Abstract
The main objective of this paper is to detect and classify the faults in a single-stage bevel gearbox. In this paper, energy operator (EO) is combined with the spectrum and cepstrum analysis is used for detection of faults and for classification purpose, J48 algorithm is used. Usually, the vibration signal is contaminated with noises which suppress the fault frequencies in spectrum analysis. So, a filter-free, simple, and efficient EO method is used to reduce noise and interferences of vibration signal coming from the gearbox test rig. All the experiments are carried out by varying the speed and load under three health conditions of gearbox such as healthy, chipped, and missing tooth. The vibration signal is preprocessed by EO, which is further analyzed by spectrum and cepstrum analysis in MATLAB to detect the location of faults. J48 decision tree algorithm is used to select the dominant feature among 12 statistical features which are extracted from the processed signal and based on these chosen features; the overall classification accuracy is approx. 89% with a precision of 0.917. The obtained results show that the presented method can detect and classify the faults of gearbox efficiently.
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.