nwidsingleMultiStep function

Identify a single target module using the Multistep algorithm.

Syntax

• model = nwidMultiStep(data,model,orders,options)  performs identification based on the provided data, initialized network model, model orders and option set. The identified predictor model is returned.

Input arguments

• data

  nwdata object

  Network data object. The input excitation, input node and output node signals (as referred to by their labels) in the Rset, Dset and Yset of the predictor model must be present in the data.

• model

  nwpredmodel object

  Initialized predictor model object. The properties of the predictor mappings G, T and H are used in the algorithm, with some restrictions:

  • The algorithm currently only supports Variable = z^-1, hence only discrete-time identification is possible.
  • As the innovations are reconstructed, the noise model H is fixed to identity.
  • For the EBLDM method, setting initial parameter values using pnum/pden is not supported.

  Additional requirements for the predictor model:

  • The model must have exactly 1 output node, i.e. length(model.Yset)==1.
  • The property aux must be of type AuxPredMultiStep.

• orders

  structure array	[1,3] integer array]

  Model orders. Can be used to override properties of the initialized network model object. When using the output error estimation method, this must a structure arrays with the optional field P, which should be a structure array with the scalar fields npnum and npden, to specify the global model orders of P. You can also add the optional fields G and T, which should each be structure arrays themselves with the optional fields npnum, npden and d (to set the analogous PredictorMap properties). When using the EBLDM method, this should be a set of orders of the target module [nb nf nk], indicating the number of parameters of the numerator and denominator, and the number of delays respectively.

• options

  nwidsingleMultiStepOptions object

  Option set for nwidsingleMultiStep function. Can be constructed using options = nwidsingleMultiStepOptions for the default option set or options = nwidsingleMultiStepOptions(Name=Value,...) to set specified options.

Output arguments

• model

  nwpredmodel object

  Estimated predictor model object. For the output error estimation method, the pnum and pden properties of the G, T and P fields are populated with the estimated parameter values. The e properties of G, T and aux.P contain the fixed and estimated transfer functions of the predictor model connections. For the EBLDM estimation method, only the pnum, pden and e properties of the target module are populated.