Before you begin estimating the parameters, you must have configured the estimation data, selected parameters, and specified estimation options, as described in Specify Estimation Data, Specify Parameters for Estimation, and Estimation Options, respectively.
To start the estimation, in the Parameter Estimation tool, on the Parameter Estimation tab, click the Estimate button .
When starting the estimation, a progress window displays. At the end of the estimation, the Estimation Progress Report window should resemble the following:
The estimation results
are saved in
EstimatedParams in the Results list
on the Browse Data pane.
EstimatedParams and select Open... from
the menu. The window looks like the following figure.
the values of the parameters, the cost function value, and information
about the stopping criteria for the estimation. The optimization stops
because the successive function values are less than the specified
The Estimation Progress Report includes
the change in the cost function in the column titled NewData(Minimize).
To see a plot of the change in the cost function during estimation,
add the cost function plot by clicking the Add Plot button
on the Parameter Estimation tab and selecting
Cost from the list. After the estimation process completes,
the cost function minimization plot appears as shown in the following
Usually, a lower cost function value indicates a successful estimation, meaning that the experimental data matches the model simulation with the estimated parameters. If the optimization went well, you should see your cost function converge on a minimum value. The lower the cost, the more successful is the estimation.
For information on types of problems you may encounter using optimization solvers, see the following topics in the Optimization Toolbox™ documentation:
The estimated parameters graph shows the change in the estimated value of the parameters by iteration.
The values of the parameters are recorded with the estimated values.
The values of the estimated parameters are also updated in the MATLAB® workspace.
You can also examine the measured versus simulated data plot
to see how closely the simulated data matches the measured estimation
data. The next figure shows the measured versus simulated data plot
generated by running the estimation of the
engine_idle_speed model, see Create Experiment). Now, the simulated
values match the measured output signal better.