In this project, the linear elasticity problem is solved with Physics Informed Neural Networks (PINN). The governing equations for isotropic linear elasticity are
where is the stress tensor, is the strain tensor, u is the displacement vector, f is the body force vector, and are the Lamé parameters and Einstein summation applies. Now we consider the linear elasticity problem on a square domain . We consider the following boundary conditions:
Top wall
Right wall
Left wall
Bottom wall
where is the traction prescribed on the boundaries and the Q is the load magnitude. We consider the following body force:
The analytical solution to this problem is [ , ].
In the numerical implementation, we output both displacements and stresses and adopt the following loss function to prescribe boundary conditions and enforce the governing equation.
For model parameters: , and , we have the following results
The decrease of the loss function is shown in the following figure.
Note: The implementations were developed and tested on colab with TensorFlow 1.9 and hardware accelerator chosen as GPU.