System Identification Toolbox™

predict(idnlarx) - Predict output k steps ahead for nonlinear ARX model

Syntax

YP = predict(MODEL,DATA,K)
YP = predict(SYS,DATA,K,INIT)
YP = predict(MODEL,DATA,K,'InitialState',INIT)

Description

YP = predict(MODEL,DATA,K) predicts the k-step ahead output with an idnlarx model.

YP = predict(SYS,DATA,K,INIT) or YP = predict(MODEL,DATA,K,'InitialState',INIT) specifies the initialization.

Input

• MODEL: idnlarx model object.

• DATA: iddata object.

• K: Prediction horizon. Old outputs up to time t-K are used to predict the output at time t. All relevant inputs are used. Default value: K = 1).

• INIT: initialization specification. INIT can be the following:

  • 'e': Assume the initial states of the model are such that the first N values of the predicted output match the first N samples of the measured output exactly, where N is the maximum channel delay in the model (N = max(getDelayInfo(model))). The initial states are not computed explicitly, but are assumed to exist. The prediction starts at the (N+1)^th sample, while a perfect match is assumed for the first N samples. If you want prediction of response values starting from the first data sample, you must estimate and provide the initial state vector explicitly as described in the following option for INIT = X0.

  • Real column vector X0, for the state vector corresponding to an appropriate number of output and input data samples prior to the simulation start time. To build an initial state vector from a given set of input-output data or to generate equilibrium states, use data2state(idnlarx), findstates(idnlarx) or findop(idnlarx). For multi-experiment data, X0 may be a matrix whose columns give different initial states for different experiments.

  • 'z': (Default) Zero initial state, equivalent to a zero vector of appropriate size.

  • iddata object containing output and input data samples prior to the simulation start time. If it contains more data samples than necessary, only the last samples are taken into account. This syntax is equivalent to sim(MODEL, U, 'InitialState', data2state(MODEL,INIT)) where data2state(idnlarx) transforms the iddata object INIT to a state vector.

Output

YP: Predicted output as an iddata object. If DATA contains multiple experiments, so will YP.

Note   If predict is called without an output argument, MATLAB software displays the predicted output(s) in a plot window.

See Also

predict

predict(idnlgrey)