检索结果-南通市图书馆

Unified stabilizing controller synthesis approach for discrete-time intelligent systems with time delays by dynamic output feedback

在线全文

学校读者我要写书评

暂无评论

Science in China(Series F) 2007年第4期50卷 636-656页

作者： liu meiqin College of Electrical Engineering Zhejiang University Hangzhou 310027 China

A novel model, termed the standard neural network model （SNNM）, is advanced to describe some delayed （or non-delayed） discrete-time intelligent systems composed of neural networks and Takagi and Sugeno （T-S） fuzzy models. The SNNM is composed of a discrete-time linear dynamic system and a bounded static nonlinear operator. Based on the global asymptotic stability analysis of the SNNMs, linear and nonlinear dynamic output feedback controllers are designed for the SNNMs to stabilize the closed-loop systems, respectively. The control design equations are shown to be a set of linear matrix inequalities （LMIs） which can be easily solved by various convex optimization algorithms to determine the control signals. Most neural-network-based （or fuzzy） discrete-time intelligent systems with time delays or without time delays can be transformed into the SNNMs for controller synthesis in a unified way. Three application examples show that the SNNMs not only make controller synthesis of neural-network-based （or fuzzy） discrete-time intelligent systems much easier, but also provide a new approach to the synthesis of the controllers for the other type of nonlinear systems.

关键词： standard neural network model (SNNM) linear matrix inequality (LMI) intelligent system asymptotic stability output feedback control time delay discrete-time chaotic neural network Takagi and Sugeno (T-S) fuzzy model

DETERMINING THE STRUCTURES AND PARAMETERS OF RADIAL BASIS FUNCTION NEURAL NETWORKS USING IMPROVED GENETIC ALGORITHMS

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 1998年第2期10卷 68-73页

作者： meiqin liu Jida Chen 1. College of Information Engineering Central South University of Technology 410083 Changsha China

The method of determining the structures and parameters of radial basis function neural networks(RBFNNs) using improved genetic algorithms is proposed. Akaike′s information criterion (AIC) with generalization error term is used as the best criterion of optimizing the structures and parameters of networks. It is shown from the simulation results that the method not only improves the approximation and generalization capability of RBFNNs ,but also obtain the optimal or suboptimal structures of networks.

关键词： radial basis function neural network genetic algorithms Akaike′s information criterion overfitting

Cooperative neural-adaptive fault-tolerant output regulation for heterogeneous nonlinear uncertain multiagent systems with disturbance

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第7期64卷 181-192页

作者： Shanling DONG Guanrong CHEN meiqin liu Zheng-Guang WU College of Electrical Engineering Zhejiang University Institute for Advanced Study Chengdu University Department of Electrical Engineering City University of Hong Kong National Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University

This paper investigates the cooperative output regulation problem for heterogeneous nonlinear uncertain multiagent networked systems subject to actuator failure, bounded matched or mismatched disturbances or disturbances produced by a given linear exosystem. Accurate information about nonlinearity,actuator failure and disturbance may be completely unknown. First, a distributed finite-time observer is designed to estimate the dynamics of the exosystem on a finite-time interval over a communication ***, a neural-adaptive control protocol is proposed. It is shown that(i) closed-loop multiagent systems are asymptotically stable, with output synchronization errors that tend to zero in the absence of mismatched disturbance, and(ii) the states of the closed-loop multiagent systems and the output synchronization errors are bounded in the presence of mismatched disturbance. Finally, a simulation example is given to demonstrate the effectiveness of the proposed control strategy.

关键词： cooperative output regulation actuator failure matched/mismatched disturbance distributed finite-time observer neural-adaptive control

A top-down positioning scheme for underwater wireless sensor networks

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) 2014年第3期57卷 288-297页

作者： ZHANG SenLin ZHANG Qiang liu meiqin FAN Zhen College of Electrical Engineering Zhejiang University

In order to increase the localization coverage while keeping the localization error small in a unique network architecture in which there are not evenly distributed anchor nodes with great ability of communication or additional infrastructure,a Top-down Positioning Scheme(TPS)for underwater acoustic sensor networks is *** defining node’s confidence reasonably,TPS insures the quality of the new reference *** also refines the nodes which have just been positioned via the gradient method and helps non-localized nodes search for more reference nodes via the new scheme for 3D Euclidean distance *** comparing the new scheme for 3D Euclidean distance estimation with the existing scheme,the new scheme is shown to have greater ability to estimate two-hop Euclidean distance in 3D *** results show that TPS which integrates node’s confidence defined reasonably,the gradient method,and the new scheme for 3D Euclidean distance estimation can increase the localization coverage ratio,while keeping the localization error small.

关键词： underwater wireless sensor networks top-down positioning scheme node’s confidence gradient method 3D Euclidean distance estimation

Energy-aware routing for delay-sensitive underwater wireless sensor networks

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) 2014年第10期57卷 93-106页

作者： ZHANG SenLin WANG ZiXiang liu meiqin QIU MeiKang College of Electrical Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Zhejiang University Department of Computer Engineering San Jose State University

The energy reduction is a challenging problem in the applications of underwater wireless sensor networks(UWSNs). The embedded battery is difficult to be replaced and it has an upper bound on its *** relay is a popular method to reduce energy consumption in data transmission. The energy minimum path from source to destination in the sensor networks can be obtained through the shortest path ***, because of the node mobility, the global path planning approach is not suitable for the routing in UWSNs. It calls for an energy-efficient routing protocol for the high dynamic UWSNs. In this paper, we propose the modified energy weight routing(MEWR) protocol to deal with the energy-efficient routing of delaysensitive UWSNs. MEWR is a low flooding routing protocol. It can tolerate the node mobility in UWSNs and achieve a low end-to-end packet delay. MEWR can provide lower energy consumption than the existing low delay routing protocols through the dynamic sending power adjustment. The simulation results demonstrate the effectiveness of MEWR.

关键词： energy delay routing UWSN node mobility

A Novel Sensor Scheduling Algorithm Based on Deep Reinforcement Learning for Bearing-Only Target Tracking in UWSNs

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1077-1079页

作者： Linyao Zheng meiqin liu Senlin Zhang Jian Lan Institute of Artificial Intelligence and Robotics Xi’an Jiaotong UniversityXi’an 710049 State Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou 310027China College of Electrical Engineering Zhejiang UniversityHangzhou 310027China

Dear Editor,This letter is concerned with the energy-aware multiple sensor coscheduling for bearing-only target tracking in the underwater wireless sensor networks(UWSNs).Considering the traditional methods facing with the problems of strong environment dependence and lack flexibility,a novel sensor scheduling algorithm based on the deep reinforcement learning is ***,the sensors’co-scheduling strategy in UWSNs is formulated as Markov decision process(MDP).

关键词： Deep networks underwater

Natural Language Inference Using LSTM Model with Sentence Fusion 36

在线全文

学校读者我要写书评

暂无评论

Natural Language Inference Using LSTM Model with Sentence Fu...

Robust adaptive H∞ control for networked uncertain semi-Markov jump nonlinear systems with input quantization

第36届中国控制会议

作者： Senlin Zhang Siyang liu meiqin liu College of Electrical Engineering Zhejiang University

ISBN: (纸本)9781538629185

Natural language inference（NLI） is a challenge and the foundation of realization of artificial *** the availability of large-scale annotated corpus,the neural network model can be widely used in natural language *** this paper,we propose a long short-term memory（LSTM） model with Sentence Fusion architecture for NLI *** of modifying the internal structure of the LSTM recurrent neural network（RNN） model,we focused on how to make full use of the distributed expression of sentence generated by the LSTM *** improved the performance of basic LSTM recurrent neural networks on Stanford natural language inference（SNLI） corpus by adding Sentence Fusion modules which enrich the distributed expression of sentence generated by the *** results demonstrate that the LSTM with Sentence Fusion which reads premise and hypothesis to produce a final fusion representation from which a three-way classifier predicts label has a better performance than LSTM RNN encoders and Lexicalized classifier.

关键词： Natural Language Inference Long Short-Term Memory Recognizing Textual Entailment Deep Learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第8期65卷 285-286页

作者： Shanling DONG Guanrong CHEN meiqin liu Zheng-Guang WU College of Electrical Engineering Zhejiang University Department of Electrical Engineering City University of Hong Kong National Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University Institute for Advanced Study Chengdu University

Dear editor,Markov jump systems(MJSs), as one kind of switched systems, are a good candidate for modeling physical systems subject to abrupt variation in their structures or parameters caused by many reasons such as s...

关键词：

A Feature-Aided Multiple Model Algorithm for Maneuvering Target Tracking

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 566-568页

作者： Yiwei Tian meiqin liu Senlin Zhang Ronghao Zheng Shanling Dong College of Electrical Engineering Zhejiang University National Key Laboratory of Industrial Control Technology Zhejiang University IEEE National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University

Dear Editor,This letter deals with the tracking problem for non-cooperative maneuvering targets based on the underwater sensor networks. Considering the acoustic intensity feature of underwater targets, a feature-aide... 详细信息

关键词： underwater Aided letter