Traditional anomaly detection AI models are outlier detection models.
They're similar to a check engine light in that they explain that there is an anomaly, but they do very little to help explain what the anomaly actually is, which results in users needing to explore their data to find the cause of the alert.
Value Predicting Models instead try to predict what the status of the system should be, given the data it has available.
For instance, if you're running this on a machine with vibration, power and temperature monitoring, it tries to estimate what each of these values should be based on each-other, and on the overall state of the system around it (ie. ambient conditions, current product, load on the conveyor etc.).
By comparing these predicted values against the actual values, we can then see when there are discrepancies. If these discrepancies are large enough, we not only detect an anomaly, but we can show which specific sensor values are incorrect - for example, the temeprature being too high for the current motor load and ambient conditions.
These sorts of models are ideal for when the assets….
To be able to predict values, they need enough information about the wider process to be able to make those predictions. If that data isn't available - or doesn't capture important factors the system would need - then it won't be possible to build useful AI models.
The addon allows you to adjust the tolerance for each of the individual values it compares between the model and the real-world asset.
Some properties may be erratic, unimportant or perhaps can't be predicted accurately - you can use the tolerance settings to effectively ignore those properties and instead focus tightly on others, like vibration, temperature and sound level.
If the difference between the predicted value and the actual value exceeds the tolerance, the AI will raise an alert about the asset.
The AI Anomaly Detector addon uses two different styles of AI to provide this type of anomaly detection. See the differences between model types for more information.