Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network
This paper proposes a novel approach to predicting the useful life of rotating machinery and making fault diagnoses using an optimal blind deconvolution and hybrid invertible neural network. First, a new optimal adaptive maximum second-order cyclostationarity blind deconvolution (OACYCBD) is develop...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/256 |
| _version_ | 1797358113022541824 |
|---|---|
| author | Yangde Gao Zahoor Ahmad Jong-Myon Kim |
| author_facet | Yangde Gao Zahoor Ahmad Jong-Myon Kim |
| author_sort | Yangde Gao |
| collection | DOAJ |
| description | This paper proposes a novel approach to predicting the useful life of rotating machinery and making fault diagnoses using an optimal blind deconvolution and hybrid invertible neural network. First, a new optimal adaptive maximum second-order cyclostationarity blind deconvolution (OACYCBD) is developed for denoising vibration signals obtained from rotating machinery. This technique is obtained from the optimization of traditional adaptive maximum second-order cyclostationarity blind deconvolution (ACYCBD). To optimize the weights of conventional ACYCBD, the proposed method utilizes a probability density function (PDF) of Monte Carlo to assess fault-related incipient changes in the vibration signal. Cross-entropy is used as a convergence criterion for denoising. Because the denoised signal carries information related to the health of the rotating machinery, a novel health index is calculated in the second step using the peak value and square of the arithmetic mean of the signal. The novel health index can change according to the degradation of the health state of the rotating bearing. To predict the remaining useful life of the bearing in the final step, the health index is used as input for a newly developed hybrid invertible neural network (HINN), which combines an invertible neural network and long short-term memory (LSTM) to forecast trends in bearing degradation. The proposed approach outperforms SVM, CNN, and LSTM methods in predicting the remaining useful life of bearings, showcasing RMSE values of 0.799, 0.593, 0.53, and 0.485, respectively, when applied to a real-world industrial bearing dataset. |
| first_indexed | 2024-03-08T14:57:06Z |
| format | Article |
| id | doaj.art-334844fbcec64ae5a3201d2d3927c958 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T14:57:06Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-334844fbcec64ae5a3201d2d3927c9582024-01-10T15:09:16ZengMDPI AGSensors1424-82202024-01-0124125610.3390/s24010256Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural NetworkYangde Gao0Zahoor Ahmad1Jong-Myon Kim2Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaThis paper proposes a novel approach to predicting the useful life of rotating machinery and making fault diagnoses using an optimal blind deconvolution and hybrid invertible neural network. First, a new optimal adaptive maximum second-order cyclostationarity blind deconvolution (OACYCBD) is developed for denoising vibration signals obtained from rotating machinery. This technique is obtained from the optimization of traditional adaptive maximum second-order cyclostationarity blind deconvolution (ACYCBD). To optimize the weights of conventional ACYCBD, the proposed method utilizes a probability density function (PDF) of Monte Carlo to assess fault-related incipient changes in the vibration signal. Cross-entropy is used as a convergence criterion for denoising. Because the denoised signal carries information related to the health of the rotating machinery, a novel health index is calculated in the second step using the peak value and square of the arithmetic mean of the signal. The novel health index can change according to the degradation of the health state of the rotating bearing. To predict the remaining useful life of the bearing in the final step, the health index is used as input for a newly developed hybrid invertible neural network (HINN), which combines an invertible neural network and long short-term memory (LSTM) to forecast trends in bearing degradation. The proposed approach outperforms SVM, CNN, and LSTM methods in predicting the remaining useful life of bearings, showcasing RMSE values of 0.799, 0.593, 0.53, and 0.485, respectively, when applied to a real-world industrial bearing dataset.https://www.mdpi.com/1424-8220/24/1/256fault diagnosisoptimal adaptive maximum second-order cyclostationarity blind deconvolutionhealth indexhybrid invertible neural network |
| spellingShingle | Yangde Gao Zahoor Ahmad Jong-Myon Kim Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network Sensors fault diagnosis optimal adaptive maximum second-order cyclostationarity blind deconvolution health index hybrid invertible neural network |
| title | Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network |
| title_full | Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network |
| title_fullStr | Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network |
| title_full_unstemmed | Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network |
| title_short | Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network |
| title_sort | fault diagnosis of rotating machinery using an optimal blind deconvolution method and hybrid invertible neural network |
| topic | fault diagnosis optimal adaptive maximum second-order cyclostationarity blind deconvolution health index hybrid invertible neural network |
| url | https://www.mdpi.com/1424-8220/24/1/256 |
| work_keys_str_mv | AT yangdegao faultdiagnosisofrotatingmachineryusinganoptimalblinddeconvolutionmethodandhybridinvertibleneuralnetwork AT zahoorahmad faultdiagnosisofrotatingmachineryusinganoptimalblinddeconvolutionmethodandhybridinvertibleneuralnetwork AT jongmyonkim faultdiagnosisofrotatingmachineryusinganoptimalblinddeconvolutionmethodandhybridinvertibleneuralnetwork |