System Identification Toolbox™

iddata - Time- or frequency-domain data

Syntax

data = iddata(y,[],Ts) data = iddata(y,u,Ts) data = iddata(y,u,Ts,'Frequency',W) data = iddata(y,u,Ts,'P1',V1,...,'PN',VN) data = iddata(idfrd_object)

Arguments

y

Name of MATLAB variable that represents the output signal from a system. Sets the OutputData iddata property. For a single-output system, this is a column vector. For a multiple-output system with N_y output channels and N_T time samples, this is an N_T-by-N_y matrix.

Note Output data must be in the same domain as input data.

u

Name of MATLAB variable that represents the input signal to a system. Sets the InputData iddata property. For a single-input system, this is a column vector. For a multiple-output system with N_u output channels and N_T time samples, this is an N_T-by-N_u matrix.

Note Input data must be in the same domain as output data.

Ts

Time interval between successive data samples in seconds. Default value is 1. For continuous-time data in the frequency domain, set Ts to 0.

'P1',V1,...,'PN',VN

Pairs of iddata property names and property values.

idfrd_object

Name of idfrd data object.

Description

data = iddata(y,[],Ts) creates an iddata object for time-series data, containing a time-domain output signal y and an empty input signal [], respectively. Ts specifies the sampling interval of the experimental data.

data = iddata(y,u,Ts) creates an iddata object containing a time-domain output signal y and input signal u, respectively. Ts specifies the sampling interval of the experimental data.

data = iddata(y,u,Ts,'Frequency',W) creates an iddata object containing a frequency-domain output signal y and input signal u, respectively.Ts specifies the sampling interval of the experimental data. W specifies the iddata property 'frequency' as a vector of frequencies.

data = iddata(y,u,Ts,'P1',V1,...,'PN',VN) creates an iddata object containing a time-domain or frequency-domain output signal y and input signal u, respectively. Ts specifies the sampling interval of the experimental data. 'P1',V1,...,'PN',VN are property-value pairs, as described in iddata Properties.

data = iddata(idfrd_object) transforms an idfrd object to a frequency-domain iddata object.

iddata Properties

The following table describes iddata object properties and their values. These properties are specified as property-value arguments 'P1',V1,...,'PN',VN' in the iddata constructor, or you can set them using the set command or dot notation. In the list below, N denotes the number of data samples in the input and output signals, ny is the number of output channels, nu is the number of input channels, and Ne is the number of experiments.

Tip Property names are not case sensitive. You do not need to type the entire property name. However, the portion you enter must by enough to uniquely identify the property.

Property Name Description Value

Domain

Specifies whether the data is in the time domain or frequency domain.

'Frequency' — Frequency-domain data.
'Time' (Default) — Time-domain data.

ExperimentName Name of each data set contained in the iddata object. For Ne experiments, a 1-by-Ne cell array of strings. Each cell contains the name of the corresponding experiment. Default names are {'Exp1', 'Exp2',...}.

Frequency

(Frequency-domain data only)

Frequency values for defining the Fourier Transforms of the signals.

For a single experiment, this is an N-by-1 vector. For Ne experiments, a 1-by-Ne cell array and each cell contains the frequencies of the corresponding experiment.

InputData

Name of MATLAB variable that stores the input signal to a system.

For nu input channels and N data samples, this is an N-by-nu matrix.

InputName Specifies the names of individual input channels. Cell array of length nu-by-1 contains the name string of each input channel. Default names are {'u1';'u2';...}.

InputUnit Specifies the units of each input channel. Cell array of length nu-by-1. Each cell contains a string that specifies the units of each input channel.

InterSample

Specifies the behavior of the input signals between samples for transformations between discrete-time and continuous-time.

For a single experiment:

zoh— (Default) Zero-order hold maintains a piecewise-contant input signal between samples.
foh— First-order hold maintains a piecewise-linear input signal between samples.
bl— Band-limited behavior specifies that the continuous-time input signal has zero power above the Nyquist frequency.

For Ne experiments, InterSample is an nu-by-Ne cell array. Each cell contains one of these values corresponding to each experiment.

Name Name of the data set. Text string.

Notes Comments about the data set. Text string.

OutputData

Name of MATLAB variable that stores the output signal from a system.

For ny output channels and N samples, this is an N-by-ny matrix.

OutputName For a multiple-output system, specifies the names of individual output channels. Cell array of length ny-by-1 contains the name string of each output channel. Default names are {'y1';'y2';...}.

OutputUnit Specifies the units of each output channel. For ny output channels, a cell array of length ny-by-1. Each cell contains a string that specifies the units of the corresponding output channel.

Period Period of the input signal. (Default) For a nonperiodic signal, set to inf. For a multiple-input signal, this is an nu-by-1 vector and the kth entry contains the period of the kth input. For Ne experiments, this is a 1-by-Ne cell array and each cell contains a scalar or vector of periods for the corresponding experiment.

SamplingInstants

(Time-domain data only) The time values in the time vector calculated from the properties Tstart and Ts.

For a single experiment, this is an N-by-1 vector. For Ne experiments, this is a 1-by-Ne cell array and each cell contains the sampling instants of the corresponding experiment.

TimeUnit (Time-domain data only) Time unit. A string that specifies the time unit for the time vector.

Ts

Time interval between successive data samples in seconds. Must be specified for both time- and frequency-domain data. For frequency-domain, it is used to compute Fourier transforms of the signals as discrete-time Fourier transforms (DTFT) with the indicated sampling interval.

Note Your data must be uniformly sampled.

Default value is 1. For continuous-time data in the frequency domain, set to 0; the inputs and outputs are interpreted as continuous-time Fourier transforms of the signals. Note that Ts is essential also for frequency-domain data, for proper interpretation of how the Fourier transforms were computed: They are interpreted as discrete-time Fourier transforms (DTFT) with the indicated sampling interval.. For multiple-experiment data, Ts is a 1-by-Ne cell array and each cell contains the sampling interval of the corresponding experiment.

Tstart

(Time-domain data only) Specifies the start time of the time vector.

For a single experiment, this is a scalar. For Ne experiments, Tstart is a 1-by-Ne cell array and each cell contains the starting time of the corresponding experiment.

Units

(Frequency-domain data only)

Frequency unit.

Specified as rad/s or Hz.For multiexperiement data with Ne experiments, Units is a 1-by-Ne cell array and each cell contains the frequency unit for each experiment.

UserData Additional comments. Text string.

`advice`
`detrend`
`fcat`
`getexp`
`idfilt`
`idfrd`
`plot`
`resample`
`size`

iddata - Time- or frequency-domain data

Syntax

Arguments

Description

iddata Properties

See Also