检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Xiangfei Niu, Yong Mao, Shiwen Cai, Yunlong He, Ruisi Ai, Bo Zhong, Zhangdui Liu, Yiru State Key Laboratory of Rail Traffic Control and Safety Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing100044 China National Mobile Communications Research Laboratory Southeast University Nanjing211189 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States Department of ISEE Zhejiang University China State Key Laboratory of Rail Traffic Control and Safety Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

With the development of wireless communication, higher requirements arise for train-ground wireless communications in high-speed railway (HSR) scenarios. The millimeter-wave (mm-wave) frequency band with rich spectrum resources can provide users in HSR scenarios with high performance broadband multimedia services, while the full-duplex (FD) technology has become mature. In this paper, we study train-ground communication system performance in HSR scenarios with mobile relays (MRs) mounted on rooftop of train and operating in the FD mode. We formulate a nonlinear programming problem to maximize network capacity by allocation of spectrum resources. Then, we develop a sequential quadratic programming (SQP) algorithm based on the Lagrange function to solve the bandwidth allocation optimization problem for track-side base station (BS) and MRs in this mm-wave train-ground communication system. Extensive simulation results demonstrate that the proposed SQP algorithm can effectively achieve high network capacity for train-ground communication in HSR scenarios while being robust to the residual self-interference (SI). Copyright © 2021, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Board-level Intelligent Built-in Test Design of Digital Input Module by Improved BP Neural Network

Board-level Intelligent Built-in Test Design of Digital Inpu...

引用

Data Driven control and Learning systems (DDCLS)

作者： Yasong Wang Congzhi Huang Jianhua Zhang Guolian Hou School of Control and Computer Engineering North China Electric Power University Beijing China Key Laboratory of Power Station Energy Transfer Conversion and System North China Electric Power University Beijing China

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

The built-in test (BIT) technology plays a major role in heavy-duty gas turbine control system. The accuracy of BIT is a guarantee for the normal operation of the equipment. In the actual production process, conventional BIT has a relatively high false alarm rate. In this paper, an intelligent built-in test (BIT) design method was presented for digital input (DI) module using a back propagation (BP), which was optimized by improved adaptive gravitational search algorithm (IAGSA) for quantitative analysis. In order to improve defect of the basic gravitational search algorithm (GSA), a tent map for population chaos initialization was proposed. Firstly, the status information that can reflect the failure of the DI module was chosen as experimental data. Then, these data were handled by normalization. After that, multiple IAGSA-BP models were established with status information about DI module. The output of these models can fully represent the fault status of the DI module. Finally, the experimental results are shown to validate the effectiveness of the proposed approaches.

关键词： Biological neural networks Neurons control systems Training Hidden Markov models Turbines Optimization

来源：评论

学校读者我要写书评

暂无评论

Online reinforcement learning control by direct heuristic dynamic programming: from time-driven to event-driven

arXiv

引用

arXiv 2020年

作者： Zhao, Qingtao Si, Jennie Sun, Jian Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing100081 China Department of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives. Among existing approximate dynamic programming (ADP) and reinforcement learning (RL) algorithms, the direct heuristic dynamic programming (dHDP) has been shown an effective tool as demonstrated in solving several complex learning control problems. It continuously updates the control policy and the critic as system states continuously evolve. It is therefore desirable to prevent the time-driven dHDP from updating due to insignificant system event such as noise. Toward this goal, we propose a new event-driven dHDP. By constructing a Lyapunov function candidate, we prove the uniformly ultimately boundedness (UUB) of the system states and the weights in the critic and the control policy networks. Consequently we show the approximate control and cost-to-go function approaching Bellman optimality within a finite bound. We also illustrate how the event-driven dHDP algorithm works in comparison to the original time-driven dHDP. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Erratum to “Time-Frequency Properties of the Short-Time Linear Canonical Transform and Its Application”

引用

Mathematical Problems in Engineering 2022年第1期2022卷

作者： Lei Huang Qingying Sun Qian Xi Yuhu Liu Mengsheng An Zihan Zhou School of Computer Science and Technology Huaiyin Normal University Huai’an 223300 *** School of Automation Chongqing University Chongqing 400044 *** Key Laboratory of Complex System Safety and Control Ministry of Education Chongqing University Chongqing 400044 ***

来源：评论

学校读者我要写书评

暂无评论

Robust model predictive control for linear systems with polytopic uncertainties under weighted mef-tod protocol

引用

IEEE Transactions on systems, Man, and Cybernetics: systems 2019年第7期49卷 1470-1481页

作者： Song, Yan Wang, Zidong Ding, Derui Wei, Guoliang Department of Control Science and Engineering Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and Technology Shanghai200093 China Department of Computer Science Brunel University London Uxbridge21589 United Kingdom School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia

This paper is concerned with the robust {-Grant-info-{2}/H-\infty } model predictive control problem for a class of linear systems with polytopic uncertainties under weighted maximum-error-first and try-once-discard (... 详细信息

This paper is concerned with the robust {-Grant-info-control/H-\infty } model predictive control problem for a class of linear systems with polytopic uncertainties under weighted maximum-error-first and try-once-discard (MEF-TOD) protocol. To prevent data from collision, the weighted MEF-TOD protocol is employed during the data transmission from sensors to controller, where only one sensor is allowed to transmit the measurement at every time instant. A switched linear system is established with respect to the switching signals generated by the adopted weighted MEF-TOD protocol. By taking the influence of the exogenous disturbance and the weighted MEF-TOD protocol into consideration, an online optimization problem with nonconvex conditions is formulated. Then, to deal with the couplings of unknown variables, singular value decomposition technique is utilized to transform the nonconvex conditions into solvable ones. Subsequently, a set of dynamic output-feedback controllers is designed to guarantee the stability of the closed-loop system with guaranteed robust { H-control/H-\infty } performance. Finally, a direct current motor example is used to illustrate the validity and effectiveness of the proposed methods. © 2013 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A security enhanced certificateless aggregate signcryption scheme for VANETs

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷

作者： Liu, Dong Tang, Wentao Wang, Liangliang Liu, Yang Liu, Zhiquan Zhang, Kai Li, Weiwei School of Computer Science and Technology Xidian University Xi’an710699 China the College of Computer Science and Technology Shanghai University of Electric Power Shanghai201306 China Institute of Network Security Inspection and Evaluation China Industrial Control System Cyber Emergency Response Team Beijing100040 China Key Laboratory of Industrial Information Security Perception and Evaluation Technology Ministry of Industry and Information Technology Beijing100040 China the College of Cyber Security Jinan University Guangzhou510632 China

Unlike traditional Internet of Things (IoT), Vehicular Ad Hoc Networks (VANETs) operate in open environments and transmit information through wireless communication technologies, making VANETs more susceptible to various attacks. To protect the security of drivers’ private information and improve the efficiency of the transportation system, various Certificateless Signcryption (CLSC) schemes have been proposed. Recently, Shao et al. designed a provably secure lightweight authentication scheme, which satisfied aggregate signcryption and batch unsigncryption. Unfortunately, we uncovered there are some vulnerabilities through security analysis in their scheme. In this paper, we first give an analysis method based on their security model with public key replacement to demonstrate the weakness. Second, we introduce a security enhanced CLSC scheme with a small index, demonstrating that the improved scheme is existential unforgeability under adaptive chosen message attacks (EUF-CMA), indistinguishability against adaptive chosen ciphertext attacks (IND-CCA2), and our scheme can resist extra Type-III adversaries which can combine the invalid signcryptions to generate a valid signcryption by formal security proof and heuristic security analysis. Finally, we compare our scheme with recent CLSC schemes in security performance, computation overhead, and communication overhead. The computational overhead of our scheme is below 41 ms under computing resource constraints while still meeting extremely high levels of security. The results show that our scheme is more suitable for VANETs. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Trajectory optimisation design of robot based on artificial intelligence algorithm

引用

International Journal of Wireless and Mobile Computing 2019年第1期16卷 35-40页

作者： Huang, Li Zhang, Kai Hu, Wei Li, Chengcheng College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Hubei Wuhan430081 China

Artificial intelligence has attracted more and more attention and has been widely used in all walks of life, especially in the education industry;artificial intelligence has gradually become the core. Aiming at the problem of robot trajectory planning in artificial intelligence, this paper applies the project teaching method to the course of artificial intelligence, regards trajectory planning as a project, analyses and studies it, uses ant colony algorithm to find the optimal planning path. Through the teaching of the project, the students will understand the ant colony algorithm more deeply. The algorithm is programmed independently to achieve the final trajectory optimisation. Students become the main body of the classroom, give full play to the initiative and enthusiasm of the students, through the operation of the project to train the students' innovative ability and cooperation ability, and improve the overall quality of the college students. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Pinning boundary sampled-data synchronization of coupled reaction–diffusion neural networks

引用

Neurocomputing 2025年 648卷

作者： Zi-Peng Wang Bo-Ming Chen Junfei Qiao Biao Luo Huai-Ning Wu Tingwen Huang Guangwei Chen School of Information Science and Technology Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System and Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing 100124 China School of Automation Central South University Changsha 410083 China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen 518107 China

In this paper, the pinning boundary sampled-data (SD) synchronization problem of coupled reaction–diffusion neural networks (CRDNNs) with SD-based couplings is investigated under boundary and distributed SD measurements. First, a pinning boundary SD controller is designed to effectively address the synchronization problem of CRDNNs, utilizing boundary and distributed SD measurements and requiring only a small number of sensors and actuators. Then, linear matrix inequalities provide adequate conditions that ensure exponential stability of the synchronization error system by using the designed pinning boundary SD controller, derived through inequality techniques and Lyapunov functionals. Finally, we present a numerical example to showcase the practical applicability and effectiveness of the proposed pinning boundary SD synchronization method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning of long-horizon sparse-reward robotic manipulator tasks with base controllers

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Xin, Minjian Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering University of California San Diego La Jolla CA92093 United States Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Coordinated Emergency Frequency control Strategy for Renewables-Rich Power systems Based on Multi-Agent Reinforcement Learning

SSRN

引用

SSRN 2025年

作者： Sun, Zhenglong Han, Junpeng Chen, Weihan Zhang, Rui Liu, Yong Levron, Yoash Belikov, Juri Department of Electrical Engineering Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Software Science Tallinn University of Technology Akadeemia Tee 15a Tallinn12618 Estonia

With the rapid growth of renewable energy in the power system and the implementation of large-capacity LCC-HVDC projects, the frequency support capability of the grid has been reduced. Simultaneously, the renewables-rich grid faces the risk of high-power shocks due to LCC-HVDC blocking. Existing centralized, single-measure approaches and the model-based emergency frequency control (EFC) methods are facing tremendous challenges. To fill this gap, this paper proposes a frequency emergency control method for renewables-rich grids that coordinates LCC-HVDC emergency power support and load shedding. The coordination of the two stabilization measures is modeled as a decentralized partially observable Markov decision process, and a multi-agent reinforcement learning (MADRL) approach is employed to optimize the power of measures for each stabilization control substation. An MADRL algorithm that integrates the system frequency response model is developed to overcome the problem of inaccurate evaluation of centralized action value in the MADRL algorithm used for EFC. This approach allows for the global optimization of the distributed coordination strategy through centralized training. The effectiveness and adaptability of the proposed method are demonstrated through simulations of the modified IEEE 39-bus system. © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

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：