An Isothermal Surface Imaging and Transfer Learning Framework for Fast Isothermal Surface Prediction and 3D Temperature Field Reconstruction in Metal Additive Manufacturing

Metal additive manufacturing (AM) technology has promising applications across many fields due to its near-net-shape advantages. The quality of the as-built component is closely linked to the temperature evolution during the metal AM process, which exhibits strong nonlinearities, localized high gradients, and rapid cooling rates. Therefore, real-time prediction of the temperature field is essential for effective online process control to achieve high fabrication quality, which poses surprising challenges for numerical methods, as traditional methods suffer from the inherent time-consuming nature of fine time-space discretizations. In this study, we proposed an isothermal surface imaging and transfer learning framework for fast prediction of isothermal surfaces, which are further used to reconstruct the high-dimensional, nonlinear temperature field. It consists of three key parts: physics-guided isothermal surface imaging to reduce the problem dimensionality by transforming the unstructured temperature field into a series of structured grayscale images, a pre-trained hybrid parameter-to-image generative neural network for the isothermal surface prediction in favor of small training samples, and a transfer learning strategy leveraging physical similarity of these isothermal surfaces in the metal AM process to obtain the 3D temperature field. The training samples are generated using a high-fidelity numerical model, which is validated against experimental data. The predicted results from the proposed framework agree well with those from the high-fidelity numerical simulation for a given combination of process parameters, achieving a computational cost measured in seconds. It is expected that the proposed framework could serve as a powerful tool for predicting the temperature field and further facilitating online control of process parameters.