Main Content

Nonlinear ARX Models

Nonlinear behavior modeled using dynamic networks such as sigmoid and wavelet

Use nonlinear ARX models to represent nonlinearities in your system using dynamic nonlinearity estimators such as wavelet networks, tree-partitioning, and sigmoid networks. In the toolbox, these models are represented as idnlarx objects. You can estimate Nonlinear ARX models in the System Identification app, or at the command line using the nlarx command.

Apps

System IdentificationIdentify models of dynamic systems from measured data

Functions

expand all

idnlarxNonlinear ARX model
nlarxEstimate parameters of nonlinear ARX model
nlarxOptionsOption set for nlarx
isnlarxDetect nonlinearity in estimation data
initSet or randomize initial parameter values
getpvecObtain model parameters and associated uncertainty data
setpvecModify values of model parameters
linearRegressorSpecify linear regressor for nonlinear ARX model (Since R2021a)
polynomialRegressorSpecify polynomial regressor for nonlinear ARX model (Since R2021a)
periodicRegressorSpecify periodic regressor for nonlinear ARX model (Since R2022a)
customRegressorSpecify custom regressor for nonlinear ARX model (Since R2021a)
getregRegressor expressions and numerical values in nonlinear ARX model
polyreg(Not recommended) Powers and products of standard regressors
customreg(Not recommended) Custom regressor for nonlinear ARX models
addreg(Not recommended) Add custom regressors to nonlinear ARX model
idWaveletNetworkWavelet network function for nonlinear ARX and Hammerstein-Wiener models
idSigmoidNetworkSigmoid network function for nonlinear ARX and Hammerstein-Wiener models
idTreePartitionTree-partitioned nonlinear function for nonlinear ARX models
idCustomNetworkCustom network function for nonlinear ARX and Hammerstein-Wiener models
idLinearLinear mapping object for nonlinear ARX models
idGaussianProcessGaussian process regression mapping function for nonlinear ARX and Hammerstein-Wiener models (requires Statistics and Machine Learning Toolbox) (Since R2021b)
idTreeEnsembleDecision tree ensemble mapping function for nonlinear ARX models (requires Statistics and Machine Learning Toolbox) (Since R2021b)
idSupportVectorMachineSupport vector machine regression mapping function for nonlinear ARX models (requires Statistics and Machine Learning Toolbox) (Since R2022a)
idNeuralNetworkMultilayer neural network mapping function for nonlinear ARX models and Hammerstein-Wiener models (requires Statistics and Machine Learning Toolbox or Deep Learning Toolbox) (Since R2023b)
idFeedforwardNetwork(Not recommended) Multilayer feedforward neural network mapping function for nonlinear ARX models (requires Deep Learning Toolbox)
evaluateEvaluate output values of idnlarx or idnlhw mapping object array for given set of input values
simSimulate response of identified model
simOptionsOption set for sim
predictPredict identified model K-step-ahead output
predictOptionsOption set for predict
compareCompare identified model output with measured output
compareOptionsOption set for compare
forecastForecast identified model output
forecastOptionsOption set for forecast
nlarxPlotPlot nonlinearity of nonlinear ARX model (Since R2023a)
evaluateEvaluate output values of idnlarx or idnlhw mapping object array for given set of input values
getDelayInfoGet input/output delay information for idnlarx model structure
findopCompute operating point for Nonlinear ARX model
findopOptionsOption set for findop
operspecConstruct operating point specification object for idnlarx model
linearizeLinearize nonlinear ARX model
linappLinear approximation of nonlinear ARX and Hammerstein-Wiener models for given input

Blocks

expand all

Nonlinear ARX ModelSimulate nonlinear ARX model in Simulink software
Iddata SinkExport simulation data as iddata object to MATLAB workspace
Iddata SourceImport time-domain data stored in iddata object in MATLAB workspace

Topics