LabVIEW 2013 Advanced Signal Processing Toolkit Help
»View Product Info
One of the most important applications of time series analysis is building mathematical models for observed time series. The resulting mathematical models can help you better understand the dynamic characteristics of the corresponding physical systems and assist you in monitoring or providing feedback control for the systems. You also can use the resulting mathematical models to estimate the power spectrum of a time series.
Using the LabVIEW Time Series Analysis Tools, you can build the following types of models:
- Polynomial models—For univariate time series, you can build autoregressive (AR) models, moving average (MA) models, and autoregressive-moving average (ARMA) models. For multivariate (vector) time series, you can build vector autoregressive (VAR) models and vector autoregressive-moving average (VARMA) models.
- Modal parametric models—For dynamic systems, especially those for which a bulk structural vibration model is useful, you can build models using the following modal parameters: natural frequencies, damping factors, resonance magnitudes, and resonance phases.
- Stochastic state-space models—For multivariate time series, you can build state-space models that characterize the dynamic behavior of a system.
||Note The LabVIEW System Identification Toolkit also provides tools for building dynamic models. These tools focus on building dynamic models with both the stimulus and response signals of the system. The Time Series Analysis Tools focus on building models using only the response signals of the system.