Nonlinear Model block

Description

This block implements a nonlinear model, which is a type of model able to learn by a process of trial and error. When constructing a blueprint, the nonlinear model must first be trained and tested before it can be implemented into the blueprint.

The Nonlinear Model block is used for prediction of targets, compared to the Nonlinear Classification Model which is used for classification of targets.

The Nonlinear Model block differs from the Nonlinear Classification Model only in the output values:

The Nonlinear Model block output is a double data type, thus an output of numerical value, whereas
The Nonlinear Classification Model output is a string data type, used to classify the target into discrete classes.

Go to instructions on training the model

Return to Overview of blocks

diagram of a Nonlinear model block

Block Type

Rules and Models block

Input port

The block contains one input port, that must contain double type input fields.

In order for this block to run, the model must first be trained and the input port must contain exactly the same number of fields and field names that were used when it was trained.

Output port

The output port of the block contains the output field(s) of the Nonlinear Model block, which is double type data, providing a numerical value as the model output. The output field name(s) can be modified in the block configuration.

The Nonlinear Model block differs from the Nonlinear Classification Model only in the output values:

The Nonlinear Model block output is a double data type, thus an output of numerical value, whereas
The Nonlinear Classification Model output is a string data type, used to classify the target into discrete classes.

Functions performed on tags

On the Values: The input values are sent through the nonlinear model and the calculated output value(s) of the model are placed in the output fields.
On the Timestamp - The timestamp of the output fields will be set to the newest time stamp of the input fields.
On the Quality: If any one of the input values is of bad quality, the output value(s) will also be of bad quality. If the Enable Input Range Validation box is checked, then the output will be set to bad quality if any of the input values are not within the range of the input minimum and maximum of the data on which it was trained.

Return to top