Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder
In 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 e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8835037/ |
| _version_ | 1819276207220326400 |
|---|---|
| author | Yang Huang Chiun-Hsun Chen Chi-Jui Huang |
| author_facet | Yang Huang Chiun-Hsun Chen Chi-Jui Huang |
| author_sort | Yang Huang |
| collection | DOAJ |
| description | In 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. |
| first_indexed | 2024-12-23T23:36:33Z |
| format | Article |
| id | doaj.art-8e2c49678d3b4f08b9b92154ec0d38ce |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:36:33Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8e2c49678d3b4f08b9b92154ec0d38ce2022-12-21T17:25:51ZengIEEEIEEE Access2169-35362019-01-01713908613909610.1109/ACCESS.2019.29407698835037Motor Fault Detection and Feature Extraction Using RNN-Based Variational AutoencoderYang Huang0https://orcid.org/0000-0002-0921-5978Chiun-Hsun Chen1https://orcid.org/0000-0003-0859-204XChi-Jui Huang2Institute of Information Management, National Chiao Tung University, Hsinchu, TaiwanDepartment of Mechanical Engineering, National Chiao Tung University, Hsinchu, TaiwanDepartment of Mechanical Engineering, National Chiao Tung University, Hsinchu, TaiwanIn 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.https://ieeexplore.ieee.org/document/8835037/Motor fault detectionfeature extractionrecurrent neural networkvariational autoencoder |
| spellingShingle | Yang Huang Chiun-Hsun Chen Chi-Jui Huang Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder IEEE Access Motor fault detection feature extraction recurrent neural network variational autoencoder |
| title | Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder |
| title_full | Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder |
| title_fullStr | Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder |
| title_full_unstemmed | Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder |
| title_short | Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder |
| title_sort | motor fault detection and feature extraction using rnn based variational autoencoder |
| topic | Motor fault detection feature extraction recurrent neural network variational autoencoder |
| url | https://ieeexplore.ieee.org/document/8835037/ |
| work_keys_str_mv | AT yanghuang motorfaultdetectionandfeatureextractionusingrnnbasedvariationalautoencoder AT chiunhsunchen motorfaultdetectionandfeatureextractionusingrnnbasedvariationalautoencoder AT chijuihuang motorfaultdetectionandfeatureextractionusingrnnbasedvariationalautoencoder |