Fit Methods
Numerical methods available for a Fit approach.
Method | Response Characteristics | Accuracy | Efficiency | Basic Parameters | Comments |
---|---|---|---|---|---|
Fit Automatically Selected by Training | General | N/A | N/A | Choose methods for Fit Automatically Selected by Training to consider. | Selects the most appropriate method and settings. It it recommended that you use this method unless you desire a specific method and settings. |
HyperKriging | Interpolated data | ✩✩✩ | ✩✩ | The time to build the Fit and
use the Fit (Evaluate From)
increases with both the number of runs and the number of design
variables in the input matrix. The number of design variables has more influence than the number of runs if order is larger than 1. |
|
Least Squares Regression | Data trend lines | ✩ | ✩✩✩ | Noises can be screened out with this method. Closed form equations are available. |
|
Moving Least Squares Method (MLSM) | General | ✩✩ | ✩✩ | The time to build the Fit and
use the Fit (Evaluate From)
increases with both the number of runs and the number of design
variables in the input matrix. The number of design variables has more influence than the number of runs if order is larger than one. |
|
Radial Basis Function | Interpolate data | ✩✩✩ | ✩✩ | The time to build the Fit
increases with both the number of runs and the number of design
variables in the input matrix. The number of runs has more influence than the number of design variables. The run time for using the Fit in another approach (Evaluate From) is very small regardless of the size of the input matrix. |
|
romAI | Leverages multilayer perceptron (MLP) and classical system theory |
Altair romAI requires installation of Twin Activate (version
2023.1 and above) and romAI block to be activated in the
extensions:
|