Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method
Open Access
Abstract
This paper proposes an improved fault diagnosis algorithm that combines a modified fast kurtogram (FK) method with the lightweight convolutional neural network GhostNet. The FK algorithm can adaptively select resonance demodulation bands for envelope demodulation to extract fault features, but it may be disturbed by non-Gaussian noise. Hence, the fast average kurtogram (FAK) method based on sub-band averaging was introduced. This method effectively weakens the impact of pulse noise on the kurtosis graph by splitting the signal into equal-length sub-signals and calculating the average kurtosis value of all sub-signal filters. Simultaneously, to fully utilize the advantages of deep learning technology in feature extraction and classification, this study used the FAK to convert vibration signals from one-dimensional to two-dimensional kurtosis graphs as the input for the GhostNet model. This combination not only achieved accurate fault diagnosis and classification but also showed significant advantages in processing efficiency and resource utilization. The experimental results indicate that the algorithm excelled in extracting features and diagnosing periodic transient impact faults, and compared with traditional methods, it exhibited noticeable improvements in computational efficiency and resource management.Keywords
Funding Information
- National Natural Science Foundation of China (52275067, 51875498, F2020203058, E2023203030)
- Province Natural Science Foundation of Hebei, China (52275067, 51875498, F2020203058, E2023203030)
This publication has 28 references indexed in Scilit:
- Detecting of transient vibration signatures using an improved fast spatial–spectral ensemble kurtosis kurtogram and its applications to mechanical signature analysis of short duration data from rotating machineryMechanical Systems and Signal Processing, 2013
- A new procedure for using envelope analysis for rolling element bearing diagnostics in variable operating conditionsMechanical Systems and Signal Processing, 2013
- Application of an improved kurtogram method for fault diagnosis of rolling element bearingsMechanical Systems and Signal Processing, 2011
- Rolling element bearing diagnostics—A tutorialMechanical Systems and Signal Processing, 2011
- A neural network approach for remaining useful life prediction utilizing both failure and suspension historiesMechanical Systems and Signal Processing, 2010
- Rolling element bearing fault diagnosis based on the combination of genetic algorithms and fast kurtogramMechanical Systems and Signal Processing, 2009
- Fast computation of the kurtogram for the detection of transient faultsMechanical Systems and Signal Processing, 2007
- The spectral kurtosis: a useful tool for characterising non-stationary signalsMechanical Systems and Signal Processing, 2006
- THE RELATIONSHIP BETWEEN SPECTRAL CORRELATION AND ENVELOPE ANALYSIS IN THE DIAGNOSTICS OF BEARING FAULTS AND OTHER CYCLOSTATIONARY MACHINE SIGNALSMechanical Systems and Signal Processing, 2001
- Use of the kurtosis statistic in the frequency domain as an aid in detecting random signalsIEEE Journal of Oceanic Engineering, 1984