A digital twin framework of reflow soldering based on a novel high dimension surrogate model

The concept of digital twins is to have a digital model that can replicate the behavior of a physical asset in real time. However, using digital models to reflect the structural performance of physical assets usually faces high computational costs, which makes it difficult for the model to satisfy real-time requirements. As a technique to replace expensive simulations, surrogate models have great potential to solve this problem. However, the optimal single surrogate model (SSM) applied to a given problem usually changes as factors change, and this can be mitigated by integrating multiple SSMs. Therefore, this study proposes a digital twin framework of reflow soldering based on a novel high dimension surrogate model. This method not only provides robust approximation but also reduces the additional cost brought by the experiment of the reflow soldering. Moreover, based on the characteristics of the experiment method, a finite element model (FEM), which provides scalability for the construction of a digital model, is established. That is, the number of FEM can be customized to not only decrease the computational cost by reducing elements but also obtain the key information by customizing the design of the reflow soldering. Numerical experiments are employed to verify the performance of the proposed digital twin framework of reflow soldering. A reflow soldering design case is used as an example to build a high dimension digital twin, which proves the feasibility and effectiveness of the framework.