Create System object for online parameter estimation of OutputError polynomial model
obj = recursiveOE
obj = recursiveOE(Orders)
obj = recursiveOE(Orders,B0,F0)
obj = recursiveOE(___,Name,Value)
Use recursiveOE
command for parameter
estimation with realtime data. If all data necessary for estimation
is available at once, and you are estimating a timeinvariant model,
use the offline estimation command, oe
.
creates
a System object™ for online parameter estimation of a default singleinputsingle
output (SISO) OutputError model structure.
The default model structure has polynomials of order 1 and initial
polynomial coefficient values obj
= recursiveOEeps
.
After creating the object, use the step
command
to update model parameter estimates using recursive estimation algorithms
and realtime data.
specifies
the polynomial orders of the OutputError model to be estimated.obj
= recursiveOE(Orders
)
specifies
the polynomial orders and initial values of the polynomial coefficients.
Specify initial values to potentially avoid local minima during estimation.
If the initial values are small compared to the default obj
= recursiveOE(Orders
,B0,F0
)InitialParameterCovariance
property
value, and you have confidence in your initial values, also specify
a smaller InitialParameterCovariance
.
specifies
additional attributes of the OutputError model structure and recursive
estimation algorithm using one or more obj
= recursiveOE(___,Name,Value
)Name,Value
pair
arguments.
recursiveOE
creates a System object for
online parameter estimation of SISO OutputError polynomial models
using a recursive estimation algorithm.
A System object is a specialized MATLAB^{®} object designed specifically for implementing and simulating dynamic systems with inputs that change over time. System objects use internal states to store past behavior, which is used in the next computational step.
After you create a System object, you use commands to process
data or obtain information from or about the object. System objects
use a minimum of two commands to process data — a constructor
to create the object and the step
command
to update object parameters using realtime data. This separation
of declaration from execution lets you create multiple, persistent,
reusable objects, each with different settings.
You can use the following commands with the online estimation System objects in System Identification Toolbox™:
Command  Description 

step  Update model parameter estimates using recursive estimation algorithms and realtime data.

release  Unlock the System object. Use this command to enable setting of nontunable parameters. 
reset  Reset the internal states of a locked System object to the initial values, and leave the object locked. 
clone  Create another System object with the same object property values. Do not create additional objects using
syntax 
isLocked  Query locked status for input attributes and nontunable properties of the System object. 
Use the recursiveOE
command to create an
online estimation System object. Then estimate the OutputError
polynomial model parameters (B
and F
)
and output using the step
command with incoming input and output
data, u
and y
.
[B,F,EstimatedOutput] = step(obj,y,u)
For recursiveOE
object properties, see Properties.
recursiveOE
System object properties
consist of readonly and writable properties. The writable properties
are tunable and nontunable properties. The nontunable properties cannot
be changed when the object is locked, that is, after you use the step
command.
Use Name,Value
arguments to specify writable
properties of recursiveOE
objects during object
creation. After object creation, use dot notation to modify the tunable
properties.
obj = recursiveOE; obj.ForgettingFactor = 0.99;

Estimated coefficients of polynomial B(q), returned as a vector of real values specified in order of ascending powers of q^{1}.


Estimated coefficients of polynomial F(q), returned as a vector of real values specified in order of ascending powers of q^{1}.


Initial values for the coefficients of polynomial B(q)
of order If the initial guesses are much smaller than the default
Default: 

Initial values for the coefficients of polynomial F(q)
of order The coefficients in InitialF = [1 0.9 0.8]; all(abs(roots(InitialF))<1) ans = 1 If the initial guesses are much smaller than the default
Default: 

Initial values of the measured outputs buffer in finitehistory estimation, specified as
The When If the initial buffer is set to Specify
Default: 

Initial values of the inputs in the finite history window, specified as
The When the If the initial buffer is set to Specify
Default: 

Estimated covariance
The interpretation of


Covariance of the initial parameter estimates, specified as one of the following:
Use only when
Default: 

Recursive estimation algorithm used for online estimation of model parameters, specified as one of the following values:
Forgetting factor and Kalman filter algorithms are more computationally intensive than gradient and unnormalized gradient methods. However, they have better convergence properties. For information about these algorithms, see Recursive Algorithms for Online Parameter Estimation. These methods all use an infinite data history, and are available only when
Default: 

Forgetting factor, λ, relevant for parameter estimation, specified as a scalar in the range (0,1]. Suppose that the system remains approximately constant over T_{0} samples. You can choose λ such that: $${T}_{0}=\frac{1}{1\lambda}$$
Typical choices of λ are in the range Use only when
Default: 

Enable or disable parameter estimation, specified as one of the following:
Default: 

Floating point precision of parameters, specified as one of the following values:
Setting
Default: 

Covariance matrix of parameter variations, specified as one of the following:
N is the number of parameters to be estimated.
Kalman filter algorithm treats the parameters as states of a
dynamic system and estimates these parameters using a Kalman filter.
Default: 

Adaptation gain, γ, used in gradient recursive estimation algorithms, specified as a positive scalar.
Specify a large value for
Default: 

Bias in adaptation gain scaling used in the
The normalized gradient algorithm divides the adaptation gain
at each step by the square of the twonorm of the gradient vector.
If the gradient is close to zero, this can cause jumps in the estimated
parameters.
Default: 

Data history type defining which type of recursive algorithm you use, specified as:
Algorithms with infinite history aim to produce parameter estimates that explain all
data since the start of the simulation. These algorithms still use a fixed amount of
memory that does not grow over time. The object provides multiple algorithms of the
Algorithms with finite history aim to produce parameter estimates that explain only
a finite number of past data samples. This method is also called
slidingwindow estimation. The object provides one algorithm of
the For more information on recursive estimation methods, see Recursive Algorithms for Online Parameter Estimation.
Default: 

Window size determining the number of time samples to use for the slidingwindow
estimation method, specified as a positive integer. Specify
Choose a window size that balances estimation performance with computational and memory burden. Sizing factors include the number and time variance of the parameters in your model. Always specify Window Length in samples, even if you are using framebased input processing.
Suitable window length is independent of whether you are using samplebased or
framebased input processing (see
Default: 

Option for samplebased or framebased input processing, specified as a character vector or string.
Your [theta,EstimatedOutput] = step(obj,y,u)
Default: 
Starting in R2016b, instead of using the step
command
to update model parameter estimates, you can call the System object with
input arguments, as if it were a function. For example, [B,F,EstimatedOutput]
= step(obj,y,u)
and [B,F,EstimatedOutput] = obj(y,u)
perform
equivalent operations.
step
 release
 reset
 clone
 isLocked
 Recursive
Polynomial Model Estimator  oe
 recursiveAR
 recursiveARX
 recursiveARMA
 recursiveARMAX
 recursiveBJ
 recursiveLS