Physics Informed Neural Network for Dynamic Stress Prediction
This work addresses structural failure prediction for engineering applications, but it is incremental as it applies an existing PINN method to a specific domain.
The paper tackles the problem of predicting dynamic stress distributions during disruptive events like earthquakes by proposing a Physics Informed Neural Network (PINN-Stress) model, which reduces computational cost compared to high-fidelity Finite Element Models while maintaining accuracy and enabling near real-time predictions.
Structural failures are often caused by catastrophic events such as earthquakes and winds. As a result, it is crucial to predict dynamic stress distributions during highly disruptive events in real time. Currently available high-fidelity methods, such as Finite Element Models (FEMs), suffer from their inherent high complexity. Therefore, to reduce computational cost while maintaining accuracy, a Physics Informed Neural Network (PINN), PINN-Stress model, is proposed to predict the entire sequence of stress distribution based on Finite Element simulations using a partial differential equation (PDE) solver. Using automatic differentiation, we embed a PDE into a deep neural network's loss function to incorporate information from measurements and PDEs. The PINN-Stress model can predict the sequence of stress distribution in almost real-time and can generalize better than the model without PINN.