article
This article presents an optimized version of the finite element informed neural network (FEI-NN) based on the bio-inspired Harris Hawks optimization (HHO) algorithm for automatic hyperparameter tuning. FEI-NN combines the approximation capabilities of deep neural networks with the residuals from the weak formulation of the finite element method to impose physical consistency during learning. The HHO algorithm is used to optimize the learning rate, the physical penalty coefficient and the network size, leading to a hybrid model called HHO-FEI-NN. The method is validated on the 72 -bar space truss reference problem. The numerical results show a significant improvement in predictive accuracy, numerical stability and convergence speed compared to the standard FEI-NN and purely data-driven models.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/iraset68627.2026.11538504
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
