Multi-fault Diagnosis of Rotating Machine Under Uncertain Speed Conditions.

Autor: Mishra, R. K., Choudhary, Anurag, Fatima, S., Mohanty, A. R., Panigrahi, B. K.
Předmět:
Zdroj: Journal of Vibration Engineering & Technologies; Mar2024, Vol. 12 Issue 3, p4637-4654, 18p
Abstrakt: Background: Multi-faults in rotating machines are critical and create an unfavourable working environment. Research on multi-faults is still in the early stages, and models are trained at constant speeds, which are not efficient under different types of uncertain speed conditions. Methodology: This paper proposes developing a multi-fault diagnosis system that can work irrespective of speed conditions. Vibration signatures were acquired from the different experimental multi-fault conditions under an uncertain operating environment. STFNet (Segmented Time-frequency Network) was applied to extract fault information and to create an intelligent multi-fault classification model. Results and validation: Rigorous testing of the proposed STFNet model was done under various uncertain speed conditions like constant, continuously accelerated, continuously decelerated and fluctuating speed, and a maximum accuracy of 97.87 % was achieved. The performance of the proposed model was compared with the existing algorithms and was validated on another bearing multi-fault dataset. Conclusion: As per the industrial requirement, the proposed approach will be very helpful for diagnosing multi-faults under various uncertain speed conditions. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index
Externí odkaz: