Guided Wave-Based Damage Detection in Composite Plate With Temperature Variation: A Residual Attention Capsule Network Approach

The structural safety of carbon-fiber composite is usually threatened by occurrence and accumulation of damage during in-service period. For structural health monitoring, guided wave based damage detection methods are widely adopted in industry. However, these methods are significantly affected by variable temperature in-service environment, which would make it hard to extract useful damage information and may further result in false damage diagnosis. To address these issues, in this paper, an efficient Residual Attention Capsules (RAC) network is innovatively developed for guided wave based damage detection in composite plate with temperature variation. Considering the part-whole spatial relationships, the proposed RAC network has deep guided wave feature mining capability without damage index calculation under temperature variation. Synchronous Squeeze-Short Time Fourier transform (S-STFT) method is adopted for wave signal processing, which can effectively convert 1D time-domain signal to 2D time-frequency signal with advantage of time-frequency ambiguity phenomenon suppression. In addition, guided wave propagation characteristic in composite structures is clearly analyzed for wave mode analysis. The performance of proposed RAC damage detection method is evaluated and verified with experimental data in composite plate. The high accuracy results have been obtained and show greater potential than other state-of-the-art contrastive damage detection methods under complex temperature environment.