Gear fault recognition method based on kurtosis ratio coefficient screening of empirical mode decomposition of symplectic geometry

By using the kurtosis ratio coefficient to filter the symplectic geometric mode decomposition method, the rotational frequency signal components containing fault information are selected. Combined with statistical parameters and SVM classifier, the problem of noise and vibration impact signals in existing gear fault diagnosis is solved, and high-precision gear fault identification is achieved.

CN115563480BActive Publication Date: 2026-07-24CHANGZHOU UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHANGZHOU UNIV
Filing Date
2022-09-05
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing gear fault diagnosis methods suffer from significant influences from noise components and vibration/impact signals during signal decomposition, and require manual parameter setting, leading to inaccurate diagnosis.

Method used

A method based on kurtosis ratio coefficient screening of symplectic geometric mode decomposition is adopted. The rotational frequency signal component containing fault information is screened out by the kurtosis ratio coefficient screening method. Combined with time domain, frequency domain, time-frequency domain and entropy value statistical parameters, the optimal feature subset is screened out by particle swarm optimization algorithm, and an SVM classifier is trained for fault identification.

Benefits of technology

It achieves adaptive signal decomposition, eliminating the need for manual parameter setting, thus improving the accuracy and precision of gear fault diagnosis and effectively identifying gear faults.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115563480B_ABST
    Figure CN115563480B_ABST
Patent Text Reader

Abstract

The application provides a gear fault recognition method based on screening of symplectic geometry modal decomposition by kurtosis ratio coefficient, and discloses a recognition method based on screening of symplectic geometry modal decomposition by kurtosis ratio coefficient in a fault diagnosis process.The application as a whole comprises three parts of sampling data preprocessing, decomposition screening of fault signal components and recognition classification.The sampling data preprocessing is composed of wavelet denoising and data division;the decomposition screening of fault signal components comprises two steps of symplectic geometry modal decomposition and screening by kurtosis ratio coefficient; and the recognition classification is composed of feature extraction and SVM model training and testing.The gear fault recognition method based on screening of symplectic geometry modal decomposition by kurtosis ratio coefficient combines symplectic geometry modal decomposition and screening by kurtosis ratio coefficient, aims to provide an effective gear fault recognition method, and thus improves the accuracy of fault diagnosis.
Need to check novelty before this filing date? Find Prior Art