Wind turbine blade crack acoustic emission detection method and device and storage medium

By pre-processing the acoustic emission signals of the fan blades and processing the Gammatone filter group, cepspectral features and other features are extracted, combined with SVM intelligent identification, the problem of insufficient crack detection sensitivity of fan blades in complex noise environments is solved, and more accurate and reliable crack detection is achieved.

CN119643709APending Publication Date: 2025-03-18JIANGSU FRONTIER ELECTRIC TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202411794789.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-09
Publication Date
2025-03-18

AI Technical Summary

Technical Problem

In the prior art In the complex background noise environment, the sensitivity of fan blade crack detection is limited, making it difficult to accurately capture the acoustic emission signal characteristics related to cracks.

Method used

By obtaining the acoustic emission signals in the fan blade area, performing de-DC and pre-emphasis processing, the signal is input to the Gammatone filter group, the cepspectral characteristics are extracted, and the logarithmic energy spectrum and Gammatone cepspectral coefficient are calculated. Combining short-time energy, short-time zero-crossing rate and short-time entropy, a vector feature spectrum is synthesized, and finally using a support vector machine (SVM) for intelligent identification to distinguish between normal signals and crack-containing signals.

Benefits of technology

This method can more accurately capture the acoustic emission signal characteristics related to cracks, improve the accuracy and reliability of crack detection, and maintain efficient detection performance especially in complex noise environments.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a fan blade crack acoustic emission detection method and device and a storage medium, and belongs to the technical field of wind power generation, and the method comprises the steps: obtaining an acoustic emission signal of a fan blade area, and converting the acoustic emission signal into a digital signal; carrying out direct current removal and pre-emphasis processing on the digital signal to obtain a processed acoustic emission signal; inputting the processed acoustic emission signal into a Gammatone filter bank, and obtaining an acoustic emission signal after cepstrum feature extraction; calculating the logarithmic energy spectrum of the acoustic emission signal after the cepstrum characteristics are extracted, and calculating a Gammatone cepstrum coefficient according to the logarithmic energy spectrum; synthesizing the Gammatone cepstrum coefficient with the short-time energy, the short-time zero-crossing rate and the short-time entropy which are obtained through pre-calculation into a vector characteristic spectrum; detecting by using the synthesized vector characteristic spectrum so as to distinguish a normal signal from a signal containing cracks; according to the invention, the acoustic emission signal characteristics related to the crack can be more accurately captured, and the accuracy and reliability of crack detection are improved.
Need to check novelty before this filing date? Find Prior Art