SI Estimate State-Space Model VI

Owning Palette: Parametric Model Estimation VIs

Requires: Advanced Signal Processing Toolkit or Control Design and Simulation Module

Estimates the parameters of a state-space model for an unknown system. You must manually select the polymorphic instance to use.

Details  Examples

SI Estimate State-Space Model (Subspace SISO Waveform)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signal specifies the input waveform of the stimulus signal.
	response signal specifies the input waveform of the response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noise returns the disturbance e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Subspace SISO Array)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signal specifies an array that represents the stimulus signal.
	response signal specifies an array that represents the response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	sampling rate (Hz) specifies the sampling frequency in hertz. The value of sampling rate must be greater than 0. The default is 1.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noise returns the disturbance e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Subspace MISO Waveform)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signals specifies the input waveform array of the stimulus signals. Each element of the array is the waveform of one stimulus signal.
	response signal specifies the input waveform of the response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noise returns the disturbance e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Subspace MISO Array)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signals specifies an array that represents the stimulus signals. Each row in the array is one stimulus signal.
	response signal specifies an array that represents the response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	sampling rate (Hz) specifies the sampling frequency in hertz. The value of sampling rate must be greater than 0. The default is 1.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noise returns the disturbance e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Subspace MIMO Waveform)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signals specifies the input waveform array of the stimulus signals. Each element of the array is the waveform of one stimulus signal.
	response signals specifies the input waveform array of the response signals. Each element of the array is the waveform of one response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noises returns the disturbances e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Subspace MIMO Array)

	structure selector determines additional matrices of the state-space model you want to estimate. D matrix? specifies whether to estimate the D matrix of the model. If TRUE, this VI estimates the D matrix. If FALSE, the D matrix is 0. The default is TRUE. K matrix? determines whether to estimate the Kalman gain matrix K. If TRUE, this VI estimates the K matrix. If FALSE, the K matrix is 0. The default is TRUE. initial states? specifies whether to estimate the initial state of the model. If TRUE, this VI estimates the initial state. If FALSE, the initial state is 0. The default is FALSE.
	stimulus signals specifies an array that represents the stimulus signals. Each row in the array is one stimulus signal.
	response signals specifies an array that represents the response signals. Each row in the array is one response signal.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	sampling rate (Hz) specifies the sampling frequency in hertz. The value of sampling rate must be greater than 0. The default is 1.
	Kalman gain returns the Kalman gain of the state-space model. The dimension of Kalman gain equals number of states.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	noises returns the disturbances e(t) in the estimated system model.
	error out contains error information. This output provides standard error out functionality.
	initial states returns the initial states of the state-space model. The dimension of initial states equals number of states.

SI Estimate State-Space Model (Realization SISO)

	impulse response is the input array of the impulse response.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	length specifies the number of data points of the impulse response to use when estimating the state-space model. The value must be less than or equal to the array size of the impulse response. The default is –1, which means this VI uses all data points of the impulse response.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	sampling rate (Hz) is the signal sampling rate in hertz. The value of sampling rate must be greater than 0.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	error out contains error information. This output provides standard error out functionality.

SI Estimate State-Space Model (Realization MIMO)

	impulse responses is the input array of the impulse response.
	number of states specifies the number of states of the system model. The value of number of states must be greater than 0. The default is 4.
	length specifies the number of data points of the impulse response to use when estimating the state-space model. The value must be less than or equal to the array size of the impulse response. The default is –1, which means this VI uses all data points of the impulse response.
	error in describes error conditions that occur before this node runs. This input provides standard error in functionality.
	sampling rate (Hz) is the signal sampling rate in hertz. The value of sampling rate must be greater than 0.
	system model out returns information about the model structure, nominal or estimated parameters, identification result, and so on. Use the Model Management VIs to retrieve the information system model out contains. Note  You can use a customized system model probe to view model information that flows through system model wires when you debug a block diagram created with the System Identification VIs. Right-click a system model wire and select Custom Probe»SI System Model from the shortcut menu to use the system model probe.
	coefficients of state-space model returns the coefficients of the state-space model. A returns the state matrix of the system model. B returns the input matrix of the system model. C returns the output matrix of the system model. D returns the direct transmission matrix of the system model.
	error out contains error information. This output provides standard error out functionality.

SI Estimate State-Space Model Details

You can use the SI Estimate Orders of System Model VI to estimate the optimal order of the state-space model. In some cases, the optimal orders returned by the SI Estimate Orders of System Model VI might not be appropriate for the number of states. You can use the singular values output of the State-Space instances of the SI Estimate Orders of System Model VI to obtain the optimal number of states. You can display singular values using an XY graph. The turning point in the curve specifies the optimal number of states.

The System Identification VIs estimate discrete state-space models using two methods: the realization and the deterministic-stochastic subspace methods. The realization method uses the system impulse response as the input. You can use the SI Estimate Impulse Response VI to compute the impulse response from stimulus and response signals.

The realization method estimates only the deterministic part, A, B, C, D, of the system and does not include the stochastic part, K, in the model structure. The deterministic-stochastic subspace method includes both the deterministic and stochastic parts in the model structure. Therefore, you must choose the subspace method if you want to include the stochastic part in the model. Otherwise, you can use the realization method.

Examples

Refer to the following VIs for examples of using the SI Estimate State-Space Model VI:

• Discrete State-Space Model (Direct Method) VI: labview\examples\System Identification\Getting Started\Closed-Loop Estimation.llb
• Estimate State-Space Model from Impulse Response VI: labview\examples\System Identification\Getting Started\Parametric Estimation.llb