Nonparameteric impulse response estimation
sys = impulseest(data)
sys = impulseest(data,N)
sys = impulseest(data,N,NK)
sys = impulseest(___,options)
an impulse response model,
sys = impulseest(
using time- or frequency-domain data,
model order (number of nonzero impulse response coefficients)
is determined automatically using persistence of excitation analysis
on the input data.
Use nonparametric impulse response to analyze
feedback effects, delays and significant time constants.
Estimation data with at least one input signal and nonzero sample time.
For time domain estimation,
For frequency domain estimation,
Order of the FIR model. Must be one of the following:
Transport delay in the estimated impulse response, specified as a scalar integer. For data containing Nu inputs and Ny outputs, you can also specify a Ny-by-Nu matrix.
Positive values of
The impulse response (input
Default: zeros(Ny, Nu)
Estimation options that specify the following:
Estimated impulse response model.
Compute a nonparametric impulse response model using data from a hair dryer. The input is the voltage applied to the heater and the output is the heater temperature. Use the first 500 samples for estimation.
load dry2 ze = dry2(1:500); sys = impulseest(ze);
ze is an
iddata object that contains time-domain data.
sys, the identified nonparametric impulse response model, is an
Analyze the impulse response of the identified model from time 0 to 1.
h = impulseplot(sys,1);
Right-click the plot and select Characteristics > Confidence Region to view the statistically zero-response region. Alternatively, you can use the
The first significantly nonzero response value occurs at 0.24 seconds, or, the third lag. This implies that the transport delay is 3 samples. To generate a model where the 3-sample delay is imposed, set the transport delay to 3:
sys = impulseest(ze,,3)
Estimate an impulse response model with a specific order.
load iddata3 z3 sys = impulseest(z3,35);
Estimate an impulse response model with transport delay of 3 samples.
If you know about the presence of delay in the input/output data in advance, use the value as a transport delay for impulse response estimation.
Generate data with 3 sample input to output lag.
u = rand(100,1); sys = idpoly([1 .1 .4],[0 0 0 4 -2],[1 1 .1]); opt = simOptions('AddNoise',true); y = sim(sys,u,opt); data = iddata(y,u,1);
Estimate a 20th order model with a 3 sample transport delay.
model = impulseest(data,20,3);
Obtain regularized estimates of impulse response model using the regularizing kernel estimation option.
Estimate a model using regularization.
load iddata3 z3; sys1 = impulseest(z3);
By default, tuned and correlated kernel (
'TC') is used for regularization.
Estimate a model with no regularization.
opt = impulseestOptions('RegulKernel','none'); sys2 = impulseest(z3,opt);
Compare the impulse response of both models.
h = impulseplot(sys1,sys2,70);
As the plot shows, using regularization makes the response smoother.
Plot the confidence interval.
The uncertainty in the computed response is reduced at larger lags for the model using regularization. Regularization decreases variance at the price of some bias. The tuning of the regularization is such that the bias is dominated by the variance error though.
load regularizationExampleData eData;
Create a transfer function model used for generating the estimation data (true system).
trueSys = idtf([0.02008 0.04017 0.02008],[1 -1.561 0.6414],1);
Obtain regularized impulse response (FIR) model.
opt = impulseestOptions('RegulKernel', 'DC'); m0 = impulseest(eData, 70, opt);
Convert the model into a transfer function model after reducing the order.
m = balred(idss(m0),15);
Obtain a state-space model using regularized reduction of ARX model.
m1 = ssregest(eData,15);
Compare the impulse responses of the true system, regularized and state-space models.
impulse(trueSys, m, m1, 50);
Use the empirical impulse response of the measured data to verify whether there are feedback effects. Significant amplitude of the impulse response for negative time values indicates feedback effects in data.
Compute the noncausal impulse response using a fourth-order prewhitening filter, automatically chosen order and negative lag using nonregularized estimation.
load iddata3 z3; opt = impulseestOptions('pw',4,'RegulKernel','none'); sys = impulseest(z3,,'negative',opt);
sys is a noncausal model containing response values for negative time.
Analyze the impulse response of the identified model.
h = impulseplot(sys);
View the statistically zero-response region by right-clicking on the plot and selecting Characteristics > Confidence Region. Alternatively, you can use the
The large response value at
t=0 (zero lag) suggests that the data comes from a process containing feedthrough. That is, the input affects the output instantaneously. There could also be a direct feedback effect (proportional control without some delay that
u(t) is determined partly by
Also, the response values are significant for some negative time lags, such as at -7 seconds and -9 seconds. Such significant negative values suggest the possibility of feedback in the data.
Compute an impulse response model for frequency response data.
load demofr; zfr = AMP.*exp(1i*PHA*pi/180); Ts = 0.1; data = idfrd(zfr,W,Ts); sys = impulseest(data);
Identify parametric and nonparametric models for a data set, and compare their step response.
Identify the impulse response model (nonparametric) and state-space model (parametric), based on a data set.
load iddata1 z1; sys1 = impulseest(z1); sys2 = ssest(z1,4);
sys1 is a discrete-time identified transfer function model.
sys2 is a continuous-time identified state-space model.
Compare the step response for
step(sys1,'b',sys2,'r'); legend('impulse response model','state-space model');
A significant value of the impulse response of
sys for negative time values indicates
the presence of feedback in the data.
To view the region of insignificant impulse response
(statistically zero) in a plot, right-click on the plot and select Characteristics > Confidence
Region. A patch depicting the zero-response
region appears on the plot. The impulse response at any time value
is significant only if it lies outside the zero response region. The
level of significance depends on the number of standard deviations
options in the property editor. A common choice is 3 standard deviations,
which gives 99.7% significance.
Correlation analysis refers to methods that estimate the impulse response of a linear model, without specific assumptions about model orders.
The impulse response, g, is the system's output when the input is an impulse signal. The output response to a general input, u(t), is obtained as the convolution with the impulse response. In continuous time:
The values of g(k) are the discrete time impulse response coefficients.
You can estimate the values from observed input-output data
in several different ways.
the first n coefficients using the least-squares
method to obtain a finite impulse response (FIR) model of order n.
Several important options are associated with the estimate:
The input can be pre-whitened by applying an input-whitening filter
PW to the data. This minimizes the effect
of the neglected tail (
k > n) of the impulse
A filter of order
PW is applied
such that it whitens the input signal
1/A = A(u)e, where
a polynomial and
e is white noise.
The inputs and outputs are filtered using the filter:
uf = Au,
yf = Ay
The filtered signals
used for estimation.
You can specify prewhitening using the
pair argument of
The least-squares estimate can be regularized. This means that a prior
estimate of the decay and mutual correlation among
formed and used to merge with the information about
the observed data. This gives an estimate with less variance, at the
price of some bias. You can choose one of the several kernels to encode
the prior estimate.
This option is essential because, often, the model order
be quite large. In cases where there is no regularization,
be automatically decreased to secure a reasonable variance.
You can specify the regularizing kernel using the
pair argument of
Autoregressive Parameters —
The basic underlying FIR model can be complemented by
parameters, making it an ARX model.
This gives both better results for small
allows unbiased estimates when data are generated in closed loop.
impulseest uses NA
= 5 for t>0 and NA
= 0 (no autoregressive component) for t<0.
Noncausal effects — Response for negative lags. It may happen that the data has been generated partly by output feedback:
where h(k) is the impulse
response of the regulator and r is a setpoint or
disturbance term. The existence and character of such feedback h can
be estimated in the same way as g, simply by trading
places between y and u in the
estimation call. Using
impulseest with an indication
of negative delays, ,
returns a model
mi with an impulse response
aligned so that it corresponds to lags .
This is achieved because the input delay (
For a multi-input multi-output system, the impulse response g(k) is an ny-by-nu matrix, where ny is the number of outputs and nu is the number of inputs. The i–j element of the matrix g(k) describes the behavior of the ith output after an impulse in the jth input.