Efficient prediction of thermal history and molten pool shape in a large domain for metal additive manufacturing via surrogate modeling and machine learning

This study is concerned with predicting accurate temperature fields in a large domain using a surrogate modeling technique and machine learning for metal laser powderbed fusion processes. Though high-fidelity modeling has been demonstrated to provide accurate representations of the attendant molten pool geometry and temperature field, simulation of large scale components is not feasible, even with massively parallelized computing, due to a prohibitive high computing costs. Using a low fidelity model, while computationally efficient, cannot predict temperature history and molten pool shapes accurately. To overcome this challenge, a surrogate modeling approach is developed using a lower-fidelity model to extract temperature variation in a large domain with pertinent features for use in a Gaussian process regression and implement an active learning algorithm to determine when and where the high-fidelity model, which has been developed in the authors’s group over the years, needs to be simulated to improve modeling results. Using such an approach, the high-fidelity model computational load can be decreased significantly, increasing calculation throughput. With this approach, accurate molten pool shapes of a large domain are predicted with affordable computational time. The validation results are provided to show that this hybrid method is effective and provides reasonable accuracy.