Diagnosis of interior damage with a convolutional neural network using simulation and measurement data

Current deep learning applications in structural health monitoring (SHM) are mostly related to surface damage such as cracks and rust. Methods using traditional image processing techniques (such as filtering and edge detection) usually face difficulties in diagnosing internal damage in thicker specimens of heterogeneous materials. In this paper, we propose a damage diagnosis framework using a deep convolutional neural network (CNN) and transfer learning, focusing on internal damage such as voids and cracks. We use thermography to study the heat transfer characteristics and infer the presence of damage in the structure. It is challenging to obtain sufficient data samples for training deep neural networks, especially in the field of SHM. Therefore we use finite element (FE) computer simulations to generate a large volume of training data for the deep neural network, considering multiple damage shapes and locations. These computer-simulated data are used along with pre-trained convolutional cores of a sophisticated computer vision-based deep convolutional network to facilitate effective transfer learning. The CNN automatically generates features for damage diagnosis as opposed to manual feature generation in traditional image processing. Systematic parameter selection study is carried out to investigate accuracy versus computational expense in generating the training data. The methodology is demonstrated with an example of damage diagnosis in concrete, a heterogeneous material, using both computer simulations and laboratory experiments. The combination of FE simulation, transfer learning and experimental data is found to achieve high accuracy in damage localization with affordable effort.