Barely visible impact damage detection in composite structures using deep learning networks with varying complexities

Visual inspection is one of the most common non-destructive testing (NDT) methods that offers a fast evaluation of surface damage in aerospace composite structures. However, it is highly dependent on human-related factors and may not detect barely visible impact damage (BVID). In this research, low velocity impact tests with different energy levels are conducted on two groups of composite panels, namely 'reference' and 'sensor-integrated' samples. Then, the results of impact tests, together with C-scan and visual inspection images, are analysed to define the BVID range and create an original image dataset. Next, four different deep learning models are trained, validated and tested to capture the BVID only from the images of the impacted and non-impacted surfaces. The results show that all four networks can learn and detect BVID quite well, and the sensor-integrated samples reduce the training time and improve the accuracy of deep learning models. ResNet outperforms other networks with the highest accuracy of 96.2% and 98.36% on the back-face of reference and sensor-integrated samples, respectively. The proposed damage recognition method can act as a fast, inexpensive and accurate structural health monitoring tool for composite structures in real-life applications.

Automated summary

Visual inspection is commonly used for evaluating surface damage in aerospace composite structures, but it has limitations in detecting barely visible impact damage. This research conducted low velocity impact tests on composite panels to define the range of barely visible impact damage (BVID). Deep learning models were trained and tested to detect BVID from impact images, with the sensor-integrated samples improving the accuracy and training time. The proposed damage recognition method can serve as an efficient and accurate structural health monitoring tool for composite structures.