Frequency Estimation using Spectral Techniques with the Support of a Deep Learning Method
Main Article Content
Abstract
In the case of damage detection, it is important to estimate the frequencies accurately. DFT-based methods provide us with amplitude-frequency pairs, but displayed frequencies carry important errors in the case of short signals. On the other hand, the amplitudes displayed for a sinusoidal signal with different time lengths describe approximately a sinc function. When involving interpolation to find the maxima of the sinc function, to which the real amplitude of the signal corresponds, it is necessary to ensure the existence of at least three points on the main lobe of the sinc function. To this aim, we apply zero-padding to the original signal in such a way that its length is doubled. The frequency estimation method proposed in this paper involves an artificial neural network (ANN). The three amplitudes taken from the main lobe determined for all considered signal lengths are the input values used to train the network. The correction term that allows us to evaluate the frequency will be the target. Following the simulations made, it is found that using normalized data sets we can estimate any frequencies, irrespective of the frequency with which the network was trained. It applies to any signal length, and any signal amplitude.
Downloads
Article Details
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.