Incidents detected by the Rule Detector

An ML model element based on the Rule Detector consists of one or several diagnostic rules. Each diagnostic rule results in a value of an indicator tag that is calculated at each point in time. The name and description of the indicator tag represent the purpose of the diagnostic rule, for example, Sensor X failure, Dirty turbine blades, and Rotor speed drop. You can interpret the values of an indicator tag as follows:

• The value 0 was received. The diagnostic rule was not triggered or applied at this moment.
• The value 1 was received. The diagnostic rule was triggered at this moment.
• Intermediate values from 0 to 1 are possible in individual cases. The diagnostic rule was partially triggered at this moment.

Whenever the value of an indicator tag reaches the threshold defined for a diagnostic rule (normally equal to 1), the Rule Detector registers an incident. The indicator tag is displayed in the incidents table in the Incidents section. For each incident registered by the Rule Detector, the application automatically creates the "Tags for event #N" preset, which is available in the History section. This preset includes the indicator tag that invoked the incident, and the tags that are included in the corresponding diagnostic rule.

To display the graphs of indicator tags, you can enable display of predicted tag values in the History section.