检索结果-南通市图书馆

一种基于流形正则化随机配置网络的化工过程故障识别方法

第37届中国控制会议

作者： Ning Wang Zhuo Sun Jianchuan Yin yongpeng weng Center for Intelligent Marine Vehicles School of Marine Electrical EngineeringDalian Maritime University Center for Intelligent Marine Vehicles Navigation CollegeDalian Maritime University

Subject to complex uncertainties,a novel surge-varying adaptive LOS（SALOS） based path following control scheme is addressed for underactuated marine vehicles（UMVs） in this *** contributions are as follows:（1） The surge velocity and heading angle are guided with path following errors,simultaneously,and the unknown sideslip angle is estimated by an adaptive term online.（2） Complex unknown uncertainties including the internal parameter perturbations,external environmental disturbances and unmodelled dynamics are compositely estimated by the constructed fuzzy uncertainty observer（FUO）;（3）Robust surge and heading tracking controllers based on the FUO are developed to ensure that the tracking errors and uncertainty observation errors are uniformly ultimately bounded（UUB）.Simulation studies are conducted to demonstrate the effectiveness and remarkable performance of the proposed SALOS scheme.

关键词： Underactuated marine vehicle Path following control Surge-varying adaptive LOS guidance Fuzzy uncertainty observation

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

仪器仪表学报 2021年第5期42卷 219-226页

作者：潘承燕徐进学翁永鹏大连海事大学船舶电气工程学院大连116026

考虑到化工过程故障数据的复杂非线性特性和样本潜在的根本结构特征,提出了一种基于流形正则化随机配置网络的故障识别方法。该方法在经典随机配置网络的基础上,在嵌入流形约束的监督机制下随机选取隐含参数,逐个添加隐含节点,然后使用... 详细信息

考虑到化工过程故障数据的复杂非线性特性和样本潜在的根本结构特征,提出了一种基于流形正则化随机配置网络的故障识别方法。该方法在经典随机配置网络的基础上,在嵌入流形约束的监督机制下随机选取隐含参数,逐个添加隐含节点,然后使用流形正则化最小二乘法计算隐含层的输出权值,保留了数据的重要几何特征,避免了信息冗余,有利于更好地识别出区别于不同类别的相关特征。在测试集上的实验表明,该方法对TE故障和半导体故障的识别准确率分别达到了87.72%和84.27%,均高于随机向量函数连接网络和随机配置网络方法。而且对于大部分故障类型,该方法的精确率和召回率较高,验证了所提方法进行故障识别的有效性和所建立模型的良好泛化能力。

关键词：随机配置网络流形正则化化工过程故障识别

Performance Enhancement and Bandwidth Guarantee in IEEE 802.11 Wireless LANs

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2004年第2期19卷 150-157页

作者： yongpeng Shi-DuanCheng NationalLaboratoryofSwitchingTechnologyandTelecommunicationNetworks BeijingUniversityofPostsandTelecommunicationsBeijing100876P.R.China

This paper first revisits the previously proposed NSAD (New Self-Adapt DCF) mechanism. Some modifications are presented to further enhance the performance of NSAD in the error-prone environment. Then a new MAC mechanism is proposed that can realize bandwidth guarantee by assigning different self-adapt parameters to users at different priority levels. The bandwidth guarantee property of this new mechanism is analyzed and the high priority users are found to have bandwidth guaranteed even in heavy contention condition, which is proved true not only by theoretical analysis but also by simulation results. At the same time the new scheme keeps the self-adapt character of NSAD, so the overall system utilization is kept very high in heavy contention condition compared with the previously studied DCF-based QoS mechanisms.

关键词： IEEE 802.11 performance enhancement bandwidth guarantee

Multi-Sensor Fusion Adaptive Estimation for Nonlinear Under-observed System with Multiplicative Noise

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

Chinese Journal of Electronics 2024年第1期33卷 282-292页

作者： yongpeng CUI Xiaojun SUN School of Electronic Engineering Heilongjiang University Key Laboratory of Information Fusion Estimation and Detection

The adaptive fusion estimation problem was studied for the multi-sensor nonlinear under-observed systems with multiplicative noise. A one-step predictor with state update equations was designed for the virtual state with virtual noise first of all. An extended incremental Kalman filter(EIKF) was then proposed for the nonlinear under-observed systems. Furthermore, an adaptive filtering method was given for optimization. The fusion adaptive incremental Kalman filter weighted by scalar was finally proposed. The comparison analysis was made to verify the optimization of the state estimation using adaptive filtering method in the filtering process.

关键词： Adaptive systems Information filters Matrices Adaptive estimation Kalman filters State estimation Nonlinear systems

Fabrication of green one-part geopolymer from silica-rich vanadium tailing via thermal activation and modification

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2022年第1期29卷 177-184页

作者： Shenxu Bao yongpeng Luo Yimin Zhang Hubei Key Laboratory of Mineral Resources Processing and Environment Wuhan University of TechnologyWuhan 430070China School of Resources and Environmental Engineering Wuhan University of TechnologyWuhan 430070China State Environmental Protection Key Laboratory of Mineral Metallurgical Resources Utilization and Pollution Control Wuhan University of Science and TechnologyWuhan 430081China Hubei Collaborative Innovation Center for High Efficient Utilization of Vanadium Resources Wuhan University of Science and TechnologyWuhan 430081China

The aim of this investigation was to prepare geopolymeric precursor from vanadium tailing(VT)by thermal activation and *** activation,a homogeneous blend of VT and sodium hydroxide was calcinated at an elevated temperature and then modified with metakaolin to produce a geopolymeric *** the thermal activation,the VT was corroded by sodium hydroxide and then sodium silicate formed on the particle *** water was added,the sodium silicate coating dissolved to release silicon species,which created an alkaline solution *** metakaolin then dissolved in the alkaline environment to generate aluminum species,which was followed by *** VT particles were connected by a gel produced during geopolymerization,which yielded a geopolymer with excellent mechanical *** investigation not only improves the feasibility of using geopolymer technology for large-scale and in-situ applications,but also promotes the utilization of VT and other silica-rich solid wastes.

关键词： vanadium tailing thermal activation geopolymeric precursor compressive strength leaching behavior

First order sea clutter cross section for bistatic shipborne HFSWR

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2017年第4期28卷 681-689页

作者： yongpeng Zhu Yinsheng Wei Peng Tong School of Electronics and Information Engineering Harbin Institute of Technology Harbin 150001 China

This paper studies the development on the first order sea clutter cross section for bistatic high frequency surface wave radar (HFSWR). Based on the received first order electric field expression, a closed-form of cross sections is derived to account for the case of receiving antenna array being mounted on the shipborne platform. The uniform linear motion and sway motion components are assumed to be responsible for the observed differences in comparison with the bistatic fixed antenna case. Correspondingly, simulations are conducted to study the sea clutter spectral characteristics for these two cases versus different system parameters and sea state conditions. It is shown numerically that the forward motion component will spread the Bragg lines severely and the influence triggered by the sway motion can be explained as the Bessel function modulation of the ordinary sea clutter spectra. The obtained results have important implications in the application of shipborne HFSWR technology to ocean remote sensing and target detection.

关键词： radar cross section (RCS) remote sensing by radar sea clutter high frequency surface wave radar (HFSWR)

Asymptotical behavior of ground state solutions for critical quasilinear Schrodinger equation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Mathematics in China 2020年第1期15卷 21-46页

作者： yongpeng CHEN Yuxia GUO Zhongwei TANG School of Mathematical Sciences Beijing Normal UniversityBeijing 100875China Department of Mathematics Tsinghua UniversityBeijing 100084China

This paper is concerned with the existence and asymptotical behavior of positive ground state solutions for a class of critical quasilinear Schrodinger *** using a change of variables and variational argument,we prove... 详细信息

关键词： Quasilinear Schrodinger equation critical exponent ground state solution asymptotical behavior

Flexible High Energy Density Sodium Dual-ion Battery with Long Cycle life

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

Energy & Environmental Materials 2022年第4期5卷 1285-1293页

作者： yongpeng Li Qun Guan Jianli Cheng Bin Wang Institute of Chemical Materials China Academy of Engineering PhysicsMianyang 621900China Institute of Fundamental and Frontiers Sciences Yangtze Delta Region Institute(Huzhou)University of Electronic Sciences and Technology of ChinaChengdu 611731China

Flexible fiber-shaped sodium dual-ion batteries(FSDIBS)as a proof of concept are fabricated by using the hierarchical ReS_(2) nanosheets anchored on the carbon nanotube(ReS_(2)@CNT)fiber as anode and graphite on the CNT as *** to large interlayer spacing and weak layer coupling force of the ReS_(2) nanosheets and the anion accommodation of the graphite combined with good flexibility of the CNT fiber,the FSDIBS demonstrate outstanding electrochemical performances with high working voltage and high specific volumetric energy density,durable cycling life,and good *** FSDIBS show a specific discharge capacity of 97.8 mAh cm^(−3) at a current density of 630 mA cm^(−3) and high specific energy density of 25.12 mWh cm^(−3)(based on the whole volume of the two electrodes)and superb stability with a capacity retention of 91.8%even after bending for 2100 ***,a series of ex situ/in situ characterizations are verified that the reversible shuttles of the Na^(+) cations and PF_(6)^(-) anions between the anode and cathode are simultaneously occurred during the charge/discharge process.

关键词： dual-ion batteries fiber-shaped flexibility ReS_(2) sodium ions

Security Issues and Defensive Approaches in Deep Learning Frameworks

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2021年第6期26卷 894-905页

作者： Hongsong Chen yongpeng Zhang Yongrui Cao Jing Xie Department of Computer Science University of Science and Technology Beijing(USTB)Beijing 100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing 100083China Department of Computer Science and Technology University of Science and Technology Beijing(USTB)Beijing 100083China Defense Electronics Institute China Industrial Control System Cyber Emergency Response TeamBeijing 100040China

Deep learning frameworks promote the development of artificial intelligence and demonstrate considerable potential in numerous ***,the security issues of deep learning frameworks are among the main risks preventing the wide application of *** on deep learning frameworks by malicious internal or external attackers would exert substantial effects on society and *** start with a description of the framework of deep learning algorithms and a detailed analysis of attacks and vulnerabilities in *** propose a highly comprehensive classification approach for security issues and defensive approaches in deep learning frameworks and connect different attacks to corresponding defensive ***,we analyze a case of the physical-world use of deep learning security *** addition,we discuss future directions and open issues in deep learning *** hope that our research will inspire future developments and draw attention from academic and industrial domains to the security of deep learning frameworks.

关键词： adversarial examples deep learning frameworks defensive approaches security issues