modelHelloWorld
Extends from Modelica.Icons.Example (Icon for runnable examples).
Information
Example showcasing how to replace block SimpleEquation
y = u^2 + 0.5u - 2
with artificial neural network surrogate PolynomNetwork.
A two-dimensional polynomial equation is approximmated with a dense feed-forward neural network. The network was generated using Python script from Notebook HelloWorld.ipynb.
Expected Results
Compare simulation results for variables reference and prediction.
Components
| Type | Name | Default | Description |
|---|---|---|---|
| Modelica.Blocks.Sources.Sine | sine | ||
| Utilities.SimpleEquation | eq | ||
| Utilities.PolynomNetwork | nn | ||
| Real | reference | eq.y | |
| Real | prediction | nn.y[1] |