检索结果-南通市图书馆

Motor Fault Diagnosis Based on short-time Fourier Transform and Convolutional Neural Network

Chinese Journal of Mechanical Engineering 2017年第6期30卷 1357-1368页

作者： Li-Hua Wang Xiao-Ping Zhao Jia-Xin Wu Yang-Yang Xie Yong-Hong Zhang School of Information and Control Nanjing University ofInformation Science and Technology Nanjing 210044 China School of Computer and Software Nanjing University ofInformation Science and Technology Nanjing 210044 China Network Monitoring Center of Jiangsu Province NanjingUniversity of Information Science and TechnologyNanjing 210044 China

With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform （STFT） to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adap- tively extracted by using a convolutional neural network （CNN）. The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by tra- ditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.

关键词： Big data Deep learning short-time fouriertransform Convolutional neural network Motor

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Evaluating ultrasound signals of carbon steel fatigue testing using signal analysis approaches

引用

Journal of Central South University 2014年第1期21卷 232-241页

作者： M.M.Padzi S.Abdullah M.Z.Nuawi S.M.Beden Z.M.Nopiah Department of Mechanical and Materials Engineering Universiti Kebangsaan Malaysia

The application of ultrasound techniques to monitor the condition of structures is becoming more prominent because these techniques can detect the early symptoms of defects such as cracks and other *** early detection of defects is of vital importance to avoid major failures with catastrophic *** assessment of an ultrasound technique was used to investigate fatigue damage *** tests were performed according to the ASTM E466-96 standard with the attachment of an ultrasound sensor to the test *** 1045 carbon steel was used due to its wide application in the automotive industry.A fatigue test was performed under constant loading stress at a sampling frequency of 8 *** sets of data acquisition systems were used to collect the fatigue strain signals and ultrasound *** of the signals were edited and analysed using a signal processing *** methods were used to evaluate the signals,the integrated Kurtosis-based algorithm for z-filter technique(I-kaz) and the short-time Fourier transform(STFT).The fatigue damage behaviour was observed from the initial stage until the last stage of the fatigue *** results of the I-kaz coefficient and the STFT spectrum were used to explain and describe the behaviour of the fatigue damage.I-kaz coefficients were ranged from 60 to 61 for strain signals and ranged from 5 to 76 for ultrasound signals.I-kaz values tend to be high at failure point due to high amplitude of respective *** spectrogram displays the colour intensity which represents the damage severity of the strain signals.I-kaz technique is found very useful and capable in assessing both stationary and non-stationary signals while STFT technique is suitable only for non-stationary signals by displaying its spectrogram.

关键词： fatigue ultrasound signal analysis integrated Kurtosis-based algorithm for z-filter technique short-time fouriertransform

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

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：