CNN-DST : ensemble deep learning based on Dempster–Shafer theory for vibration-based fault recognition
- Author
- Vahid Yaghoubi Nasrabadi (UGent) , Liangliang Cheng (UGent) , Wim Van Paepegem (UGent) and Mathias Kersemans (UGent)
- Organization
- Abstract
- Nowadays, using vibration data in conjunction with pattern recognition methods is one of the most common fault detection strategies for structures. However, their performances depend on the features extracted from vibration data, the features selected to train the classifier, and the classifier used for pattern recognition. Deep learning facilitates the fault detection procedure by automating the feature extraction and selection, and classification procedure. Though, deep learning approaches have challenges in designing its structure and tuning its hyperparameters, which may result in a low generalization capability. Therefore, this study proposes an ensemble deep learning framework based on a convolutional neural network (CNN) and Dempster–Shafer theory (DST), called CNN-DST. In this framework, several CNNs with the proposed structure are first trained, and then, the outputs of the CNNs selected by the proposed technique are combined by using an improved DST-based method. To validate the proposed CNN-DST framework, it is applied to an experimental dataset created by the broadband vibrational responses of polycrystalline nickel alloy first-stage turbine blades with different types and severities of damage. Through statistical analysis, it is shown that the proposed CNN-DST framework classifies the turbine blades with an average prediction accuracy of 97.19%. The proposed CNN-DST framework is benchmarked with other state-of-the-art classification methods, demonstrating its high performance. The robustness of the proposed CNN-DST framework with respect to measurement noise is investigated, showing its high noise-resistance. Further, bandwidth analysis reveals that most of the required information for detecting faulty samples is available in a small frequency range.
- Keywords
- Mechanical Engineering, Biophysics, Ensemble deep learning, convolutional neural network, Dempster-Shafer theory of evidence, classifier selection, fault recognition, CLASSIFIER FUSION, FEATURE-SELECTION, NEURAL-NETWORK, DAMAGE IDENTIFICATION, MULTIPLE CLASSIFIERS, COMBINATION, EVIDENCES
Downloads
-
manuscript Rev1.docx
- full text (Accepted manuscript)
- |
- open access
- |
- ZIP archive
- |
- 5.29 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8749420
- MLA
- Yaghoubi Nasrabadi, Vahid, et al. “CNN-DST : Ensemble Deep Learning Based on Dempster–Shafer Theory for Vibration-Based Fault Recognition.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, vol. 21, no. 5, 2022, pp. 2063–82, doi:10.1177/14759217211050012.
- APA
- Yaghoubi Nasrabadi, V., Cheng, L., Van Paepegem, W., & Kersemans, M. (2022). CNN-DST : ensemble deep learning based on Dempster–Shafer theory for vibration-based fault recognition. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 21(5), 2063–2082. https://doi.org/10.1177/14759217211050012
- Chicago author-date
- Yaghoubi Nasrabadi, Vahid, Liangliang Cheng, Wim Van Paepegem, and Mathias Kersemans. 2022. “CNN-DST : Ensemble Deep Learning Based on Dempster–Shafer Theory for Vibration-Based Fault Recognition.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 21 (5): 2063–82. https://doi.org/10.1177/14759217211050012.
- Chicago author-date (all authors)
- Yaghoubi Nasrabadi, Vahid, Liangliang Cheng, Wim Van Paepegem, and Mathias Kersemans. 2022. “CNN-DST : Ensemble Deep Learning Based on Dempster–Shafer Theory for Vibration-Based Fault Recognition.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 21 (5): 2063–2082. doi:10.1177/14759217211050012.
- Vancouver
- 1.Yaghoubi Nasrabadi V, Cheng L, Van Paepegem W, Kersemans M. CNN-DST : ensemble deep learning based on Dempster–Shafer theory for vibration-based fault recognition. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL. 2022;21(5):2063–82.
- IEEE
- [1]V. Yaghoubi Nasrabadi, L. Cheng, W. Van Paepegem, and M. Kersemans, “CNN-DST : ensemble deep learning based on Dempster–Shafer theory for vibration-based fault recognition,” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, vol. 21, no. 5, pp. 2063–2082, 2022.
@article{8749420, abstract = {{Nowadays, using vibration data in conjunction with pattern recognition methods is one of the most common fault detection strategies for structures. However, their performances depend on the features extracted from vibration data, the features selected to train the classifier, and the classifier used for pattern recognition. Deep learning facilitates the fault detection procedure by automating the feature extraction and selection, and classification procedure. Though, deep learning approaches have challenges in designing its structure and tuning its hyperparameters, which may result in a low generalization capability. Therefore, this study proposes an ensemble deep learning framework based on a convolutional neural network (CNN) and Dempster–Shafer theory (DST), called CNN-DST. In this framework, several CNNs with the proposed structure are first trained, and then, the outputs of the CNNs selected by the proposed technique are combined by using an improved DST-based method. To validate the proposed CNN-DST framework, it is applied to an experimental dataset created by the broadband vibrational responses of polycrystalline nickel alloy first-stage turbine blades with different types and severities of damage. Through statistical analysis, it is shown that the proposed CNN-DST framework classifies the turbine blades with an average prediction accuracy of 97.19%. The proposed CNN-DST framework is benchmarked with other state-of-the-art classification methods, demonstrating its high performance. The robustness of the proposed CNN-DST framework with respect to measurement noise is investigated, showing its high noise-resistance. Further, bandwidth analysis reveals that most of the required information for detecting faulty samples is available in a small frequency range.}}, author = {{Yaghoubi Nasrabadi, Vahid and Cheng, Liangliang and Van Paepegem, Wim and Kersemans, Mathias}}, issn = {{1475-9217}}, journal = {{STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL}}, keywords = {{Mechanical Engineering,Biophysics,Ensemble deep learning,convolutional neural network,Dempster-Shafer theory of evidence,classifier selection,fault recognition,CLASSIFIER FUSION,FEATURE-SELECTION,NEURAL-NETWORK,DAMAGE IDENTIFICATION,MULTIPLE CLASSIFIERS,COMBINATION,EVIDENCES}}, language = {{eng}}, number = {{5}}, pages = {{2063--2082}}, title = {{CNN-DST : ensemble deep learning based on Dempster–Shafer theory for vibration-based fault recognition}}, url = {{http://doi.org/10.1177/14759217211050012}}, volume = {{21}}, year = {{2022}}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: