检索结果-南通市图书馆

Atlas Compatibility Transformation:A Normal manifold Learning Algorithm

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2015年第4期12卷 382-392页

作者： Zhong-Hua Hao shi-wei ma Fan Zhao School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Power Station Automation TechnologyShanghai University

Over the past few years,nonlinear manifold learning has been widely exploited in data analysis and machine *** paper presents a novel manifold learning algorithm,named atlas compatibility transformation(ACT),It solves two problems which correspond to two key points in the manifold definition:how to chart a given manifold and how to align the patches to a global coordinate space based on *** the first problem,we divide the manifold into maximal linear patch(MLP) based on normal vector field of the *** the second problem,we align patches into an optimal global system by solving a generalized eigenvalue *** with the traditional method,the ACT could deal with noise datasets and fragment ***,the mappings between high dimensional space and low dimensional space are *** on both synthetic data and real-world data indicate the effection of the proposed algorithm.

关键词： Nonlinear dimensionality reduction manifold learning normal vector field maximal linear patch ambient space.

Relationship between Dislocation Density in P91 Steel and Its Nonlinear Ultrasonic Parameter

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2015年第11期22卷 1024-1030页

作者： Ye-qing CAI Jin-zhong SUN Cheng-jie LIU shi-wei ma Xi-cheng wei School of materials Science and Engineering Shanghai University School of Mechatronics Engineering and Automation Shanghai University

P91 steel is an important bearing material used in nuclear power plants. The study of its mechanical degradation behavior is important for ensuring safe operation. The relationship between the dislocation density of P91 steel under different strains and the corresponding nonlinear ultrasonic parameter β was studied. The dislocation density of strained samples was estimated by X-ray diffraction. Nonlinear ultrasonic testing was conducted to evaluate β, showing that this value increased with increasing dislocation density induced by different tensile elongations. It was shown that the ultrasonic secondharmonic generation technique can effectively evaluate the degradation behavior of metallic materials, and the prediction of the residual life of bearing parts in service can be made based on β and the dislocation density.

关键词： dislocation density P91 steel nonlinear ultrasonic second order harmonic

Simultaneous Identification of Process Structure, Parameters and Time-delay Based on Non-negative Garrote

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2020年第6期17卷 873-882页

作者： Jian-Guo Wang Qian-Ping Xiao Tiao Shen shi-wei ma Wen-Tao Rao Yong-Jie Zhang School of Mechatronical Engineering and Automation Shanghai UniversityShanghai Key Lab of Power Station Automation TechnologyShanghai 200072China Institute of Environment and Resources Baosteel Research InstituteShanghai 201900China

In practice,the model structure,parameters and time-delay of the actual process may vary ***,the general identification methods of the 3 items are performed with separate procedures which is very inconvenient in practical *** view of the fact that variable selection procedure can ensure a compact model with robust input-output,relation and in order to explore the feasibility of variable selection algorithm for the simultaneous identification of process structure,parameters and time-delay,non-negative garrote(NNG)algorithm is introduced and applied to system identification and the corresponding procedures are *** application of NNG variable selection algorithm to the identification of single input single output(SISO)system,multiple input multiple output(MIN1O)system and Wood-Berry tower industry are *** identification accuracy and the time-series variable selection results are analyzed and compared between NNG and ordinary least square(OLS)*** derived excellent results show that the proposed NNG-based modeling algorithm can be utilized for simultaneous identification of the model structure,parameters and time-delay with high precision.

关键词： Model structure model parameter time-delay non-negative garrote variable selection.

Implications of the *** Crisis for the Development of China's Telecom Sector

在线全文

学校读者我要写书评

暂无评论

China Communications 2008年第4期5卷 116-119页

作者： shi wei,ma Conghui,Zhao Xuefeng Institute of Economic System and management,National Development and Reform Commission,Beijing,100035,P.R.C Natl Dev & Reform Commiss Inst Econ Syst & Management Beijing 100035 Peoples R China

The financial turbulence caused by the *** crisis has a far-reaching impact on the global financial system and economic *** on an in-depth analysis of the cause of *** crisis and its effects on China and global economy,in combi-nation with the current status of China's telecom sector,this article puts forward policy suggestions for the de-velopment and regulation of China's telecom sector.

关键词： subprime crisis telecom regulation devel-opment strategy

Non-destructive Testing of CFRP Using Pulsed Thermographic Data Enhanced by Wavelet Transform-based Image Denoising 36

在线全文

学校读者我要写书评

暂无评论

Non-destructive Testing of CFRP Using Pulsed Thermographic D...

第36届中国控制会议

作者： Jian-Guo Wang Zhi-Duo Cao Bang-Hua Yang shi-wei ma Min-Rui Fei shi-Qi Huang Yuan Yao Tao Chen Xiao-Fei Wang School of Mechatronical Engineering and Automation Shanghai UniversityShanghai Key Lab of Power Station Automation Technology Department of Chemical Engineering National Tsing-Hua University Department of Chemical and Process Engineering University of Surrey Shanghai Zhenhua Heavy Industries Company Limited

ISBN: (纸本)9781538629185

Pulsed thermography（PT） is a widely used non-destructive testing（NDT） technique for defect detection in carbon fiber reinforced polymers（CFRP） *** signal reconstruction（TSR） is often employed to process thermographic data due to its excellent performance in enhancing the contrast between defects and ***,TSR does not reduce the noise of thermographic data *** solve this problem,this thesis proposes an image denoising method based on wavelet *** experiment results show that dealt with wavelet transform the characteristics of the defective regions are more clearly compared with previous *** the signal-to-noise ratio（SNR） values are improved obviously at the same time.

关键词： Pulsed Thermography Non-Destructive Testing Thermographic Signal Reconstruction Wavelet Transform

A Mothed of Improving Identification Accuracy via Deep Learning Algorithm under Condition of Deficient Labeled Data 36

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Mothed of Improving Identification Accuracy via Deep Learn...

第36届中国控制会议

作者： Jian-Guo Wang Zhi-Duo Cao Bang-Hua Yang shi-wei ma Min-Rui Fei Hao Wang Yuan Yao Tao Chen Xiao-Fei Wang School of Mechatronical Engineering and Automation Shanghai UniversityShanghai Key Lab of Power Station Automation Technology Department of Chemical Engineering “Tsing-Hua University” Department of Chemical and Process Engineering University of Surrey Shanghai Zhenhua Heavy Industries Company Limited

ISBN: (纸本)9781538629185

In industrial process, some important variables such as quality index, efficiency index and concentration of product components are difficult or even impossible to be measured directly due to the limitation of technology. This phenomenon leads to few labeled data and plenty of unlabeled data. Traditional identification method for controlled auto regressive（CAR） model usually cannot deal with unlabeled training data. As a result, these traditional identification methods may receive poor identification precision or even cannot work entirely. To solve the problems above, this paper proposes a new identification method based on deep learning（DL）. Firstly, the CAR model is transformed into finite impulse response（FIR） model solve the problem of lack of autoregressive part;Secondly, autoencoder of deep learning make full use of unlabeled data to pretrain the model;Thirdly, small amount of label data is used for fine-tuning. As a semi-supervised learning method, deep learning can be able to extract more information from unlabeled data than traditional supervised learning method. The results show that the proposed method can acquire higher identification accuracy than BP neural network.

关键词： System Identification Deep Learning Controlled Auto Regressive Finite Impulse Response

A Wind Tunnel Experimental Study on the Wake Characteristics of a Horizontal Axis Wind Turbine

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Thermal Science 2025年第1期34卷 145-158页

作者： GUO Xingduo LI Yinran LI Rennian ma Yulong wei Kui College of Energy and Power Engineering Lanzhou University of Technology Key Laboratory of Fluid machinery and Systems Gansu Provincial Technology Centre for Wind Turbines

The characteristics of wind turbine wakes are influenced by multiple factors,including the atmospheric boundary layer(ABL) wind and wind turbine operating conditions(e.g.,tip speed ratio and yaw angle).In this study,two types of ABL winds with different velocity gradients and turbulence intensities are generated in a wind tunnel through configurations of spires,baffles,and various numbers of roughness elements.A wind turbine with a rotor diameter of 0.8 m and a hub height of 0.6 m is tested under varying tip speed ratios,yaw angles,and ABL wind *** results indicate that the streamwise velocity deficit in the near-wake region becomes more pronounced with an increase in the tip speed ratio,while the far-wake velocity deficit remains largely unaffected by changes in the tip speed *** the yaw angle increases,the wake deflection becomes more prominent and the wake narrows;the offset of the wake center at various downstream positions grows linearly,reaching a maximum value of approximately half the rotor ***,the turbulence level and influence range in the wake region are reduced when the turbine is *** ABL wind conditions,high turbulence intensity in the incoming flow accelerates wake recovery,and the Reynolds stress at different lateral positions tends to become consistent with increasing longitudinal ***,turbulence has a significant impact on the meandering characteristics of the wind turbine wake,with greater fluctuations in the wake center observed under higher turbulence ***,this study provides insights that could inform the optimal operation of wind farms.

关键词： horizontal axis wind turbine turbulence wind tunnel experiment wind turbine wake

A Nonnegative Garrote-based Method for Multivariate Fault Isolation 36

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Nonnegative Garrote-based Method for Multivariate Fault Is...

第36届中国控制会议

作者： Yi-Min Guo Jian-Guo Wang Bang-Hua Yang shi-wei ma Min-Rui Fei Li-Lan Liu Hui Xu Yuan Yao Yi-Ping Wu School of Mechatronical Engineering and Automation Shanghai UniversityShanghai Key Lab of Power Station Automation Technology Department of Chemical Engineering National Tsing-Hua University Shanghai Baosight Software Co Ltd

ISBN: (纸本)9781538629185

Fault isolation is an essential step in multivariate statistical process monitoring,which discovers the cause of the detected *** common adopted techniques for fault isolation,such as contribution plots,reconstruction analysis,branch and bound,etc.,often suffer from the problems of the smearing effect,insufficient historical fault data,and heavy computational *** this paper,the nonnegative garrote（NNG） estimator is utilized for multivariate statistical fault isolation,which solves the problems of the existing *** proposed method is based on the finding that there is equivalence between fault isolation and variable selection in discriminant *** from the existing methods,the NNG-based fault isolation method does not suggest a single set of faulty ***,it provides a sequence of process variables according to their responsibilities for the detected *** results are informative for diagnosing the root cause of the fault.

关键词： Fault isolation Variable selection Nonnegative garrote Process monitoring

Simultaneous Identification of Parameter and Time-delay Based on Subspace Method and Cross-correlation Function 36

在线全文

cnki会议

学校读者我要写书评

暂无评论

Simultaneous Identification of Parameter and Time-delay Base...

第36届中国控制会议

作者： Jian-Guo Wang Zhi-Fu Deng Bang-Hua Yang shi-wei ma Min-Rui Fei Li-Lan Liu Yuan Yao Tao Chen Yi-Ping Wu School of Mechatronical Engineering and Automation Shanghai UniversityShanghai Key Lab of Power Station Automation Technology Department of Chemical Engineering “Tsing-Hua University” Department of Chemical and Process Engineering University of Surrey Shanghai Baosight Software Co Ltd

ISBN: (纸本)9781538629185

Both the plant parameter4 and delay time of the system may vary in the time-varying system, which makes system identification relatively complex. In this paper, a new system identification algorithm based on subspace method and cross-correlation function is proposed to identify system parameter and time-delay simultaneously. The time delay is identified with the calculation of the cross-correlation function between pre-processed input data that processed through initial plant parameters and original output data. Then, the time delay in the output data can be deleted with the time delay identified before and the parameters can be achieved by subspace identification algorithm. Therefore, the process parameters and time delay identification can be performed online by through above two alternative operations. The validity of the proposed identification algorithm is verified by the simulation study.

关键词： Subspace Method Cross-Correlation Time-Varying Identification