Deep learning based fault classification algorithm for roller bearings using time-frequency localized features

Bera, A and Dutta, A and Dhara, AK (2021) Deep learning based fault classification algorithm for roller bearings using time-frequency localized features. In: 2021 IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2021, 19-20 Feb 2021, Greater Noida, pp. 419-424.

PDF icccis_2021.pdf - Published Version Restricted to Registered users only Download (824kB) | Request a copy

Abstract

The paper proposes an algorithm to classify different conditions of a bearing based on vibration data using a deep convolutional neural network. Spectrograms of vibration data are generated by means of Short-time Fourier Transform and then provided as input to a convolutional neural network. The network is successful in predicting the health condition of the bearing from the spectrograms and achieves a classification accuracy of 97. The trained model is then tested on a different dataset and the model is able to predict the classes with an accuracy of 96. The proposed model is finally compared with pre-existing models to evaluate its performance and the results demonstrate the state of the art performance of our proposed algorithm. © 2021 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings - IEEE 2021 International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2021
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Convolution; Convolutional neural networks; Deep neural networks; Intelligent systems; Roller bearings; Spectrographs, Classification accuracy; Fault classification; Health condition; Localized features; Short time Fourier transforms; State-of-the-art performance; Time frequency; Vibration data, Deep learning
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	10 Aug 2021 11:48
Last Modified:	10 Aug 2021 11:48
URI:	http://eprints.iisc.ac.in/id/eprint/69119

Actions (login required)

View Item