Data-driven simulation-assisted-Physics learned AI (DPAI) for heat diffusion in large grain polycrystalline materials

Abstract

In this paper, we propose Data-driven simulation-assisted Physics-learned Artificial Intelligence (DPAI), a deep-learning algorithm to simulate heat diffusion in large-grain polycrystalline materials. The DPAI model captures the spatio-temporal representation of heat diffusion in the material from input sequences from the training dataset. The training dataset consists of various temperature plots of polycrystalline materials taken from Finite Element (FE) simulations having varying numbers of grains oriented in random directions with a single-point heat source at the center. The arbitrary plane of the 3D microstructure of these materials is represented using 2D Voronoi tessellations. Voronoi configurations are used to model the geometry of the 2D Computer-Aided Design (CAD) model. Each cell of the Voronoi tessellation represents one grain of the microstructure. This CAD model is used as an input to the FE for solving heat diffusion equations. To model the near-realistic material anisotropy and accurately measure temperature differences at cell boundaries, a smaller mesh size is required in FE modeling, which takes considerable solver time. Therefore, the proposed Deep learning model significantly reduces the computational time while maintaining accuracy as compared to conventional numerical techniques. After training, the effectiveness of the trained DPAI model is examined by modeling larger domain problems involving a greater number of grains and varying material properties. The simulation result is qualitatively compared with the experiment. A scaled-up version of the microstructure is represented using Unidirectional Carbon Fiber laminate. The laminate is heated with a point heat source and the temperature plots are captured using Infrared Camera.