Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis
Rotating machinery is one of the major components of industries that suffer from various faults due to the constant workload. Therefore, a fast and reliable fault diagnosis method is essential for machine condition monitoring. In this study, noise eliminated ensemble empirical mode decomposition (NE...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8114 |
| _version_ | 1827674610263392256 |
|---|---|
| author | Atik Faysal Wai Keng Ngui Meng Hee Lim Mohd Salman Leong |
| author_facet | Atik Faysal Wai Keng Ngui Meng Hee Lim Mohd Salman Leong |
| author_sort | Atik Faysal |
| collection | DOAJ |
| description | Rotating machinery is one of the major components of industries that suffer from various faults due to the constant workload. Therefore, a fast and reliable fault diagnosis method is essential for machine condition monitoring. In this study, noise eliminated ensemble empirical mode decomposition (NEEEMD) was used for fault feature extraction. A convolution neural network (CNN) classifier was applied for classification because of its feature learning ability. A generalized CNN architecture was proposed to reduce the model training time. A sample size of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>64</mn><mo>×</mo><mn>64</mn><mo>×</mo><mn>3</mn></mrow></semantics></math></inline-formula> pixels RGB scalograms are used as the classifier input. However, CNN requires a large number of training data to achieve high accuracy and robustness. Deep convolution generative adversarial network (DCGAN) was applied for data augmentation during the training phase. To evaluate the effectiveness of the proposed feature extraction method, scalograms from related feature extraction methods such as ensemble empirical mode decomposition (EEMD), complementary EEMD (CEEMD), and continuous wavelet transform (CWT) are classified. The effectiveness of scalograms is also validated by comparing the classifier performance using grayscale samples from the raw vibration signals. All the outputs from bearing and blade fault classifiers showed that scalogram samples from the proposed NEEEMD method obtained the highest accuracy, sensitivity, and robustness using CNN. DCGAN was applied with the proposed NEEEMD scalograms to further increase the CNN classifier’s performance and identify the optimal number of training data. After training the classifier using augmented samples, the results showed that the classifier obtained even higher validation and test accuracy with greater robustness. The proposed method can be used as a more generalized and robust method for rotating machinery fault diagnosis. |
| first_indexed | 2024-03-10T04:44:42Z |
| format | Article |
| id | doaj.art-ac67e3dcdb62438db1a4d68aedb6cd02 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:44:42Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ac67e3dcdb62438db1a4d68aedb6cd022023-11-23T03:04:13ZengMDPI AGSensors1424-82202021-12-012123811410.3390/s21238114Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault DiagnosisAtik Faysal0Wai Keng Ngui1Meng Hee Lim2Mohd Salman Leong3College of Engineering, Universiti Malaysia Pahang, Pekan Pahang 26600, MalaysiaCollege of Engineering, Universiti Malaysia Pahang, Pekan Pahang 26600, MalaysiaInstitute of Noise and Vibration, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaInstitute of Noise and Vibration, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaRotating machinery is one of the major components of industries that suffer from various faults due to the constant workload. Therefore, a fast and reliable fault diagnosis method is essential for machine condition monitoring. In this study, noise eliminated ensemble empirical mode decomposition (NEEEMD) was used for fault feature extraction. A convolution neural network (CNN) classifier was applied for classification because of its feature learning ability. A generalized CNN architecture was proposed to reduce the model training time. A sample size of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>64</mn><mo>×</mo><mn>64</mn><mo>×</mo><mn>3</mn></mrow></semantics></math></inline-formula> pixels RGB scalograms are used as the classifier input. However, CNN requires a large number of training data to achieve high accuracy and robustness. Deep convolution generative adversarial network (DCGAN) was applied for data augmentation during the training phase. To evaluate the effectiveness of the proposed feature extraction method, scalograms from related feature extraction methods such as ensemble empirical mode decomposition (EEMD), complementary EEMD (CEEMD), and continuous wavelet transform (CWT) are classified. The effectiveness of scalograms is also validated by comparing the classifier performance using grayscale samples from the raw vibration signals. All the outputs from bearing and blade fault classifiers showed that scalogram samples from the proposed NEEEMD method obtained the highest accuracy, sensitivity, and robustness using CNN. DCGAN was applied with the proposed NEEEMD scalograms to further increase the CNN classifier’s performance and identify the optimal number of training data. After training the classifier using augmented samples, the results showed that the classifier obtained even higher validation and test accuracy with greater robustness. The proposed method can be used as a more generalized and robust method for rotating machinery fault diagnosis.https://www.mdpi.com/1424-8220/21/23/8114convolution neural networkempirical mode decompositiondeep convolution generative adversarial networkcontinuous wavelet transform |
| spellingShingle | Atik Faysal Wai Keng Ngui Meng Hee Lim Mohd Salman Leong Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis Sensors convolution neural network empirical mode decomposition deep convolution generative adversarial network continuous wavelet transform |
| title | Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis |
| title_full | Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis |
| title_fullStr | Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis |
| title_full_unstemmed | Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis |
| title_short | Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis |
| title_sort | noise eliminated ensemble empirical mode decomposition scalogram analysis for rotating machinery fault diagnosis |
| topic | convolution neural network empirical mode decomposition deep convolution generative adversarial network continuous wavelet transform |
| url | https://www.mdpi.com/1424-8220/21/23/8114 |
| work_keys_str_mv | AT atikfaysal noiseeliminatedensembleempiricalmodedecompositionscalogramanalysisforrotatingmachineryfaultdiagnosis AT waikengngui noiseeliminatedensembleempiricalmodedecompositionscalogramanalysisforrotatingmachineryfaultdiagnosis AT mengheelim noiseeliminatedensembleempiricalmodedecompositionscalogramanalysisforrotatingmachineryfaultdiagnosis AT mohdsalmanleong noiseeliminatedensembleempiricalmodedecompositionscalogramanalysisforrotatingmachineryfaultdiagnosis |