Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method

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.

Abnormal Detection and Fault Diagnosis of Adjustment Hydraulic Servomotor Based on Genetic Algorithm to Optimize Support Vector Data Description with Negative Samples and One-Dimensional Convolutional Neural Network

“…Finally, based on the principle of warning-then-diagnosis, when the anomaly detection model gives a fault prediction, the classification model realizes the diagnosis of existing faults. In recent years, with the improvement in computing power, deep learning, and especially Convolutional Neural Networks (CNNs), has become a research focus in the field of fault diagnosis [32]. CNNs can automatically extract features, and the feature extraction process is directly oriented to fault classification.…”