A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network
In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/7/1102 |
| _version_ | 1817981253144543232 |
|---|---|
| author | Youngji Yoo Jun-Geol Baek |
| author_facet | Youngji Yoo Jun-Geol Baek |
| author_sort | Youngji Yoo |
| collection | DOAJ |
| description | In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time–frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time–frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time–frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset. |
| first_indexed | 2024-04-13T23:03:27Z |
| format | Article |
| id | doaj.art-e9b5aa6683f64e8298033f68213beaa5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-13T23:03:27Z |
| publishDate | 2018-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e9b5aa6683f64e8298033f68213beaa52022-12-22T02:25:45ZengMDPI AGApplied Sciences2076-34172018-07-0187110210.3390/app8071102app8071102A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural NetworkYoungji Yoo0Jun-Geol Baek1Department of Industrial Management Engineering, Korea University, Seoul 02841, KoreaDepartment of Industrial Management Engineering, Korea University, Seoul 02841, KoreaIn data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time–frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time–frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time–frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.http://www.mdpi.com/2076-3417/8/7/1102continuous wavelet transformconvolutional neural networkbearingsremaining useful lifetimeprognostics and health managementhealth indicator |
| spellingShingle | Youngji Yoo Jun-Geol Baek A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network Applied Sciences continuous wavelet transform convolutional neural network bearings remaining useful lifetime prognostics and health management health indicator |
| title | A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network |
| title_full | A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network |
| title_fullStr | A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network |
| title_full_unstemmed | A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network |
| title_short | A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network |
| title_sort | novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network |
| topic | continuous wavelet transform convolutional neural network bearings remaining useful lifetime prognostics and health management health indicator |
| url | http://www.mdpi.com/2076-3417/8/7/1102 |
| work_keys_str_mv | AT youngjiyoo anovelimagefeaturefortheremainingusefullifetimepredictionofbearingsbasedoncontinuouswavelettransformandconvolutionalneuralnetwork AT jungeolbaek anovelimagefeaturefortheremainingusefullifetimepredictionofbearingsbasedoncontinuouswavelettransformandconvolutionalneuralnetwork AT youngjiyoo novelimagefeaturefortheremainingusefullifetimepredictionofbearingsbasedoncontinuouswavelettransformandconvolutionalneuralnetwork AT jungeolbaek novelimagefeaturefortheremainingusefullifetimepredictionofbearingsbasedoncontinuouswavelettransformandconvolutionalneuralnetwork |