完整後設資料紀錄
DC 欄位語言
dc.contributor.authorHuang, Yangen_US
dc.contributor.authorChen, Chiun-Hsunen_US
dc.contributor.authorHuang, Chi-Juien_US
dc.date.accessioned2020-10-05T02:01:52Z-
dc.date.available2020-10-05T02:01:52Z-
dc.date.issued2019-01-01en_US
dc.identifier.issn2169-3536en_US
dc.identifier.urihttp://dx.doi.org/10.1109/ACCESS.2019.2940769en_US
dc.identifier.urihttp://hdl.handle.net/11536/155302-
dc.description.abstractIn most of the fault detection methods, the time domain signals collected from the mechanical equipment usually need to be transformed into frequency domain or other high-level data, highly relying on professional knowledge such as signal processing and fault pattern recognition. Contrary to those existing approaches, we proposed a two-stage machine learning analysis architecture which can accurately predict the motor fault modes only by using motor vibration time-domain signals without any complicated preprocessing. In the first stage, the method RNN-based VAE was proposed which is highly suitable for dimension reduction of time series data. In addition to reducing the dimension of sequential data from 150*3 to 25 dimensions, our method furthermore improves the prediction accuracy evaluated by several classification algorithms. While other dimension reduction methods such as Autoencoder and Variational Autoencoder cannot improve the classification accuracy effectively or even decreased. It indicates that the sequential data after dimension reduction via the RNN-based VAE still can maintain the high-dimensional data information. Furthermore, the experimental results demonstrate that it can be well applied to time series data dimension reduction and shows a significant improvement of the prediction performance, even with a simple double-layer Neural Network can reach over 99% of accuracy. In the second stage, Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) are used to further perform the second dimension reduction, such that the different or unknown fault modes can be clearly visualized and detected.en_US
dc.language.isoen_USen_US
dc.subjectFeature extractionen_US
dc.subjectFault detectionen_US
dc.subjectDimensionality reductionen_US
dc.subjectVibrationsen_US
dc.subjectData modelsen_US
dc.subjectFault diagnosisen_US
dc.subjectTime-domain analysisen_US
dc.subjectMotor fault detectionen_US
dc.subjectfeature extractionen_US
dc.subjectrecurrent neural networken_US
dc.subjectvariational autoencoderen_US
dc.titleMotor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoderen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/ACCESS.2019.2940769en_US
dc.identifier.journalIEEE ACCESSen_US
dc.citation.volume7en_US
dc.citation.spage139086en_US
dc.citation.epage139096en_US
dc.contributor.department機械工程學系zh_TW
dc.contributor.department資訊管理與財務金融系 註:原資管所+財金所zh_TW
dc.contributor.departmentDepartment of Mechanical Engineeringen_US
dc.contributor.departmentDepartment of Information Management and Financeen_US
dc.identifier.wosnumberWOS:000560318900001en_US
dc.citation.woscount0en_US
顯示於類別:期刊論文