How to build an ML Model.

Tutorials → Technology Learning Tutorial → ML.NET Tutorial | Concept | How-to Guide | Reference

This Tutorial Teaches you to:

This tutorial demonstrates how to use machine learning for real-time anomaly detection on sensor data using FrameworX Script Classes.

Prerequisites:

Step 1: Create Tag

  1. In Unified Namespace → Tags create the following tag

Name

Type

Array

AnomalyBuffer

Text

9

Step 2: Create Value Simulator

  1. With these tags created: Pressure (Integer) and AnomalyBuffer (Text Array 9 position)

  2. In Devices → Protocols, select the Value Simulator and click the "New Channel..." button.

  3. In Devices → Points, create points to generate simulated data.

TagName

Node

Address

DataType

AccessType

Tag.Pressure

Node.ValueSimulator1Node1

INTEGER:0,100,1

Native

AccessType.Read

For more information about the Value Simulator, see: Value Simulator Connector

Step 3: Create ML Anomaly Detection Script Class

  1. Navigate to Scripts → Classes

  2. Click the "Create a New Class" button

  3. In "Import code from Library:", select AnomalyML

  4. Open the script and uncomment the line that returns the detection to the AnomalyBuffer tag in Check() method.

Step 4: Create an Expression

This expression will check for anomalies each time the tag value changes.

  1. Go to Scripts → Expressions

  2. Create the following expression:

ObjectName

Expression

Execution


Script.Class.AnomalyML.Check(<DesiredTag>)

OnChange

Where:

  • <DesiredTag> is the tag you want to monitor for anomalies

Example:

ObjectName

Expression

Execution


Script.Class.AnomalyML.Check(Tag.Pressure)

OnChange

Step 5: Test the System

  1. Go in Runtime → “Run Startup”

  2. Wait a couple minutes to have some data in the model.

  3. Open the PropertyWatch

  4. See the values in the AnomalyBuffer, to see the predictions.

In this section...