Ultrasonic signal classification for composite materials via deep convolutional neural networks

Ultrasonic testing (UT) is the most commonly used non-destructive testing method in the aerospace field. However, for the detection of delamination defect in multi-layer composite adhesive materials with metal and non-metal bonding, traditional energy statistics methods are limited and cannot achieve high-precision automatic signal classification. This article proposes a signal classification model based on hybrid neural networks. By studying the classification accuracy of convolutional neural networks (CNN) and long short-term memory networks (LSTM) for different types of signals, a relatively balanced classification is achieved, which effectively improves the classification accuracy. By integrating attention mechanisms, the ability of the detection model to identify key features is further enhanced. Experimental results demonstrate that the proposed model achieves an accuracy of 98.57%. Bayesian Optimisation (BO) can effectively and automatically select the optimal hyperparameters, and achieve global optimisation. In the experiment, the accuracy increased by 0.73% compared to the benchmark value. Comparative experiments show that the signal classification model established in this paper has good performance.