|Download Help (Windows Only)|
The purpose of system identification is to build mathematical models of an unknown dynamic system by using a set of stimulus and response signals. The following figure shows a typical diagram of the system identification process that uses an adaptive filter.
In the previous figure, x(n) is the stimulus signal, which excites both the unknown system and the adaptive filter. d(n) is the response signal of the unknown system. y(n) is the output signal from the adaptive filter. e(n) is the error signal that denotes the difference between d(n) and y(n).
During each iteration, the adaptive filter adjusts the filter coefficients to minimize the power of e(n). As a result, the power of e(n) becomes small and the coefficients of the adaptive filter become close to the coefficients of the unknown system.
|Note You can use the LabVIEW Adaptive Filter Toolkit to estimate only the impulse response of the unknown system. To estimate other types of system models, such as parametric models, install the LabVIEW System Identification Toolkit.|
Refer to the System Identification VI in the examples\Adaptive Filters\Applications\System Identification directory for an example that uses the Adaptive Filter Toolkit to identify a dynamic, unknown system.