Variable-scale demodulation extraction method for early-stage multiple damage fault information of mechanical transmission part
Through technologies such as variational modal decomposition and signal reweighting, the vibration signals of mechanical transmission parts are processed, the fine scale frequency band is automatically selected, and the early multiple damage fault information is extracted, which solves the problems of missed diagnosis and rapid fault degradation in the existing technology, and achieves high-accurate fault diagnosis.
Patent Information
- Application Number
- CN202411803894.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-09
- Publication Date
- 2025-03-28
AI Technical Summary
The prior art is difficult to effectively extract information on multiple damage and faults in early mechanical transmission parts, especially when noise interference and multiple faults interfere with each other, resulting in misdiagnosis and rapid degradation of faults.
The original vibration signal is decomposed by the variational modal decomposition method, the fault information related index CFII is calculated, and the noise reduction reconstruction is achieved through the signal reweighting criterion, the coarse scale frequency band range where the fault information is located is retained, and the fine scale frequency band is automatically selected through the cyclic spectrum coherence spectrum and square enhancement envelope spectrum analysis, and the early multiple damage fault information is extracted.
Effectively overcome the mutual interference between noise and multiple faults, accurately extract information on multiple damage and faults in early mechanical transmission parts, reduce the risk of missed diagnosis, and improve the accuracy and reliability of fault diagnosis.