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.
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
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.
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.
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.
Smart Images

Figure CN115563480B_ABST