Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network
Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/11/1248 |
| _version_ | 1797532969888382976 |
|---|---|
| author | Rafia Nishat Toma Cheol-Hong Kim Jong-Myon Kim |
| author_facet | Rafia Nishat Toma Cheol-Hong Kim Jong-Myon Kim |
| author_sort | Rafia Nishat Toma |
| collection | DOAJ |
| description | Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings. |
| first_indexed | 2024-03-10T11:06:57Z |
| format | Article |
| id | doaj.art-fed98971d5604d7eaefb249f974bae15 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T11:06:57Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-fed98971d5604d7eaefb249f974bae152023-11-21T21:05:49ZengMDPI AGElectronics2079-92922021-05-011011124810.3390/electronics10111248Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural NetworkRafia Nishat Toma0Cheol-Hong Kim1Jong-Myon Kim2Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, KoreaSchool of Computer Science and Engineering, Soongsil University, Seoul 06978, KoreaDepartment of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, KoreaCondition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.https://www.mdpi.com/2079-9292/10/11/1248bearing fault diagnosisvibration signalEEMDenvelope analysisCWTtime-frequency representation |
| spellingShingle | Rafia Nishat Toma Cheol-Hong Kim Jong-Myon Kim Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network Electronics bearing fault diagnosis vibration signal EEMD envelope analysis CWT time-frequency representation |
| title | Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network |
| title_full | Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network |
| title_fullStr | Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network |
| title_full_unstemmed | Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network |
| title_short | Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network |
| title_sort | bearing fault classification using ensemble empirical mode decomposition and convolutional neural network |
| topic | bearing fault diagnosis vibration signal EEMD envelope analysis CWT time-frequency representation |
| url | https://www.mdpi.com/2079-9292/10/11/1248 |
| work_keys_str_mv | AT rafianishattoma bearingfaultclassificationusingensembleempiricalmodedecompositionandconvolutionalneuralnetwork AT cheolhongkim bearingfaultclassificationusingensembleempiricalmodedecompositionandconvolutionalneuralnetwork AT jongmyonkim bearingfaultclassificationusingensembleempiricalmodedecompositionandconvolutionalneuralnetwork |