Abstract
In this paper we consider the problem of local damage detection in rotating machines. Usually vibration signal is used for the analysis. Unfortunately classical methods are often not effective enough to properly detect cyclic components in real-life signal, especially for heavy-duty machinery used in mining industry. Therefore it is proposed to design analytical algorithms focused on the evaluation of the periodicity features of the signal. In this article we apply the cointegration approach to vibration signal. Although the method itself has been already proposed in the previous work, the main goal of this article is evaluation of the detection effectiveness with respect to changing Signal-to-Noise Ratio (SNR) of the input data. In the paper authors present the complete procedure for the effectiveness evaluation, which is based on the Monte Carlo simulations. The success rate of the method is assessed based on analyzing the cointegration with respect to SNR value of input signal. It allows to discover confidence level for such methodology considering internal quality of the data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.