Performs wavelet decomposition of the input signal. The output is a trended version of the data with the mean removed. The range of data variation picked up in the decomposition is controlled by the scale input.
The Residual is then the difference between the original signal and the decomposed signal.
Defines the time series data fed into the function. This can be a sensor ID or another function.
Defines the proportion at which to decompose data.
The Scale must be a whole number >= 1.
A smaller number means that a shorter window of data is considered and higher frequency fluctuations are accounted for. Larger Scales will smooth out the data more.
*Input data is optional in most cases. If Info360 detects that the first input is time series data, it will be applied to the function. Otherwise, the current active sensor's data will be used, which is often the case in Reference Charts.
Example Usage as an Expression:
Decompose(ROC(3), 2) - Decompose the rate of change for the last 3 intervals at a scale of 2
Example Reference Chart:
The following example illustrates the Decompose function using three different scales.
Note that with increasing Scale, the results are smoother. In this case, Decompose(3) best captures the natural frequency of tank level behavior.
The following example shows Decompose(3)+Mean() to capture a smooth moving trend of the data.
As illustrated, Decompose(3)+Residual(3) is equal to the original signal.
For information on setting up custom equations and syntax, please refer to Analytical Functions.