Deep convolutional neural network with 2D spectral energy maps for fault diagnosis of gearboxes under variable speed.

Hasan, Md Junayed; Kim, Jongmyon

Abstract

For industrial safety, correct classification of gearbox fault conditions is necessary. One of the most crucial tasks in data-driven fault diagnosis is determining the best set of features by analyzing the statistical parameters of the signals. However, under variable speed conditions, these statistical parameters are incapable of uncovering the dynamic characteristics of different fault conditions of gearboxes. Later, several deep learning algorithms are used to improve the performance of the feature selection process, but domain knowledge expertise is still necessary. In this paper, a combination domain knowledge analysis and a deep neural network is proposed. By using the input acoustic emission (AE) signal, a two-dimensional spectrum energy map (2D AE-SEM) is created to form an identical fault pattern for various speed conditions of gearboxes. Then, a deep convolutional neural network (DCNN) is proposed to investigate the detailed structure of the 2D input for final fault classification. This 2D AE-SEM offers a graphical depiction of acoustic emission spectral characteristics. Our proposed system offers vigorous and dynamic classification performance through the proposed DCNN with a high diagnostic fault classification accuracy of 96.37% in all considered scenarios.

Citation

HASAN, M.J. and KIM, J. 2020. Deep convolutional neural network with 2D spectral energy maps for fault diagnosis of gearboxes under variable speed. In Djeddi, C., Jamil, A. and Siddiqi, I. (eds.) Pattern recognition and artificial intelligence: proceedings of the 3rd Mediterranean conference on pattern recognition and artificial intelligence (MedPRAI 2019), 22-23 December 2019, Istanbul, Turkey. Communications in computer and information science (CCIS), 1144. Cham: Springer [online], pages 106-117. Available from: https://doi.org/10.1007/978-3-030-37548-5_9

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 3rd Mediterranean conference on pattern recognition and artificial intelligence (MedPRAI 2019)
• Start Date: Dec 22, 2019
• End Date: Dec 23, 2019
• Acceptance Date: Aug 31, 2019
• Online Publication Date: Dec 18, 2019
• Publication Date: Jan 1, 2020
• Deposit Date: Nov 3, 2022
• Publicly Available Date: Nov 10, 2022
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 106-117
• Series Title: Communications in computer and information science (CCIS)
• Series Number: 1144
• Series ISSN: 1865-0929; 1865-0937
• Book Title: Pattern recognition and artificial intelligence: proceedings of Mediterranean conference on pattern recognition and artificial intelligence (MedPRAI 2019), 22-23 December 2019, Istanbul, Turkey
• ISBN: 9783030375478
• DOI: https://doi.org/10.1007/978-3-030-37548-5_9
• Keywords: Gearbox safety; Fault diagnosis; Convolutional neural network
• Public URL: https://rgu-repository.worktribe.com/output/1664728