Physics-informed neural networks for PDE-constrained optimization and control
Barry-Straume, Jostein, Sarshar, Arash, Popov, Andrey A., Sandu, Adrian
–arXiv.org Artificial Intelligence
A fundamental problem in science and engineering is designing optimal control policies that steer a given system towards a desired outcome. This work proposes Control Physics-Informed Neural Networks (Control PINNs) that simultaneously solve for a given system state, and for the optimal control signal, in a one-stage framework that conforms to the underlying physical laws. Prior approaches use a two-stage framework that first models and then controls a system in sequential order. In contrast, a Control PINN incorporates the required optimality conditions in its architecture and in its loss function. The success of Control PINNs is demonstrated by solving the following open-loop optimal control problems: (i) an analytical problem, (ii) a one-dimensional heat equation, and (iii) a two-dimensional predator-prey problem.
arXiv.org Artificial Intelligence
Aug-18-2022
- Country:
- North America > United States
- Virginia > Montgomery County > Blacksburg (0.04)
- Europe > Latvia
- Riga Municipality > Riga (0.04)
- North America > United States
- Genre:
- Overview (1.00)
- Industry:
- Energy (0.68)
- Technology: