Variance measures how far the data is from the mean.
A small variance indicates that the values are closer to the mean and to each other, versus a high variance indicates that the values are spread out further from the mean and from each other. The square root of the variance results in the standard deviation.
A variance of zero indicates that all the values are identical. Variance is always non-negative.
The following equations are used, where xi from i=1 to N represents the sensor values, from the current value and back N periods.
where
Parameter | Description |
---|---|
Input Data* | Defines the time series data fed into the function. This can be a sensor ID or another function. |
Period | Number of data intervals considered in the function |
*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:
Var(12) - Outputs the Variance of the previous 12 data points for the current data stream.
Var(Sensor('Tank_A'),24) - Outputs the Variance of the previous 24 data points for the Tank_A sensor.
Examples Reference Chart:
The following example shows measured discharge pressures along with a smoother WMA(12) function, and their respective measures of deviation.
The bottom panel shows Variance for the two data streams over the previous 12 points. Obviously, the WMA signal has smaller Variance values. Large steps in pressure from pumps turning on and off result in spikes in Variance.
The StdDev in the middle panel shows the same trends as Variance, since StdDev is the square root of variance. Variance has a greater contrast between spikes and normal noise; for this reason it is more commonly used for deviation alert thresholds rather than StdDev.
For information on setting up custom equations and syntax, please refer to Analytical Functions.