A composable autoencoder-based iterative algorithm for accelerating numerical simulations
This work addresses the computational bottleneck in engineering simulations by offering a faster, accurate ML-based alternative, though it appears incremental as it builds on existing ideas from commercial solvers and autoencoders.
The paper tackled the problem of accelerating numerical simulations for engineering applications by proposing CoAE-MLSim, a composable autoencoder-based ML method that reduces computational cost while maintaining accuracy across various PDE conditions, achieving significant speedups compared to commercial solvers and other ML approaches.
Numerical simulations for engineering applications solve partial differential equations (PDE) to model various physical processes. Traditional PDE solvers are very accurate but computationally costly. On the other hand, Machine Learning (ML) methods offer a significant computational speedup but face challenges with accuracy and generalization to different PDE conditions, such as geometry, boundary conditions, initial conditions and PDE source terms. In this work, we propose a novel ML-based approach, CoAE-MLSim (Composable AutoEncoder Machine Learning Simulation), which is an unsupervised, lower-dimensional, local method, that is motivated from key ideas used in commercial PDE solvers. This allows our approach to learn better with relatively fewer samples of PDE solutions. The proposed ML-approach is compared against commercial solvers for better benchmarks as well as latest ML-approaches for solving PDEs. It is tested for a variety of complex engineering cases to demonstrate its computational speed, accuracy, scalability, and generalization across different PDE conditions. The results show that our approach captures physics accurately across all metrics of comparison (including measures such as results on section cuts and lines).