Toward deep generation of guided wave representations for composite materials

Laminated composite materials are widely used in most fields of engineering. Wave propagation analysis plays an essential role in understanding the short-duration transient response of composite structures. The forward physics-based models are utilized to map from elastic properties space to wave propagation behavior in a laminated composite material. Due to the high-frequency, multimodal, and dispersive nature of the guided waves, the physics-based simulations are computationally demanding. It makes property prediction, generation, and material design problems more challenging. In this work, a forward physics-based simulator, such as the stiffness matrix method is utilized to collect group velocities of guided waves for a set of composite materials. A variational autoencoder (VAE)-based deep generative model is proposed for the generation of new and realistic polar group velocity representations. It is observed that the deep generator is able to reconstruct unseen representations with very low mean square reconstruction error. Global Monte Carlo and directional equally spaced samplers are used to sample the continuous, complete, and organized low-dimensional latent space of VAE. The sampled point is fed into the trained decoder to generate new polar representations. The network has shown exceptional generation capabilities. It is also seen that the latent space forms a conceptual space where different directions and regions show inherent patterns related to the generated representations and their corresponding material properties. Impact Statement-AI-Accelerated property prediction, discovery, and design of materials have emerged as a new research front with many promising features. There are many investigations on different materials, but no emphasis is placed on composite materials. Among many challenges, the unavailability of datasets for composite materials is a significant roadblock. This is because conducting multiple experiments is costly and cumbersome, and performing simulations is time-Taking and demands computational resources. In order to accelerate and scale the prediction, discovery, and design, a deep generation approach is proposed for composite materials. The current research requires limited physical simulations to train a deep generator network.The generator can generate enormous data, eliminating the demerits of both experiments and simulations. The work is novel in terms of the deep generation approach as well as the applications for composite materials. © 2022 IEEE.