Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals
As failures of rolling bearings lead to major failures in rotating machines, recent vibration-based rolling bearing fault diagnosis techniques are focused on obtaining useful fault features from the huge collection of raw data. However, too many features reduce the classification accuracy and increa...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/24/4/511 |
| _version_ | 1827628932905566208 |
|---|---|
| author | Hosameldin O. A. Ahmed Asoke K. Nandi |
| author_facet | Hosameldin O. A. Ahmed Asoke K. Nandi |
| author_sort | Hosameldin O. A. Ahmed |
| collection | DOAJ |
| description | As failures of rolling bearings lead to major failures in rotating machines, recent vibration-based rolling bearing fault diagnosis techniques are focused on obtaining useful fault features from the huge collection of raw data. However, too many features reduce the classification accuracy and increase the computation time. This paper proposes an effective feature selection technique based on intrinsic dimension estimation of compressively sampled vibration signals. First, compressive sampling (CS) is used to get compressed measurements from the collected raw vibration signals. Then, a global dimension estimator, the geodesic minimal spanning tree (GMST), is employed to compute the minimal number of features needed to represent efficiently the compressively sampled signals. Finally, a feature selection process, combining the stochastic proximity embedding (SPE) and the neighbourhood component analysis (NCA), is used to select fewer features for bearing fault diagnosis. With regression analysis-based predictive modelling technique and the multinomial logistic regression (MLR) classifier, the selected features are assessed in two case studies of rolling bearings vibration signals under different working loads. The experimental results demonstrate that the proposed method can successfully select fewer features, with which the MLR-based trained model achieves high classification accuracy and significantly reduced computation times compared to published research. |
| first_indexed | 2024-03-09T13:42:38Z |
| format | Article |
| id | doaj.art-c3ad24f491b34e50a55ebde5cebc3123 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T13:42:38Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-c3ad24f491b34e50a55ebde5cebc31232023-11-30T21:05:28ZengMDPI AGEntropy1099-43002022-04-0124451110.3390/e24040511Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration SignalsHosameldin O. A. Ahmed0Asoke K. Nandi1Department of Mechanical and Aerospace Engineering, Brunel University London, London UB8 3PH, UKDepartment of Electronic and Electrical Engineering, Brunel University London, London UB8 3PH, UKAs failures of rolling bearings lead to major failures in rotating machines, recent vibration-based rolling bearing fault diagnosis techniques are focused on obtaining useful fault features from the huge collection of raw data. However, too many features reduce the classification accuracy and increase the computation time. This paper proposes an effective feature selection technique based on intrinsic dimension estimation of compressively sampled vibration signals. First, compressive sampling (CS) is used to get compressed measurements from the collected raw vibration signals. Then, a global dimension estimator, the geodesic minimal spanning tree (GMST), is employed to compute the minimal number of features needed to represent efficiently the compressively sampled signals. Finally, a feature selection process, combining the stochastic proximity embedding (SPE) and the neighbourhood component analysis (NCA), is used to select fewer features for bearing fault diagnosis. With regression analysis-based predictive modelling technique and the multinomial logistic regression (MLR) classifier, the selected features are assessed in two case studies of rolling bearings vibration signals under different working loads. The experimental results demonstrate that the proposed method can successfully select fewer features, with which the MLR-based trained model achieves high classification accuracy and significantly reduced computation times compared to published research.https://www.mdpi.com/1099-4300/24/4/511vibration-based condition monitoringrolling bearing fault diagnosiscompressive sampling (CS)feature selectionmultinomial logistic regression (MLR) |
| spellingShingle | Hosameldin O. A. Ahmed Asoke K. Nandi Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals Entropy vibration-based condition monitoring rolling bearing fault diagnosis compressive sampling (CS) feature selection multinomial logistic regression (MLR) |
| title | Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals |
| title_full | Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals |
| title_fullStr | Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals |
| title_full_unstemmed | Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals |
| title_short | Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals |
| title_sort | intrinsic dimension estimation based feature selection and multinomial logistic regression for classification of bearing faults using compressively sampled vibration signals |
| topic | vibration-based condition monitoring rolling bearing fault diagnosis compressive sampling (CS) feature selection multinomial logistic regression (MLR) |
| url | https://www.mdpi.com/1099-4300/24/4/511 |
| work_keys_str_mv | AT hosameldinoaahmed intrinsicdimensionestimationbasedfeatureselectionandmultinomiallogisticregressionforclassificationofbearingfaultsusingcompressivelysampledvibrationsignals AT asokeknandi intrinsicdimensionestimationbasedfeatureselectionandmultinomiallogisticregressionforclassificationofbearingfaultsusingcompressivelysampledvibrationsignals |