An Improved Model of Stacked Short Time Fourier Transform and SqueezeNet Using Golden Jackal Algorithm for Rolling Bearing Fault Detection
Main Article Content
Abstract
Rolling bearings are critical components in rotating machinery, and their fault detection is essential for ensuring the machinery's risk-free operation. Fault detection techniques equipped with deep learning (DL) models have been in focus recently. This work presents an efficient rolling bearing fault detection model using the Stacked Short Time Fourier Transform (S-STFT) and an enhanced SqueezeNet model. The enhanced SqueezeNet is the integration of SqueezeNet and the golden jackal algorithm (GJA). Initially, the S-STFT is utilized for converting the vibration signals into time-frequency images. Then, the images are fed to the enhanced SqueezeNet for efficient feature extraction and fault detection. For verifying the efficiency of the suggested fault detection model, two datasets are considered, and achieved accuracies of 99.65% on the CWRU and 99.71% on the test rig dataset, respectively.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Journal author rights
In order for Romanian Journal of Acoustics and Vibration to publish and disseminate research articles, we need publishing rights. This is determined by a publishing agreement between the author and Romanian Journal of Acoustics and Vibration. This agreement deals with the transfer or license of the copyright to Romanian Journal of Acoustics and Vibration and authors retain significant rights to use and share their own published articles. Romanian Journal of Acoustics and Vibration supports the need for authors to share, disseminate and maximize the impact of their research and these rights, in Romanian Journal of Acoustics and Vibration proprietary are defined below:
For subscription articles:
Authors transfer copyright to the publisher as part of a journal publishing agreement, but have the right to: Share their article for personal use (manuscript version); retain patent, trademark and other intellectual property rights (including research data); proper attribution and credit for the published work.
For open access articles:
Authors sign an exclusive license agreement, where authors have copyright but license exclusive rights in their article to the publisher. In this case authors have the right to: share their article in the same ways permitted to third parties under the relevant user license; retain patent, trademark and other intellectual property rights (including research data); proper attribution and credit for the published work.
Rights granted to Romanian Journal of Acoustics and Vibration
For both subscription and open access articles, published in proprietary titles, Romanian Journal of Acoustics and Vibration is granted the following rights:
- The exclusive right to publish and distribute an article, and to grant rights to others, including for commercial purposes;
- For open access articles, Romanian Journal of Acoustics and Vibration will apply the relevant third party user licence (Open access licencses) where Romanian Journal of Acoustics and Vibration publishes the article on its online platforms;
- The right to provide the article in all forms and media so the article can be used on the latest technology even after publication;
- The authority to enforce the rights in the article, on behalf of an author, against third parties, for example in the case of plagiarism or copyright infringement.