Deep learning fan fault diagnosis method based on double-wavelet fusion and CEEMDAN decomposition

Through the deep learning method of dual wavelet fusion and CEEMDAN decomposition, independent modeling is performed for the key measurement points of the fan, which solves the non-stationary and noise interference problems of the fan fault signal and achieves high-precision fault diagnosis.

CN120705759APending Publication Date: 2025-09-26ZHEJIANG UNIV OF TECH
0 Cites 2 Cited by

Patent Information

Application Number
CN202510719120.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-30
Publication Date
2025-09-26

AI Technical Summary

Technical Problem

When a wind turbine operates in an underground space, the fault signal exhibits non-stationarity and nonlinearity. Traditional methods are difficult to effectively extract fault features, and deep learning methods are limited in their feature learning capabilities under noise interference. CEEMDAN is sensitive to noise, and single wavelet packet decomposition has the problem of insufficient matching.

Method used

The method of dual wavelet fusion and CEEMDAN decomposition is adopted. By improving the wavelet packet denoising algorithm and CEEMDAN decomposition, combined with time-frequency domain feature extraction, independent modeling is performed on the key measurement points of the wind turbine. 1D-CNN and LSTM are used to extract time domain features, and CNN is used to extract frequency domain features to achieve fault diagnosis.

Benefits of technology

It significantly improves the signal reconstruction quality and fault identification accuracy, avoids interference between measurement points, and enhances the sensitivity and accuracy of fault diagnosis. It is suitable for fan fault identification under complex working conditions.

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

Abstract

A deep learning fan fault diagnosis method based on double wavelet fusion and CEEMDAN decomposition comprises the following steps: S1, collecting vibration signals of a fan motor driving end, a fan driving end and a non-driving end, and constructing a data set; s2, performing improvement on the basis of wavelet packet noise reduction to form a double-wavelet fusion noise reduction algorithm; s3, carrying out noise reduction processing on the acquired signals; s4, carrying out sample division on the noise reduction signals according to a fixed time window, and carrying out classification according to measurement points; s5, randomly dividing the samples into a training set, a verification set and a test set; s6, decomposing all the samples by using CEEMDAN, and extracting IMFs; s7, sending the sample into the time-frequency domain joint feature extraction model of the corresponding measuring point for modeling; s8, training to obtain a diagnosis model and exporting a weight file; and S9, loading the model detection test set, and comprehensively judging the operation state of the fan. According to the invention, the signal processing quality and the fault identification accuracy are improved.
Need to check novelty before this filing date? Find Prior Art