Icon

02_​Time_​Series_​AR_​Training

Anomaly Detection. Time Series AR Training

This workflow trains an auto-regressive model to predict signal values. Only time series values from normal functioning conditions are used to train the model.

- Read 313 spectral amplitudes time series produced by the Pre-processing/Time Alignment & Visualization workflow - define training set with only normal data (till August 2007) - For each frequency bin, for each sensor, for each motor part: - train auto-regressive model on training set (Lag = 10) - write PMML model (313 models) Anomaly Detection: Time Series AR TrainingThis workflow trains an auto-regressive model to predict signal values. Only time series valuesfrom normal functioning conditions are used to train the model. Learn "normality" with a linear auto-regressive modelsfor each partfor each sensorfor each frequency bandNode 324 Learn "normal" Read IOTTraining Data - Read 313 spectral amplitudes time series produced by the Pre-processing/Time Alignment & Visualization workflow - define training set with only normal data (till August 2007) - For each frequency bin, for each sensor, for each motor part: - train auto-regressive model on training set (Lag = 10) - write PMML model (313 models) Anomaly Detection: Time Series AR TrainingThis workflow trains an auto-regressive model to predict signal values. Only time series valuesfrom normal functioning conditions are used to train the model. Learn "normality" with a linear auto-regressive modelsfor each partfor each sensorfor each frequency bandNode 324 Learn "normal" Read IOTTraining Data

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: 2019-10-03
Last update: 2026-01-06
Created with KNIME version: v4.0.2

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

Try NodePit Runner!