This workflow performs time alignment on different time series. It reads 6 of the original 28 data files containing amplitude values organized by time and frequency (FFT results); calculates average amplitudes for each frequency bin and date; performs time alignment; writes output to a CSV file AlignedData.csv; performs various visualizations.
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.
This workflow applies a previously trained auto-regressive model to predict signal values. The model was trained for normal functioning conditions. After prediction, the first and second level alarms are calculated based on the differences between real values and predicted values.
This workflow detects anomalies just by checking the wandering off of the signal from a band centered around the time series "normal conditions" average and large as 4 times the corresponding standard deviation.