Answered
Using built in ARX function to estimate a linear ARX model for multiple input/output pairs of different size
Try creating independent iddata objects for each I/O pair. Then merge them into one "multi-experiment" iddata object. Use the mu...

13 years ago | 0

| accepted

Answered
Using ARX to obtain a transfer function from frequency response data
ARX is usually not a good estimator of frequency response data. Please try Output-Error (OE) model which more closely represents...

13 years ago | 0

| accepted

Answered
system identification toolbox
* If you use Output-Error (OE) model structure, then the ratio of the polynomials B and F is your transfer function: TF := B(q)/...

13 years ago | 0

| accepted

Answered
Bode plot for an Array type input signal
Looks like you need to generate the power spectrum of the input signal and compare that to the spectrum of the output. Look in S...

13 years ago | 2

Answered
AIC for ARIMA
In System Identification Toolbox, use the armax command to generate a model. Suppose x represents your time series data: z = i...

13 years ago | 0

Answered
ARMA forecasting
Use ARMAX function in System Identification Toolbox to estimate an ARMA model, as in model = arma(data, [na nc]) In R2012a: u...

13 years ago | 1

Answered
Problem using Hammerstein-Wiener model estimation.
The Hammerstein-Wiener model (idnlhw) contains the linear model as its component. See the "LinearModel" property of the idnlhw o...

13 years ago | 0

Answered
Wc = gram(sys,'c') (gramian controllability)
c is just a string indicating your choice of gramian type ('c' for controllability gramian and 'o' for observability) Try: gr...

13 years ago | 0

Answered
Z-transform of time domain data
Try this: data = iddata(x,[],Ts) % ts:= sampling time Filter = armax(data, [na nc]) % na, nc are filter design parameters...

13 years ago | 0

Answered
time series analysis - correlation
If there is dynamic/causal dependence, you should try dynamic model fitting tools like those in System Identification Toolbox. S...

13 years ago | 0

Answered
How to plot more points with bodeplot
You can specify the frequency vector you want as an input argument to BODE or BODEPLOT. You can also fetch the magnitude/phase e...

13 years ago | 0

Answered
system identification
By vibration signature, do you mean the frequency responses from the two inputs to the output? Are F1 and F2 constants? Is the s...

14 years ago | 0

Answered
system Identification using MEX C++
It seems your ODE file is returning nonfinite values of either y or dx for the current parameter values in model nlgr. To debug ...

14 years ago | 0

Answered
bayesian information criterion
What does class(yp) reveal? If it is iddata, you would need to use yp.y(1:4018) to retrieve the predicted response data used in ...

14 years ago | 0

Answered
Forecasting function
In R2012a, you can also use a new "FORECAST" function. See help on "idParametric/forecast".

14 years ago | 0

Answered
pem: Adding noise model *worsens* fit?
It could be. But to isolate the issue, set 'focus' to 'simulation' in the call to PEM command since by default you are minimizin...

14 years ago | 0

Answered
Identification of NARX problem with death time between Inputs and Outputs
Have you looked at nlarx, idnlarx functions in system identification toolbox? The input argument "nk" denotes delay from input t...

14 years ago | 0

Answered
Need to incorporate measured plant response into model
What kind of data is it? You could try "impulseest" function in R2012a release which is an FIR estimator.

14 years ago | 0

Answered
avoid negative step response
If you are using idproc model type, you can impose a constraint on model's gain (Kp) and zero (Tz) values to achieve this. Other...

14 years ago | 0

Answered
Linear Coefficient from Non Linear ARX
try running the getlinmod command on it.

14 years ago | 0

Answered
Identifying the numbers of AR or MA terms in matlab
Look into arxstruc, selstruc and n4sid's order selection feature.

14 years ago | 0

Answered
SYstem Id doubt
That means that the model is not reliable. What orders did you try? Usually, this indicates unnecessarily high orders.

14 years ago | 0

Answered
ARIMA models and Box-jenkins function
In R2012a, use the ARMAX function with "IntegrateNoise" attribute specified using name-value pair. See ARMAX documentation for m...

14 years ago | 0

Answered
ARIMA Model - AR(4)AR(364) with MA(7) - too big for MATLAB - how to handle?
Try nlarx. Choose orders [0 0 0], and specify all regressors using "custom regressors". For example: model = idnlarx([0 0 0]...

14 years ago | 0

Answered
Enforcing constraints during grey-box state space identification
In R2012a release, idgrey supports specification of parameter constraints. Look at the (new) "Structure" property of the model w...

14 years ago | 1

Answered
System Identification - SISO -SIPO
You might need to do some homework on concepts of data fitting, static (e.g. polynomial function) vs. dynamic (e.g., transfer fu...

14 years ago | 0

Answered
Compare error plot in command line for system id toolbox model/data object
Have you looked at RESID and PE routines? PE calculates prediction errors and allows specification of initial conditions.

14 years ago | 0

Answered
Calculation of dead time and time constant for non linear system
Delays are not necessarily separable from system dynamics such as effect of poles and zeros on the response. However, in many ca...

14 years ago | 0

Answered
Data import for System identifications toolbox
You will need to bring data into MATLAB workspace as double matrices first. If using System Identification GUI, you can import v...

14 years ago | 0

Answered
grey box parameter estimation with discrete time and force data .
The model suggests it has 2 outputs and 1 input. So I guess "y" should be matrix with 2 columns.

14 years ago | 0