Composite material damage detection method based on wavelet analysis and BP neural network

Abstract

The invention discloses a composite material damage detection method based on wavelet analysis and a BP neural network, comprising the steps as follows: preprocessing a damage signal based on wavelet packet analysis in a wavelet analysis algorithm; reconstructing a wavelet packet decomposition coefficient according to a wavelet packet analysis algorithm; using a wavelet packet to decompose the damage signal into five layers to obtain 32 frequency components; reconstructing the wavelet packet decomposition coefficient; obtaining the energy spectrum diagram of the wavelet packet based on the fact that each node coefficient represents the energy of a corresponding order; selecting the energy value of an order, which has the maximum energy value (namely, which is the most sensitive) in the energy spectrum diagram of the wavelet packet, as a damage feature vector; and extracting feature vectors of different damage levels to constitute a learning sample of the BP neural network. The composite material damage detection method is fast in convergence, and simple and effective. The BP neural network after learning and training has the ability to identify the mode of damage to a composite material, can accurately identify the damage to a composite material and the degree of damage, and can locate the damage.

Description

technical field [0001] The invention designs a composite material damage detection method based on wavelet analysis and BP neural network, and belongs to the technical field of damage signal identification and processing in structural health monitoring. Background technique [0002] Composite materials have the advantages of light weight, high strength, and corrosion resistance, and have been widely used in military, aerospace, transportation, electronics, and other fields. Since composite materials are easily damaged by external damage, it is very important to detect damage to composite materials. At present, there are few researches on efficient identification and processing methods for composite damage signals. [0003] In the prior art, the detection of composite materials generally adopts the acoustic emission method, and the detection of sound waves generally uses Lamb waves. Since Lamb waves are more sensitive to damage and easier to analyze, short-time Fourier transf...

AI Technical Summary

Problems solved by technology

Conventional Fourier analysis theory has limitations in time-frequency joint analysis. It can only simply convert time-domain signals into frequency-domain signals, but cannot obtain the time when specific frequency band data appears, which has serious drawbacks in data processing; HHT When the transformation decomposes complex signals, it has the disadvantages of low accuracy of solution results and long calculation time. At the same time, there are problems of edge effects, cross-border problems, stopping criteria and filtering of false low-frequency components.

The short-time Fourier transform has a better effect on the set frequency when extracting the envelope, and the signal processing effect on other frequencies is poor.

Wavelet transform can divide data into n segments for processing, but simple wavelet transform is not intelligent enough, and requires professionals to identify signals, which is inconvenient to detect

Images