-320页

作者： Jingwei ZHANG Guoqing LI Meng ZHANG Xinye CAO Yu ZHANG Xiang LI Ziyang CHEN Jun YANG school of electronics Science and engineering Southeast University

The lower power object detection challenge(LPODC) at the IEEE/ACM Design Automation Conference is a premier contest in low-power object detection and algorithm(software)-hardware co-design for edge artificial intelligence, which has been a success in the past five years. LPODC focused on designing and implementing novel algorithms on the edge platform for object detection in images taken from unmanned aerial vehicles(UAVs), which attracted hundreds of teams from dozens of countries to participate. Our team SEUer has been participating in this competition for three consecutive years from 2020 to 2022 and obtained sixth place respectively in 2020 and 2021. Recently, we achieved the championship in 2022. In this paper, we presented the LPODC for UAV object detection from 2018 to 2022, including the dataset, hardware platform,and evaluation method. In addition, we also introduced and discussed the details of methods proposed by each year's top three teams from 2018 to 2022 in terms of network, accuracy, quantization method, hardware performance, and total score. Additionally, we conducted an in-depth analysis of the selected entries and results, along with summarizing representative methodologies. This analysis serves as a valuable practical resource for researchers and engineers in deploying the UAV application on edge platforms and enhancing its feasibility and reliability. According to the analysis and discussion, it becomes evident that the adoption of a hardware-algorithm co-design approach is paramount in the context of tiny machine learning(TinyML).This approach surpasses the mere optimization of software and hardware as separate entities, proving to be essential for achieving optimal performance and efficiency in TinyML applications.

关键词： tiny machine learning object detection convolutional neural networks algorithm-hardware co-design low power field programmable gate array

Adaptive multi-channel Bayesian graph attention network for IoT transaction security

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第3期10卷 631-644页

作者： Zhaowei Liu Dong Yang Shenqiang Wang Hang Su school of Computer and control engineering Yantai UniversityYantai264005China Department of electronics Information and BioengineeringPolitecnico di MilanoMilan20133Italy

With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic *** to the vast amounts of data created by numerous 5G IoT devices,the Ethereum platform has become a tool for the storage and sharing of IoT device data,thanks to its open and tamper-resistant ***,Ethereum account security is necessary for the Internet of Things to grow quickly and improve people's *** modeling Ethereum trans-action records as a transaction network,the account types are well identified by the Ethereum account classifi-cation system established based on Graph Neural Networks(GNNs).This work first investigates the Ethereum transaction ***,experimental metrics reveal that the Ethereum transaction network is neither optimal nor even satisfactory in terms of accurately representing transactions per *** flaw may significantly impede the classification capability of GNNs,which is mostly governed by their *** work proposes an Adaptive Multi-channel Bayesian Graph Attention Network(AMBGAT)for Ethereum account clas-sification to address this *** uses attention to enhance node features,estimate graph topology that conforms to the ground truth,and efficiently extract node features pertinent to downstream *** extensive experiment with actual Ethereum transaction data demonstrates that AMBGAT obtains competitive performance in the classification of Ethereum accounts while accurately estimating the graph topology.

关键词： Internet of things Graph representation learning Node classification Security mechanism

State estimation for delayed switched positive systems: delayed radius approach

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 190-205页

作者： Weizhong CHEN Zhongyang FEI Xudong ZHAO Zheng-Guang WU school of electronics and Information Xi'an Polytechnic University Research Institute of Intelligent control and Systems Harbin Institute of Technology Key Laboratory of Intelligent control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology school of control Science and engineering Dalian University of Technology State Key Laboratory of Industrial control Technology Institute of Cyber-Systems and ControlZhejiang University

In this paper, an interval estimation scheme is developed for delayed switched positive systems（DSPS） with mode-dependent average dwell time switching. A lossless zonotopic estimation approach is proposed for the delayed intersection zonotope with the positive generator matrix. First, considering the existence of asynchronism between the system mode and the correction matrix mode, the mismatched intersection zonotope is constructed for DSPS to verify the consistency between the system model and ***, by utilizing the introduced radius definitions, the ?∞performance is addressed to optimize the size of delayed intersection zonotopes. Subsequently, we present a joint-design approach of switching signals and the mode-dependent correction matrix by constructing positive generator matrix-based delayed radius functions. Furthermore, guaranteed nonnegative state bounds are derived for the considered DSPS based on the proposed lossless zonotopic estimation criteria. Finally, detailed simulations are conducted to validate the feasibility and superiority of the developed methods.

关键词： delayed switched positive systems interval estimation asynchronous correction matrix zonotopes mode-dependent average dwell time

Low-temperature chemistry in plasma-driven ammonia oxidative pyrolysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Green Energy & Environment 2024年第9期9卷 1477-1488页

作者： Mingming Zhang Qi Chen Guangzhao Zhou Jintao Sun He Lin school of Mechanical Electronic and Control Engineering Beijing Jiaotong University school of Mechanical engineering Shanghai Jiao Tong University

Ammonia is gaining increasing attention as a green alternative fuel for achieving large-scale carbon emission reduction. Despite its potential technical prospects, the harsh ignition conditions and slow flame propagation speed of ammonia pose significant challenges to its application in engines. Non-equilibrium plasma has been identified as a promising method, but current research on plasma-enhanced ammonia combustion is limited and primarily focuses on ignition characteristics revealed by kinetic models. In this study, low-temperature and low-pressure chemistry in plasma-assisted ammonia oxidative pyrolysis is investigated by integrated studies of steady-state GC measurements and mathematical simulation. The detailed kinetic mechanism of NH3decomposition in plasma-driven Ar/NH3and Ar/NH3/O2mixtures has been developed. The numerical model has good agreements with the experimental measurements in NH3/O2consumption and N2/H2generation, which demonstrates the rationality of modelling. Based on the modelling results, species density profiles, path flux and sensitivity analysis for the key plasmaproduced species such as NH2, NH, H2, OH, H, O, O（1D）, O2（a1△g）, O2（b1∑g+）, Ar*, H-, Ar+, NH3+, O2-in the discharge and afterglow are analyzed in detail to illustrate the effectiveness of the active species on NH3excitation and decomposition at low temperature and relatively higher E/N values. The results revealed that NH2, NH, H as well as H2are primarily generated through the electron collision reactions e + NH3→ e + NH2+ H, e + NH3→ e + NH + H2and the excited-argon collision reaction Ar*+ NH3+ H → Ar + NH2+ 2H, which will then react with highly reactive oxidative species such as O2*, O*, O, OH, and O2to produce stable products of NOx and H2O. NH3→ NH is found a specific pathway for NH3consumption with plasma assistance, which further highlights the enhanced kinetic effects.

关键词： Non-equilibrium plasma Ammonia fuel Oxidative pyrolysis Pathway flux analysis Sensitivity analysis

An online value iteration method for linear-quadratic mean field social control with unknown dynamics

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 38-39页

作者： Bing-Chang WANG Shumei LI Ying CAO school of control Science and engineering Shandong University

Mean field(MF) models have been widely applied to economics, control theory, and other fields. Its prominent feature is that the individual influence on the overall population is negligible and the impact of the entire system to the single agent is significant and cannot be ignored. As a classical problem in control theory, linear quadratic(LQ) control for MF models has been widely investigated(e.g., [1, 2]).

关键词：