Use System Identification Toolbox Model with input parameters

Hi,

I used the System Identification Model to make a polynomial model with three inputs and one output. This of course yields a discrete polynomial system. I can export this as a idpoly object to the workspace. My question is how I can use this object to create predictions?

The goal with my model is to create predictions for a system let's say 10 sampls in the future, and then compare them to some measurements. I want the model to use the three inputs, but also utilize some old measurements as the inital values for the prediction. What is the easiest/best way to achieve this?

I have looked at lsim(), but I can't make it work with the x0 parameter

Answer 1

[Star Strider]

From the polyest documentation:

[sys,ic] = polyest(___) returns the estimated initial conditions as an initialCondition object. Use this syntax if you plan to simulate or predict the model response using the same estimation input data and then compare the response with the same estimation output data. Incorporating the initial conditions yields a better match during the first part of the simulation.

That is the only way I am aware of to return the intital conditions from a polynomial model. (Similar options exist for other estimation functions, such as tfest and ssest.)

.