Finite Element Method-enhanced Neural Network for Forward and Inverse Problems
This addresses simulation and optimization challenges in engineering domains, but it appears incremental as it builds on existing FEM and neural network techniques.
The authors tackled forward and inverse problems by developing a hybrid model combining finite element methods and neural networks, resulting in a data-efficient and physics-conforming surrogate model with demonstrated accuracy in applications like uncertainty quantification for wind effects on buildings and bearing coefficient identification.
We introduce a novel hybrid methodology combining classical finite element methods (FEM) with neural networks to create a well-performing and generalizable surrogate model for forward and inverse problems. The residual from finite element methods and custom loss functions from neural networks are merged to form the algorithm. The Finite Element Method-enhanced Neural Network hybrid model (FEM-NN hybrid) is data-efficient and physics conforming. The proposed methodology can be used for surrogate models in real-time simulation, uncertainty quantification, and optimization in the case of forward problems. It can be used for updating the models in the case of inverse problems. The method is demonstrated with examples, and the accuracy of the results and performance is compared against the conventional way of network training and the classical finite element method. An application of the forward-solving algorithm is demonstrated for the uncertainty quantification of wind effects on a high-rise buildings. The inverse algorithm is demonstrated in the speed-dependent bearing coefficient identification of fluid bearings. The hybrid methodology of this kind will serve as a paradigm shift in the simulation methods currently used.