Icon

Anomaly Detection on IoT Data

Anomaly Detection. Control Chart

This workflow performs anomaly detection using a control chart:
- Calculate the "normal conditions" as the cumulative average +/- 2 times the corresponding standard deviation
- Raise a 1st level alarm if a sensor exceeds the band for normal conditions on a single frequency band
- Raise a 2nd level alarm if this happens on at least 25% of the frequency bands of all sensors at the same time
- Visualize the 2nd level alarms in a line plot in order to show the 2nd level alarms w.r.t the rotor breakdown
- Trigger an action if a 2nd level alarm is active

Anomaly Detection

This workflow performs anomaly detection using a control chart: - Calculate the "normal conditions" as the cumulative average +/- 2 times the corresponding standard deviation - Raise a 1st level alarm if a sensor exceeds the band for normal conditions on a single frequency band - Raise a 2nd level alarm if this happens on at least 25% of the frequency bands of all sensors at the same time - Visualize the 2nd level alarms in a line plot in order to show the 2nd level alarms w.r.t the rotor breakdown - Trigger an action if a 2nd level alarm is active


mean(alarm 1) across signals at same time if mean(alarm 1) > 0.25 => alarm 2
2nd level alarm
send email
Fire if level 2 Alarm
write alarmPlot.png
Image Writer (Port)
resolve missings with last value
Missing Value
line plots with date on x-axis average alarm on y-axis
Generate LinePlot
Column Appender
Example Control Chart
Column Splitter
learning boundaries and throw 1 if signal is outside of boundaries
1st level alarm
Read AlignedData.csv produced by the preprocessing workflow
CSV Reader

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
On NodePit since: 2025-10-30
Last update: 2025-10-30
Created with KNIME version: v5.8.0
Tags: anomaly detectiontime series analysisIoTInternet of Thingscontrol chartpredictive maintenancesensormanufacturing

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!