AWS Industrial PdM ML Model with Modbus Communication
Publication date: March 4, 2024 (Diagram history)
With this architecture, you can create a predictive maintenance (PdM) ML model by using AWS IoT SiteWise and AWS IoT Analytics with Amazon Simple Notification Service (Amazon SNS) anomaly detection notifications. This solution uses AWS IoT Greengrass, AWS IoT Core, Amazon Elastic Container Registry, and Amazon Quick Sight.
Industrial PdM ML Modbus architecture diagram
The following steps describe the architecture:
-
Deploy an AWS IoT SiteWise Gateway to connect to factory machines' OPC Unified Architecture (OPC-UA) Servers.
-
Create a view in AWS IoT SiteWise and define factory machines as assets with metrics to monitor.
-
Configure a Modbus Greengrass Connector on AWS IoT Greengrass to send Modbus data to AWS IoT Analytics through an AWS IoT Core rule.
-
Build a Docker image and add it to Amazon ECR.
-
In AWS IoT Analytics, create a container data set from the AWS IoT SiteWise data store linked to your Docker container.
-
Create a Jupyter Notebook for the data set to build a PdM ML model.
-
Visualize analysis with Quick on the AWS IoT Analytics data source.
-
Create a topic for anomaly detection notifications in Amazon SNS and configure the trigger.
For a related reference architecture, see AWS Industrial IoT Predictive Maintenance ML Model.
Further reading
For additional information, see the following resources:
Diagram history
To be notified about updates to this reference architecture diagram, subscribe to the RSS feed.
| Change | Description | Date |
|---|---|---|
Initial publication | Reference architecture diagram first published. | March 4, 2024 |
RSS subscription
To subscribe to RSS updates, you must have an RSS plugin enabled for the browser that you are using.
