检索结果-内蒙古大学图书馆

Fault diagnosis method for wind turbine rolling bearings based on Hankel tensor decomposition

IET RENEWABLE POWER GENERATION 2019年第2期13卷 220-226页

作者： Zhao, Hongshan Zhang, Wei Wang, Guilan North China Elect Power Univ Dept Elect & Elect Engn Baoding Peoples R China Cable Co State Grid Shanghai Elect Power Co Shanghai Peoples R China

In order to diagnose the wind turbine rolling bearing faults with vibration signals effectively, a fault diagnosis method based on Hankel tensor decomposition is proposed. Firstly, IMF-SVD (intrinsic mode function, IMF;singular value decomposition, SVD) is used to estimate the number of sources in sensor observation signals. Secondary, a third-order Hankel tensor is formed by the observation matrix, and a set of low-rank tensor subterms are obtained by tensor rank-$\lpar L_r{\rm \comma \;}L_r{\rm \comma \;1\rpar }$(Lr,Lr,1) decomposition. The fault features of each source are contained in the first and second modes of the corresponding subterm. Then, the source signals are reconstructed by the subterms. Finally, the envelope spectra of the reconstructed source signals are analysed, and the fault characteristic frequencies are extracted. The results of simulation and practical case analysis show that this method can realise the fault diagnosis of wind turbine rolling bearings correctly and effectively.

关键词： tensors mechanical engineering computing fault diagnosis singular value decomposition wind turbines vibrations rolling bearings signal reconstruction vibration signals fault diagnosis method Hankel tensor decomposition intrinsic mode function singular value decomposition sensor observation signals low-rank tensor subterms reconstructed source signals fault characteristic frequencies wind turbine rolling bearings tensor rank envelope spectra

来源：评论

学校读者我要写书评

暂无评论

Unsupervised fault diagnosis method based on iterative multi-manifold spectral clusteringInspec keywordsOther keywords

IET COLLABORATIVE INTELLIGENT MANUFACTURING

引用

IET COLLABORATIVE INTELLIGENT MANUFACTURING 2019年第2期1卷 48-55页

作者： Song, Wenbin Wen, Long Gao, Liang Li, Xinyu Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

Fault diagnosis is very important to the modern manufacturing system. As a powerful data-driven method, machine learning (ML) has been widely used for fault diagnosis. However, a certain amount of labelled data is essential to most of the ML methods, which is not always available. In this study, an unsupervised fault diagnosis method based on iterative multi-manifold spectral clustering (IMMSC) is proposed. The IMMSC, that the affinity matrix is constructed based on local tangent space, can improve the performance of spectral clustering on multi-manifold distributed data. The IMMSC is conducted after feature extraction to divide data into different clusters first. Then local outlier factor is utilised to identify the normal condition. A fault index is found to recognise the fault conditions. The proposed IMMSC is tested on five simulation datasets and the proposed method is validated on the motor bearing dataset provided by Case Western Reserve University. The mean accuracy of IMMSC on simulation data is 97.85%, which outperforms the other spectral clustering and traditional methods. Furthermore, the result of the IMMSC is stable over 30 individual tests. The mean accuracy of the proposed method on motor bearing dataset is 98.53%. The result demonstrates its potential in fault diagnosis field.

关键词： machine bearings mechanical engineering computing fault diagnosis pattern clustering feature extraction iterative methods matrix algebra unsupervised fault diagnosis method IMMSC modern manufacturing system labelled data ML methods iterative multimanifold spectral clustering multimanifold distributed data fault index fault conditions motor bearing dataset simulation data fault diagnosis field data-driven method machine learning affinity matrix local tangent space feature extraction local outlier factor

来源：评论

学校读者我要写书评

暂无评论

Novel physical network algorithm for indirect measurement of polished rod load of beam-pumping unit

引用

JOURNAL OF engineering-JOE 2019年第10期2019卷 7287-7292页

作者： Wang, Ke Gong, Guoliang Shen, Rongxuan Wang, An Yao, Zhaolin Mao, Wenyu Lu, Huaxiang Chinese Acad Sci Lab Artificial Networks Inst Semicond Beijing Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Shanghai Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Beijing Key Lab Semicond Neural Network Intellige Beijing Peoples R China

A novel neural network algorithm for indirect measurement of the polished rod load of the beam-pumping unit is proposed. The dynamometer card is a two-dimension graph of polished rod load versus horse head position, and it is widely used for working state monitoring of pumping unit. The drift problem of load sensor makes the direct measurement of polished rod load not economical and practical, so indirect measurement of polished rod load is crucial. Through the analysis of the mechanical characteristics of the pumping unit, a neural network with physical meaning (physical network) is designed. The experiment shows that the physical network can simulate the energy transfer process properly with only 18 training data items, which is about 1% of other data-driven models, and maintains good performance under different down-hole conditions.

关键词： two-dimension graph energy transfer process novel physical network algorithm indirect polished rod load measurement dynamometers Neural computing techniques working state monitoring novel neural network algorithm Combinatorial mathematics Power engineering computing down-hole conditions Drives Measurement beam-pumping unit spatial variables measurement economical measurement drift problem load sensor neural nets mechanical engineering computing electric drives mechanical engineering applications of IT physical meaning mechanical variables measurement mechanical drives and transmissions dynamometer card graph theory Civil and mechanical engineering computing horse head position data-driven models rods (structures) Spatial variables measurement

来源：评论

学校读者我要写书评

暂无评论

Study on transient contact performance of meshing transmission of cycloid gear and needle wheel in RV reducer

引用

JOURNAL OF engineering-JOE 2020年第14期2020卷 1001-1004页

作者： Xuetao, Qiao Libin, Zhang Chunshan, Chen Cunfu, Yan Changlu, Wang Weigong, Wang Zhongyuan Univ Technol Sch Sch Mech Engn Zhengzhou Peoples R China Zhejiang Shuanghuan Driveline Co Ltd Huaian Peoples R China Jiangsu Zhenggong Res Inst Adv Equipment Co Ltd Taixing Peoples R China

The model of rotor vector (RV) reducer was established by 3D software, and was imported into ANSYS Workbench for transient dynamic analysis. The stress distribution diagram and total deformation diagram of the gear tooth surface during the meshing process of the cycloidal wheel and the pin wheel were obtained, and the stress distribution law of the cycloidal wheel in the process was also obtained. Comparing the calculation results of Hertz formula with the results of finite-element analysis showed that the deviation are smaller and within the allowable range, which provides the theoretical reference for the optimisation of the cycloidal wheel.

关键词： mechanical engineering computing deformation wheels rotors finite element analysis gears mechanical contact stress analysis transient contact performance meshing transmission cycloid gear needle wheel RV reducer rotor vector reducer ANSYS Workbench transient dynamic analysis stress distribution diagram total deformation diagram gear tooth surface meshing process cycloidal wheel pin wheel stress distribution law finite-element analysis

来源：评论

学校读者我要写书评

暂无评论

Novel study on the pressure pulsation of the axial piston machines with even number of pistons

引用

JOURNAL OF engineering-JOE 2020年第14期2020卷 932-935页

作者： Zhou, Junjie Jing, Chongbo Bao, Qianqian Wu, Wei Beijing Inst Technol Natl Key Lab Vehicular Transmiss Beijing 10081 Peoples R China

Flow and pressure ripples of axial piston machines have received sustained attentions by researcher in flow power domain. Traditionally, almost all the axial piston pumps have been designed with odd number of pistons. This study presents a novel study focusing on the actual flow and pressure pulsations of even number piston pump. A fluid dynamic model based on lumped parameter approach is presented to predict the flow and pressure performance of axial piston pumps. Particularly, the cylinder and valve plate are re-designed to fit the ten-piston pump based on a commercial pump. Both the simulation and test results show that the pressure pulsation rate of ten-piston pump is actually few percent bigger than that of nine-piston pump. The relative difference is much smaller than what has been expected by the theoretical flow calculation. Therefore, the design of axial piston machines with even number of pistons may be feasible in some circumstances.

关键词： pumps pistons mechanical engineering computing valves plates (structures) axial piston machines pressure ripples flow power domain axial piston pumps pressure pulsations pressure performance ten-piston pump commercial pump pressure pulsation rate nine-piston pump

来源：评论

学校读者我要写书评

暂无评论

Analysis and suppression of torsional vibration in electromechanical coupling transmission system of high-speed train

引用

JOURNAL OF engineering-JOE 2020年第14期2020卷 980-984页

作者： Zhao Jing-Bo Yang Chao-Yue Pu Chao-Yi Changzhou Inst Technol Sch Automot Engn Changzhou Jiangsu Peoples R China Jiangsu Univ Technol Sch Automobile & Traff Engn Changzhou Jiangsu Peoples R China

The high-speed train transmission system is a complex electromechanical coupling system. In this study, the torsional vibration of a train transmission system was studied. The centralised mass model of the mechanical structure of the coupling system was established. The natural vibration characteristics of the mechanical mechanism system were analysed. The results show that the natural vibration frequency of the universal shaft was 4.08 Hz, the natural vibration frequency of the pinion was 7.24 Hz, the natural vibration frequency of the big gear was 35.6 Hz, and the natural vibration frequency of the wheelset was 107.48 Hz. The traction motor model was built, and by considering the electromechanical coupling of the system, a torsional vibration suppression strategy for harmonic components in the motor is proposed. The effectiveness of the suppression strategy was verified by MATLAB/Simulink model simulation.

关键词： vibration control shafts gears traction motors mechanical engineering computing railway engineering natural vibration frequency torsional vibration suppression strategy electromechanical coupling transmission system high-speed train transmission system natural vibration characteristics electromechanical coupling system traction motor model MATLAB Simulink model simulation frequency 4 08 Hz frequency 7 24 Hz frequency 35 6 Hz frequency 107 48 Hz

来源：评论

学校读者我要写书评

暂无评论

Hotspots Integrating of Expert and Beginner Experiences of Machine Operations through Egocentric Vision 16

Hotspots Integrating of Expert and Beginner Experiences of M...

引用

16th IAPR International Conference on Machine Vision Applications (MVA)

作者： Chen, Longfei Nakamura, Yuichi Kondo, Kazuaki Damen, Dima Mayol-Cuevas, Walterio W. Kyoto Univ Acad Ctr Comp & Media Studies Kyoto Japan Univ Bristol Dept Comp Sci Bristol Avon England

ISBN: (纸本)9784901122184

Beginners can often provide useful information regarding machine operations, e.g., how difficult a specific operation is or how beginners deal with difficulties. However, their experiences oftentimes widely vary, and it is difficult to summarize these diverse experiences in an extensive way. To try and solve this problem, this study focused on developing a framework for integrating beginners' and experts' experiences into a unified operation model. A baseline model was first obtained based on hand{machine interactions automatically extracted from experts' egocentric vision records. Then, the beginners' behaviors were integrated by dynamically aligning them to the baseline model. Through this process, an integrated model based on the experiences of a wide range of users was achieved. We applied our method to the operation experiences of two tabletop devices, an IH heater and a sewing machine. The results show good potentials in modeling the common and different behaviors among experts and beginners.

关键词： computer vision human computer interaction mechanical engineering computing sewing machines sewing machine mechanical engineering computing Professional personnel computer human interaction images computer vision Surgery operational mode Sight

来源：评论

学校读者我要写书评

暂无评论

Time-frequery image processing based jet engine modulation extraction method towards target recognition

Time-frequery image processing based jet engine modulation e...

引用

IET International Radar Conference (IET IRC 2020)

作者： Z.-Y. Lei Z.-P. Huang W.-Y. Wang G. Wu L. Zhang Nanjing Research Institute of Electronics Technology Nanjing 210039 China

Jet Engine Modulation (JEM) characteristics are widely used in airborne radar to detect and classify helicopter, propeller-driven aircraft and jet aircraft. Airborne clutter and low signal-to-noise ratio (SNR), however, veils the JEM phenomena. Factors such as Observation Angle, Blade Pitch, Intermodulation of Rotors and Radar Cross Section (RCS) scintillation, can affect the JEM characteristics of radar echoes significantly. Thus a robust and optimized JEM extraction method is in sore need. In this paper, we propose a fusion detection method, using super resolution to obtain JEM time-frequency images. By means of pre-processing, time-frequency analyzing and fusion detecting, JEM characteristics areextracted from complex background. Further measurements and data analysis verify its effectiveness. We anticipate that this method will form the basis for the development of JEM engineering and indicate possible lines for airborne radar's target classificationin future.

关键词： time-frequency analysis jet engines helicopters feature extraction object detection radar cross-sections radar clutter radar target recognition propellers airborne radar blades image classification radar detection radar imaging image fusion image resolution data analysis mechanical engineering computing

来源：评论

学校读者我要写书评

暂无评论

Research on thermal analysis theory and simulation technology of civil aircraft hydraulic energy system

Research on thermal analysis theory and simulation technolog...

引用

CSAA/IET International Conference on Aircraft Utility Systems (AUS 2020)

作者： C. Guo G. Xiong X. Wang L. Quan Yanshan University School of Mechanical Engineering Qinhuangdao Hebei China

This paper is based on the theory analysis of the thermal characteristics of the key components of the hydraulic energy system of civil aircraft, the key components and system-level thermal analysis simulation models are established through AMESim software. Taking the thermal analysis of a certain aircraft 2# hydraulic energy system under normal working conditions during hot weather and low altitude hovering as an example, the effectiveness of the simulation technology and model is verified. The simulation technology can be used for the demonstration and optimization of the hydraulic energy system of civil aircraft at the beginning of design, which is of great significance to the improvement of civil aircraft design efficiency.

关键词： aircraft power systems thermal analysis aircraft mechanical engineering computing hydraulic systems design engineering computer simulation formal verification computational fluid dynamics hydraulic fluids

来源：评论

学校读者我要写书评

暂无评论

Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding 30

Road Crack Detection Using Deep Convolutional Neural Network...

引用

30th IEEE Intelligent Vehicles Symposium (IV)

作者： Fan, Rui Bocus, Mohammud Junaid Zhu, Yilong Jiao, Jianhao Wang, Li Ma, Fulong Cheng, Shanshan Liu, Ming Kong Univ Sci & Technol Robot Inst Robot & Multipercept Lab Hong Kong Peoples R China Univ Bristol Visual Informat Inst Bristol Avon England Unity Dr Technol Inc Shenzhen Peoples R China Natl Engn Res Ctr Rd Maintenance Technol Beijing Peoples R China

ISBN: (纸本)9781728105604

Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. In this paper, a novel road crack detection algorithm which is based on deep learning and adaptive image segmentation is proposed. Firstly, a deep convolutional neural network is trained to determine whether an image contains cracks or not. The images containing cracks are then smoothed using bilateral filtering, which greatly minimizes the number of noisy pixels. Finally, cracks are extracted from the road surface using an adaptive thresholding method. The experimental results illustrate that our network can classify images with an accuracy of 99.92%, and the cracks can be successfully extracted from the images using our proposed thresholding algorithm.

关键词： convolutional neural nets crack detection image classification image denoising image filtering image segmentation learning (artificial intelligence) mechanical engineering computing road safety smoothing methods crack detection mechanical engineering computing image segmentation smoothing methods image filtering Road safety cracks adaptive thresholding image denoising Image classification images bilateral filtering

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：