Main Content

Neural State-Space Models

Use neural networks to represent the functions defining the nonlinear state space realization of your system

Functions

createMLPNetworkCreate and initialize a Multi-Layer Perceptron (MPL) network to be used within a neural state-space system
nssTrainingOptionsCreate training options object for neural state-space systems
nlssestEstimate nonlinear state-space model using measured time-domain system data
generateMATLABFunctionGenerate MATLAB functions that evaluate the state and output functions of a neural state-space object, and their Jacobians
idNeuralStateSpace/evaluateEvaluate a neural state-space system for a given set of state and input values and return state derivative (or next state) and output values
idNeuralStateSpace/linearizeLinearize a neural state-space model around an operating point
simSimulate response of identified model

Objects

idNeuralStateSpaceNeural state-space model with identifiable network weights
nssTrainingADAMAdam training options object for neural state-space systems
nssTrainingSGDMSGDM training options object for neural state-space systems

Blocks

Neural State-Space ModelSimulate neural state-space model in Simulink

Topics

  • About Identified Nonlinear Models

    Dynamic models in System Identification Toolbox™ software are mathematical relationships between the inputs u(t) and outputs y(t) of a system.