Miettinen, J., Nikula, R.-P., Keski-Rahkonen, J., Fagerholm, F., Tiainen, T., Sierla, S., & Viitala, R. (2022). Whitening cnn-based rotor system fault diagnosis model features. Applied Sciences, 12(9), 4411. https://doi.org/10.3390/app12094411
Whitening CNN-based rotor system fault diagnosis model features
|Author:||Miettinen, Jesse1; Nikula, Riku-Pekka2; Keski-Rahkonen, Joni3;|
1Department of Mechanical Engineering, Aalto University, 02150 Espoo, Finland
2Control Engineering, Environmental and Chemical Engineering, University of Oulu, 90014 Oulu, Finland
3Kongsberg Maritime Finland Oy, 26101 Rauma, Finland
4Department of Electrical Engineering and Automation, Aalto University, 02150 Espoo, Finland
|Online Access:||PDF Full Text (PDF, 2.6 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2022111665844
Multidisciplinary Digital Publishing Institute,
|Publish Date:|| 2022-11-16
Intelligent fault diagnosis (IFD) models have the potential to increase the level of automation and the diagnosis accuracy of machine condition monitoring systems. Many of the latest IFD models rely on convolutional layers for feature extraction from vibration data. The majority of these models employ batch normalisation (BN) for centring and scaling the input for each neuron. This study includes a novel examination of a competitive approach for layer input normalisation in the scope of fault diagnosis. Network deconvolution (ND) is a technique that further decorrelates the layer inputs reducing redundancy among the learned features. Both normalisation techniques are implemented on three common 1D-CNN-based fault diagnosis models. The models with ND mostly outperform the baseline models with BN in three experiments concerning fault datasets from two different rotor systems. Furthermore, the models with ND significantly outperform the baseline models with BN in the common CWRU bearing fault tests with load domain shifts, if the data from drive-end and fan-end sensors are employed. The results show that whitened features can improve the performance of CNN-based fault diagnosis models.
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
213 Electronic, automation and communications engineering, electronics
214 Mechanical engineering
This research was funded by Business Finland as part of the Reboot IoT project (grant number 4356/31/2019) and by the Academy of Finland as part of the AI-ROT research project (grant number 335717).
Data sharing concerning the thruster dataset is not applicable to this article due to legal issues. Publicly available datasets were analyzed in this study. This data, concerning the bearing fault dataset, can be found here: https://engineering.case.edu/bearingdatacenter.
© 2022 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).