Abstract

Condition monitoring of planetary gearboxes in time-varying speed service is an important and actual engineering requirement, however, also an intractable task. The traditional sideband energy ratio (SER) method limits its application to complex operational conditions due to the frequency spectrum based and manual bandwidth selection. To this end, this paper proposes an adaptive order-band energy ratio (AOER) method, an enhanced version of the SER, to quantitatively and intelligently diagnose gear faults under different operational conditions. First, a signal model based on angular increment and order components is proposed to properly describe the vibrations for both stationary and non-stationary conditions. The proposed model provides the theoretical source and reliance for the order spectrum analysis and the diagnostic mechanism of the OER. Second, the OER is theoretically proved to be a reliable fault indicator by analyzing the proposed signal model. The offset of the uncertainty terms highlighting the fault symptoms demonstrates the potential success of using OER for the fault diagnosis. Finally, OERs generated from the vibration data and three typical machine learning algorithms are used to adaptively obtain the optimal bandwidth and thus the AOER. The AOER can be directly used for the remaining vibration data of the corresponding operational condition. Comparing with SER and the convolutional neural network, the experimental results demonstrate the effectiveness and outperformance of AOER for both stationary and non-stationary operational conditions. More importantly, since AOER can cope with diagnostic tasks for different operational conditions, it enables an improved ability to monitor a PG’s health in the actual complex environment.

Full Text
Published version (Free)

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 call