Abstract
In order to improve the reliability of fault diagnosis, total energy growth rate of rolling bearing during run-up is defined and applied to bearing detection. Firstly, an approach of merging short-time Fourier transform (STFT), linear fitting and median filtering is developed to extract the total energy growth rate. Secondly, the relationship between the total energy growth rate and different running conditions is discussed. Thirdly, the total energy growth rate is adopted to diagnose faults as input vector of radial basis function (RBF) neural network. Experiment results show that the total energy growth rate is an effective failure symbol for fault diagnosis of rolling bearing during run-up.
Highlights
Rolling bearings, considered as critical mechanical components, are widely used in industry
Subrahmanyam and Sujatha [8] suggested a neural network based on error back-propagation and adaptive resonance theory 2 (ART2) to diagnose the localized defects in ball bearings under various loads and speed conditions
An effective failure symptom, which is extracted from a time-frequency spectrum obtained by the short-time Fourier transform (STFT), is defined and used to diagnose faults of rolling bearing by radial basis function (RBF) neural networks
Summary
Rolling bearings, considered as critical mechanical components, are widely used in industry. It is significant to detect rolling bearing to improve the reliability and security of mechanical equipment [2]. As an important part in the entire workflow, vibration signals of the run-up process can be used to diagnose fault state [3]. Fault diagnosis during run-up, especially for large rotating machinery which need to run up frequently, such as mine hoist, plays an important role in improving the detection reliability. Subrahmanyam and Sujatha [8] suggested a neural network based on error back-propagation and adaptive resonance theory 2 (ART2) to diagnose the localized defects in ball bearings under various loads and speed conditions. An effective failure symptom, which is extracted from a time-frequency spectrum obtained by the STFT, is defined and used to diagnose faults of rolling bearing by RBF neural networks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
