Generation of the model predictions (Inference)¶
Select the asset and aspect to write prediction results. The result is added to the selected aspect, which should already be available in IoT asset model.
The inference engine will generate predictions of the quality variable used for the training of the model. The destination aspect must contain variables following variables with the same names as in the quality file used to train the model:
Identifier – variable containing unique values representing serial numbers of parts. These values should have counterparts in the identifiers available in the selected process data.
Target – variable containing target quality feature to train the model.
Tolerance Low – low tolerance limit used for quality acceptance check.
Tolerance High – high tolerance limit used for quality acceptance check.
Select either one of the following modes of inference,
- Single point – Prediction result will be generated at each data point of the selected asset, which meets filtering criteria defining the manufacturing phase used to configure and train the model. The aggregated data used as input for the model to generate prediction will be calculated starting from the first data point of the manufacturing phase.
- Aggregation – The aggregated data will be calculated only one time after completion of the manufacturing phase.
To display the prediction configuration dialog window in the model versions overview, click "Start Prediction".