🤖 AI Summary
High-fidelity engineering simulations—such as computational fluid dynamics (CFD) and finite element analysis (FEA)—are computationally prohibitive, and conventional surrogate modeling relies heavily on costly simulation runs. To address this, we propose a Bayesian-free, batch-mode deep active learning framework grounded in teacher–student distillation and an uncertainty-driven, gradient-free batch sampling strategy. By eliminating redundant deep neural network (DNN) ensembles, our approach preserves strong high-dimensional nonlinear modeling capability while substantially improving computational scalability. Evaluated on three representative engineering tasks—FEA, CFD, and propeller design—the method achieves accuracy comparable to state-of-the-art deep batch active learning (DBAL) baselines, yet reduces the required number of expensive simulation evaluations by 40%. To the best of our knowledge, this is the first efficient deep active learning paradigm that achieves high performance without Bayesian ensemble approximations.
📝 Abstract
In a computer-aided engineering design optimization problem that involves notoriously complex and time-consuming simulator, the prevalent approach is to replace these simulations with a data-driven surrogate that approximates the simulator's behavior at a much cheaper cost. The main challenge in creating an inexpensive data-driven surrogate is the generation of a sheer number of data using these computationally expensive numerical simulations. In such cases, Active Learning (AL) methods have been used that attempt to learn an input--output behavior while labeling the fewest samples possible. The current trend in AL for a regression problem is dominated by the Bayesian framework that needs training an ensemble of learning models that makes surrogate training computationally tedious if the underlying learning model is Deep Neural Networks (DNNs). However, DNNs have an excellent capability to learn highly nonlinear and complex relationships even for a very high dimensional problem. To leverage the excellent learning capability of deep networks along with avoiding the computational complexity of the Bayesian paradigm, in this work we propose a simple and scalable approach for active learning that works in a student-teacher manner to train a surrogate model. By using this proposed approach, we are able to achieve the same level of surrogate accuracy as the other baselines like DBAL and Monte Carlo sampling with up to 40 % fewer samples. We empirically evaluated this method on multiple use cases including three different engineering design domains:finite element analysis, computational fluid dynamics, and propeller design.
