A gear fault diagnosis method based on hierarchical scattered Katz dimension

Abstract

This invention discloses a gear fault diagnosis method based on hierarchical scattering Katz dimension, belonging to the field of gear fault diagnosis. The method includes: first, collecting time-domain vibration signals of the gear under different operating conditions using sensors and normalizing these signals; next, extracting features of the gear under different operating conditions using hierarchical scattering Katz dimension; then, adding classification labels to these feature data and dividing the entire feature data into training samples and test samples; finally, training a classifier using the training samples and using the trained classifier to classify the test samples, thereby achieving effective diagnosis of gear fault types. This invention provides a gear fault diagnosis method based on hierarchical scattering Katz dimension, which realizes the identification of different gear fault modes. Compared with traditional fault diagnosis methods based on fractal dimension, this invention can extract gear fault information more comprehensively and achieve better diagnostic results for gear faults.

Images