Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers
Engine fault diagnosis is a critical task in automotive aftermarket management. Developing appropriate fault-labeled datasets can be challenging due to nonlinearity variations and divergence in feature distribution among different engine kinds or operating scenarios. To solve this task, this study e...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/22/7316 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846152420169613312 |
|---|---|
| author | Bernardo Luis Tuleski Cristina Keiko Yamaguchi Stefano Frizzo Stefenon Leandro dos Santos Coelho Viviana Cocco Mariani |
| author_facet | Bernardo Luis Tuleski Cristina Keiko Yamaguchi Stefano Frizzo Stefenon Leandro dos Santos Coelho Viviana Cocco Mariani |
| author_sort | Bernardo Luis Tuleski |
| collection | DOAJ |
| description | Engine fault diagnosis is a critical task in automotive aftermarket management. Developing appropriate fault-labeled datasets can be challenging due to nonlinearity variations and divergence in feature distribution among different engine kinds or operating scenarios. To solve this task, this study experimentally measures audio emission signals from compression ignition engines in different vehicles, simulating injector failures, intake hose failures, and absence of failures. Based on these faults, a hybrid approach is applied to classify different conditions that help the planning and decision-making of the automobile industry. The proposed hybrid approach combines the wavelet packet transform (WPT), Markov blanket feature selection, random convolutional kernel transform (ROCKET), tree-structured Parzen estimator (TPE) for hyperparameters tuning, and ten machine learning (ML) classifiers, such as ridge regression, quadratic discriminant analysis (QDA), naive Bayes, <i>k</i>-nearest neighbors (<i>k</i>-NN), support vector machine (SVM), multilayer perceptron (MLP), random forest (RF), extra trees (ET), gradient boosting machine (GBM), and LightGBM. The audio data are broken down into sub-time series with various frequencies and resolutions using the WPT. These data are subsequently utilized as input for obtaining an informative feature subset using a Markov blanket-based selection method. This feature subset is then fed into the ROCKET method, which is paired with ML classifiers, and tuned using Optuna using the TPE approach. The generalization performance applying the proposed hybrid approach outperforms other standard ML classifiers. |
| format | Article |
| id | doaj-art-718000a6b04a45d08b9ab44b89544ece |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-718000a6b04a45d08b9ab44b89544ece2024-11-26T18:21:31ZengMDPI AGSensors1424-82202024-11-012422731610.3390/s24227316Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning ClassifiersBernardo Luis Tuleski0Cristina Keiko Yamaguchi1Stefano Frizzo Stefenon2Leandro dos Santos Coelho3Viviana Cocco Mariani4Department of Mechanical Engineering, Pontifical Catholic University of Parana, Curitiba 80242-980, PR, BrazilPostgraduate Program in Productive Systems in Association with UNIPLAC, UNC, UNESC, and UNIVILLE, Lages 88509-900, SC, BrazilPostgraduate Program in Productive Systems in Association with UNIPLAC, UNC, UNESC, and UNIVILLE, Lages 88509-900, SC, BrazilGraduate Program in Electrical Engineering, Federal University of Parana, Curitiba 80242-980, PR, BrazilDepartment of Electrical Engineering, Federal University of Parana, Curitiba 80242-980, PR, BrazilEngine fault diagnosis is a critical task in automotive aftermarket management. Developing appropriate fault-labeled datasets can be challenging due to nonlinearity variations and divergence in feature distribution among different engine kinds or operating scenarios. To solve this task, this study experimentally measures audio emission signals from compression ignition engines in different vehicles, simulating injector failures, intake hose failures, and absence of failures. Based on these faults, a hybrid approach is applied to classify different conditions that help the planning and decision-making of the automobile industry. The proposed hybrid approach combines the wavelet packet transform (WPT), Markov blanket feature selection, random convolutional kernel transform (ROCKET), tree-structured Parzen estimator (TPE) for hyperparameters tuning, and ten machine learning (ML) classifiers, such as ridge regression, quadratic discriminant analysis (QDA), naive Bayes, <i>k</i>-nearest neighbors (<i>k</i>-NN), support vector machine (SVM), multilayer perceptron (MLP), random forest (RF), extra trees (ET), gradient boosting machine (GBM), and LightGBM. The audio data are broken down into sub-time series with various frequencies and resolutions using the WPT. These data are subsequently utilized as input for obtaining an informative feature subset using a Markov blanket-based selection method. This feature subset is then fed into the ROCKET method, which is paired with ML classifiers, and tuned using Optuna using the TPE approach. The generalization performance applying the proposed hybrid approach outperforms other standard ML classifiers.https://www.mdpi.com/1424-8220/24/22/7316machine learning classifiersMarkov blanketrandom convolutional kernel transform (ROCKET)time-series classificationwavelet packet transform |
| spellingShingle | Bernardo Luis Tuleski Cristina Keiko Yamaguchi Stefano Frizzo Stefenon Leandro dos Santos Coelho Viviana Cocco Mariani Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers Sensors machine learning classifiers Markov blanket random convolutional kernel transform (ROCKET) time-series classification wavelet packet transform |
| title | Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers |
| title_full | Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers |
| title_fullStr | Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers |
| title_full_unstemmed | Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers |
| title_short | Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers |
| title_sort | audio based engine fault diagnosis with wavelet markov blanket rocket and optimized machine learning classifiers |
| topic | machine learning classifiers Markov blanket random convolutional kernel transform (ROCKET) time-series classification wavelet packet transform |
| url | https://www.mdpi.com/1424-8220/24/22/7316 |
| work_keys_str_mv | AT bernardoluistuleski audiobasedenginefaultdiagnosiswithwaveletmarkovblanketrocketandoptimizedmachinelearningclassifiers AT cristinakeikoyamaguchi audiobasedenginefaultdiagnosiswithwaveletmarkovblanketrocketandoptimizedmachinelearningclassifiers AT stefanofrizzostefenon audiobasedenginefaultdiagnosiswithwaveletmarkovblanketrocketandoptimizedmachinelearningclassifiers AT leandrodossantoscoelho audiobasedenginefaultdiagnosiswithwaveletmarkovblanketrocketandoptimizedmachinelearningclassifiers AT vivianacoccomariani audiobasedenginefaultdiagnosiswithwaveletmarkovblanketrocketandoptimizedmachinelearningclassifiers |