检索结果-南通市图书馆

Diesel Engine Valve Clearance Fault Diagnosis Based on Features Extraction Techniques and FastICA-SVM

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2017年第4期30卷 991-1007页

作者： Ya-bing Jing Chang-Wen Liu Feng-Rong bi xiao-Yang bi Xia Wang Kang Shao State Key Laboratory of Engines Tianjin UniversityTianjin 300072 China School of Mechanical Engineering Tianjin UniversityTianjin 300072 China Internal Combustion Engine Research Institute Tianjin University Tianjin 300072 China

Numerous vibration-based techniques are rarely used in diesel engines fault diagnosis in a direct way, due to the surface vibration signals of diesel engines with the complex non-stationary and nonlinear time-varying fea- tures. To investigate the fault diagnosis of diesel engines, fractal correlation dimension, wavelet energy and entropy as features reflecting the diesel engine fault fractal and energy characteristics are extracted from the decomposed signals through analyzing vibration acceleration signals derived from the cylinder head in seven different states of valve train. An intelligent fault detector FastICA-SVM is applied for diesel engine fault diagnosis and classification. The results demonstrate that FastlCA-SVM achieves higher classification accuracy and makes better general- ization performance in small samples recognition. Besides, the fractal correlation dimension and wavelet energy and entropy as the special features of diesel engine vibration signal are considered as input vectors of classifier FastlCA- SVM and could produce the excellent classification results. The proposed methodology improves the accuracy of fea- ture extraction and the fault diagnosis of diesel engines.

关键词： Feature extraction Diesel engine valve train FastlCA PCA Support vector machine

Research on Transfer Learning of Vision-based Gesture Recognition

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2021年第3期18卷 422-431页

作者： bi-xiao Wu Chen-Guang Yang Jun-Pei Zhong College of Automation Science and Engineering South China University of TechnologyGuangzhou 510640China Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou 511442China Foshan Newthinking Intelligent Technology Company Ltd. Foshan 528231China

Gesture recognition has been widely used for human-robot *** present,a problem in gesture recognition is that the researchers did not use the learned knowledge in existing domains to discover and recognize gestures in new *** each new domain,it is required to collect and annotate a large amount of data,and the training of the algorithm does not benefit from prior knowledge,leading to redundant calculation workload and excessive time *** address this problem,the paper proposes a method that could transfer gesture data in different *** use a red-green-blue(RGB)Camera to collect images of the gestures,and use Leap Motion to collect the coordinates of 21 joint points of the human ***,we extract a set of novel feature descriptors from two different distributions of data for the study of transfer *** paper compares the effects of three classification algorithms,i.e.,support vector machine(SVM),broad learning system(BLS)and deep learning(DL).We also compare learning performances with and without using the joint distribution adaptation(JDA)*** experimental results show that the proposed method could effectively solve the transfer problem between RGB Camera and Leap *** addition,we found that when using DL to classify the data,excessive training on the source domain may reduce the accuracy of recognition in the target domain.

关键词： Transfer learning gesture recognition red-green-blue(RGB)Camera Leap Motion joint distribution adaptation(JDA)

An Optimization Approach of Rotor Contour for Variable Reluctance Resolver

在线全文

学校读者我要写书评

暂无评论

CES Transactions on Electrical Machines and Systems 2021年第3期5卷 257-261页

作者： LongFei xiao Chao bi the researcher of Fortior Technology(Shenzhen)Co.Ltd. Machinery Department University of Shanghai for Science and TechnologyShanghaiChina

An effective approach for optimizing the rotor contour for variable reluctance(VR)resolver is *** this approach,the procedure for optimizing the rotor is divided into two parts:the establishment of initial shape curve,and then computation for the *** order to simplify the process of the former,a shape function is *** the latter is carried out by Taguchi optimization method and finite element method(FEM).An example of a 3-10 VR resolver is used to present the procedure of the optimization,and the testing results confirmed the effectivity of the approach.

关键词： VR resolver Rotor contour Optimization Fourier series Taguchi FEM

Exploring fermionic multiplet dark matter through precision measurements at the CEPC

在线全文

学校读者我要写书评

暂无评论

Chinese Physics C 2022年第9期46卷 159-172页

作者： Lin-Qing Gao xiao-Jun bi Jin-Wei Wang Qian-Fei xiang Peng-Fei Yin Key Laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China School of Physical Sciences University of Chinese Academy of SciencesBeijing 100049China Scuola Internazionale Superiore di Studi Avanzati(SISSA) via Bonomea 26534136 TriesteItaly INFN Sezione di Triestevia Valerio 234127 TriesteItaly Institute for Fundamental Physics of the Universe(IFPU) via Beirut 234151 TriesteItaly Center for High Energy Physics Peking UniversityBeijing 100871China

New physics could be explored through loop effects using the precision measurements at the Circular Electron Positron Collider(CEPC)owing to its clean collision environment and high *** this paper,we focus on two dark matter models that involve additional electroweak fermionic *** calculate their one-loop corrections in five processes,i.e.,e^(+)e^(-)→μ^(+)μ^(-),Zh,W^(+)W^(-),ZZ,and,Zγ,and investigate the corresponding signatures at the CEPC with the projected *** observe that the detectable parameter regions of these processes are *** combined analysis shows that the mass of dark matter m_(χ^(0)_(1))in these two models can be probed up to-150GeV and-450GeV,respectively,at a 95%confidence level.

关键词： CEPC dark matter loop correction

Assessing Flood Risk Using Reservoir Flood Control Rules

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2016年第1期27卷 68-73页

作者： xiang Fu Yadong Mei Zhihuai xiao State Key Laboratory of Water Resources and Hydropower Engineering Science Wuhan University Wuhan 430072 China Hubei Provincial Collaborative Innovation Center for Water Resources Security Wuhan 430072 China College of Power & Mechanical Engineering Wuhan University Wuhan 430072 China

The application of conventional flood operation regulation is restricted due to insufficient description of flood control rules for the Pubugou Reservoir in southern China. Based on the requirements of different flood control objects, this paper proposes to optimize flood control rules with punishment mechanism by defining different parameters of flood control rules in response to flood inflow forecast and reservoir water level. A genetic algorithm is adopted for solving parameter optimization problem. The failure risk and overflow volume of the downstream insufficient flood control capacity are assessed through the reservoir operation policies. The results show that an optimised regulation can provide better performance than the current flood control rules.

关键词： reservoir flood control operation parameters optimization of rules risk assessment.

Outage analysis of opportunistic multi-antenna relay selection in decode-and-forward relay networks

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2010年第4期17卷 6-12页

作者： WANG xiao-xiang ZHENG Zi-yun Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing 100876 China

This article studies the closed-form expressions of outage performance for opportunistic relay under aggregate power constraint in decode-and-forward （DF） relay networks over Rayleigh fading channels, assuming that multiple antennas are available at the relay node. According to whether instantaneous signal-to-noise ratio （SNR） or average SNR can be utilized for relay selection, two opportunistic relay schemes, opportunistic multi-antenna relay selection （OMRS） and average best relay selection （ABRS） are proposed. The performances of both two schemes are evaluated by means of theoretical analysis and simulation, it is observed that OMRS is outage-optimal among multi-antenna relay selection schemes and closely approaches the beamforming （BF） scheme known as theoretical outage-optimal. Compared with previous single-antenna opportunistic relaying （OR） scheme, OMRS brings remarkable performance improvement, which is obtained from maximum ratio combining （MRC） and beamforming techniques. It is also shown that the performance of ABRS in asymmetric channels is close to OMRS in the low and median SNR range.

关键词： relay selection multiple antennas multiple relays decode and forward cooperative networks

Criterion of Semi-Markov Dependent Risk Model

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2014年第7期30卷 1273-1280页

作者： xiao Yun MO xiang Qun YANG Department of Basic Subjects Hu’nan University of Finance and Economics College of Mathematics and Computer Science Hu’nan Normal University

A rigorous definition of semi-Markov dependent risk model is given. This model is a generalization of the Markov dependent risk model. A criterion and necessary conditions of semi- Markov dependent risk model are obtained. The results clarify relations between elements among semi-Markov dependent risk model more clear and are applicable for Markov dependent risk model.

关键词： Semi-Markov dependent risk model Markov dependent risk model criterion necessarycondition Markov chain

Curve Shortening Flow in Arbitrary Dimensional Euclidian Space

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2005年第4期21卷 715-722页

作者： Yun Yan YANG xiao xiang JIAO School of Mathematical Sciences Peking University Beijing 100871 P. R. China Graduate School Chinese Academy of Sciences P. R. China

In this paper, curve shortening flow in Euclidian space R^n（n≥3） is studied, and S. Altschuler＇s results about flow for space curves are generalized. We prove that the curve shortening flow converges to a straight line in infinite time if the initial curve is a ramp. We also prove the planar phenomenon when the curve shortening flow blows up.

关键词： Curve shortening flow Singularity formation Blow up

Resource allocation algorithm with limited feedback for multicast single frequency networks

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2012年第2期13卷 146-154页

作者： Ming-wei TANG xiao-xiang WANG MOE Key Laboratory of Universal Wireless Communications Beijing University of Posts and TelecommunicationsBeijing 100876China

The single frequency network (SFN) can provide a multimedia broadcast multicast service over a large coverage area. However, the application of SFN is still restricted by a large amount of feedback. Therefore, we propose a multicast resource allocation scheme based on limited feedback to maximize the total rate while guaranteeing the quality of service (QoS) requirement of real-time services. In this scheme, we design a user feedback control algorithm to effectively reduce feedback load. The algorithm determines to which base stations the users should report channel state information. We then formulate a joint subcarrier and power allocation issue and find that it has high complexity. Hence, we first distribute subcarriers under the assumption of equal power and develop a proportional allocation strategy to achieve a tradeoff between fairness and QoS. Next, an iterative water-filling power allocation is proposed to fully utilize the limited power. To further decrease complexity, a power iterative scheme is introduced. Simulation results show that the proposed scheme significantly improves system performance while reducing 68% of the feedback overhead. In addition, the power iterative strategy is suitable in practice due to low complexity.

关键词： Multicast Single frequency networks (SFN) Orthogonal frequency division multiplexing access (OFDMA) Resource allocation