Feature Extractor
The Feature Extractor processor extracts meaningful patterns and characteristics from raw PLC data, transforming complex data into features that advanced analytic models can easily understand and utilize.
- Let's say you picked a window of N values:
- Minimum: Gives you minimum of N values
- Maximum: Gives you maximum of N values
- Average: Gives you the average(mean) of N values
- Standard Deviation : squareRoot( (x - average)^2/(N-1) )
- Variance : (x - average)^2/(N-1)
- Median : N/2 for odd number of window elements, {[N-1] + [N]}/2 for even window elements
- Kurtosis : [ (N)(N+1) / (N-1)(N-2)(N-3) ] * SIGMA [(x_i - x_avg)/(stdDeviation) ^4]
- Skewness : [ (N) / (N-1)(N-2)] * SIGMA [(x_i - x_avg)/(stdDeviation) ^3]
- Zero crossing rate: Gives you how many times the signal has crossed zero i.e positive value to negative, OR negative value to positive
- Root Mean Square : squareRoot[ SIGMA x^2 / N]
- Quartiles: Divides the signal into 4 equal quartiles, based on medians
- Inter-quartile Range: Difference between the third quartile and first quartile
- Mean Absolute Deviation : abs(x - average)/(N)
- Average absolute variation : abs(x - average)/(N)
- The timer interval parameter is useful if the connected input tag is currently not polling, but you still want this KPI to publish a value every few seconds, defined by the aforementioned timer.
- If you know your input is going to publish at the expected interval, it is better to disable this timer by entering 0 in the field.
Parameters | Details |
---|---|
Window Size | This parameter specifies the window in which to calculate the features, represented in seconds. |
Minimum Maximum Average Standard Deviation Variance Median Kurtosis Skewness Zero Crossing Rate Root Mean Square Quartiles Inter Quartile Range Mean Absolute Deviation Average Absolute Variation | Minimum: It gives the minimum value within the specified window size. Maximum: This parameter gives you the maximum value within the specified window size. Average: It calculates the average (mean) of the values within the window size. Standard Deviation: This parameter computes the standard deviation of the values within the window. Variance: It calculates the variance of the values within the window. Median: This parameter gives you the median of the values within the window. Kurtosis: Kurtosis measures the "heaviness" of the tails of the distribution of values within the window. Skewness: Skewness measures the asymmetry of the distribution of values within the window. Zero Crossing Rate: It determines the number of times the signal crosses zero within the window. Root Mean Square: This parameter calculates the root mean square of the values within the window. Quartiles: It divides the signal into four equal quartiles based on the medians within the window. Inter-Quartile Range: This parameter determines the difference between the third quartile and the first quartile within the window. Mean Absolute Deviation: It calculates the mean absolute deviation of the values within the window. Average Absolute Variation: This parameter calculates the average absolute variation of the values within the window. |
Timer Interval | This parameter allows you to set the timer in milliseconds. It's useful for continuous output display when no event is triggering the expression. |
Pass Through Value | The Pass Through Value parameter enables you to specify how anomalous data should be handled. |
Note: When creating an analytics flow with Feature Extractor processor, refer the Use the Feature Extractor Function guide for more details.