FactoryTalk® Analytics™ GuardianAI™ is a machine learning based supervisory application that uses existing plant devices, such as variable-frequency drives, as sensors to monitor the health of components such as pumps, fans, and blowers on a plant floor. It uses device data to establish a baseline signature of each component’s behavior under normal operating conditions. Then, it monitors the components for any deviation from the baseline. Once a deviation is detected, a notification is sent to the user identifying the anomaly. If an anomaly is detected but cannot be identified, FactoryTalk Analytics GuardianAI notifies the maintenance engineer that an unidentified anomaly was detected. The engineer can then investigate the issue, determine the cause of the anomaly, and tag the deviation accordingly. The machine learning engine in FactoryTalk Analytics GuardianAI then trains to identify new anomalies for future encounters. The following diagram illustrates this process and the variation between a known fault and an unknown deviation.
The FactoryTalk Analytics GuardianAI workflow takes a no-code approach to machine learning. As a result, a data scientist is not required to configure, deploy, or use this AI application. It is designed so that OT personnel, such as maintenance engineers, controls engineers, machine operators, and plant managers, can work with FactoryTalk Analytics GuardianAI with minimal training required.
The configuration workflow consists of four steps.
Deploy the FactoryTalk Analytics GuardianAI application on a local Virtual Machine.
Add the device that will act as a sensor.
Provide the identifying information about the component being monitored (pump, fan, blower, or motor).
Training the model to establish the baseline.
FactoryTalk Analytics GuardianAI supports monitoring multiple baselines based on a component's state. Components such as pumps, motors, fans, and blowers on a plant floor can operate under different conditions and processes. FactoryTalk Analytics GuardianAI provides the capability to monitor these varying situations.
NOTE:
State refers to a component's specific operating condition, such as different pressures, flow rates, speed, etc.
FactoryTalk Analytics GuardianAI provides premium integration with the controller to seamlessly read changes in the component’s tags selected during configuration. When a component's tag value in the controller changes, FactoryTalk Analytics GuardianAI automatically creates a new state and starts acquiring the baseline for that specific state. Once the baseline is acquired, FactoryTalk Analytics GuardianAI continuously monitors the component for any deviation in that particular state. FactoryTalk Analytics GuardianAI will automatically switch to the corresponding state based on the change in the controller tags to ensure accurate monitoring.
For example, if a pump operates under different pressures or flow rates, FactoryTalk Analytics GuardianAI will create and monitor baselines for each condition and switch to the appropriate state when the component's operating condition changes to ensure accurate monitoring.
FactoryTalk Analytics GuardianAI provides premier integration with PowerFlex® 755, 755TL,
755TR, 755HiHP, 755TM, 755TS, and 6000T drives to use as sensors to access three-phase current
data for motor current signature analysis. It focuses on anomaly detection and identification
for the following component types: pumps, fans, and blowers. The application is designed to
work with single-drive and motor applications. Given its adaptive nature, FactoryTalk
Analytics GuardianAI can learn process-centric issues and adapt to component types beyond
those listed above. For this use case, the application comes equipped with generic motor
control analytics.
Example of a VFD connected to a motor with direct coupling to a Component
Beyond the classification provided by the maintenance engineers, FactoryTalk Analytics
GuardianAI comes equipped with embedded expertise to detect certain anomaly patterns that are
out of the box, as outlined below.
