Search Results for kurtogram

Abstract

Diagnosing faults in rotary machines is critical, as early fault detection is a precise and essential task in minimizing operational risks and economic losses. Bearings are vital components in rotary machines and are subject to gradual degradation due to continuous operation. Failure to detect early damage can lead to problem escalation, resulting in severe damage and increased costs. In this study, two types of signals from rotary machines are analyzed: acoustic emission (AE) signals and vibration signals. These signals are utilized as input features for a deep learning neural network based on images, where the features are extracted using the Kurtogram, a powerful fourth-order spectral analysis tool that generalizes spectral kurtosis (SK) for a given signal. The results demonstrate that the accuracy of diagnosing the machine’s operational condition whether healthy or faulty ranges from 99.2% to 100%, while the accuracy of fault classification reaches 96.6%. These findings highlight the high efficiency of this methodology in fault detection and classification, establishing it as one of the most important techniques for diagnosing faults in rotary machines.