Once you have your Phoenix Contact PLCnext Control data flowing to the cloud, it’s time to develop some fast and efficient algorithms and Machine Learning models for real-time processing of the data. Azure Machine Learning empowers us with a wide range of productive experiences for building, training, and deploying machine learning models faster. IoT Ensemble provides out of the box APIs that allow you to easily load your PLCnext data into Azure Machine Learning. But first things first, let’s get our PLCnext Control connected to Microsoft Azure.
Phoenix Contact has a video at https://youtu.be/QST1RpTkdfA that shows how to connect your PLCnext controller to an Azure IoT Hub using a Node.js client. It’s a great video and very informative. However, instead of going through all of the tedious steps outlined in the video of setting up an Azure resource group, the IoT Hub, storage containers, the storage endpoints, and everything else, I prefer to use Fathym’s IoT Ensemble. With one click I can register my PLCnext device and immediately get access to the data for downstream use in alerts, dashboards, visualizations, and machine learning. After I enroll my device in IoT Ensemble, it displays the IoT Hub connectionstring. I take the connectionstring into PLCnext Engineer to use as my Azure Key and I’m ready to rock. Here’s a screenshot of my connected PLCnext Control.
The PLCnext data is immediately flowing to IoT Ensemble and I can view the data on screen. Reminder that behind the scenes in IoT Ensemble the PLCnext data is stored in Microsoft Azure in blob storage, as well as in CosmosDB.
How to access data in Microsoft Azure:
- Behind the scenes in IoT Ensemble the PLCnext data is stored in Microsoft Azure in blob storage, as well as in CosmosDB. Read This to learn more about accessing your data.
Fathym’s IoT Ensemble is providing an easy-to-use UI for interacting with the data instead of using the Azure portal – and it saves me a ton of time and money.
PLCnext Azure Machine Learning
IoT Ensemble provides out of the box APIs that allow you to easily load your PLCnext data into Azure Machine Learning. This IoT Ensemble doc explains how to use IoT Ensemble’s cold query to configure an Azure ML Dataset and an associated Automated ML Task to run your model. Here’s a couple of screenshots.
Sign up for IoT Ensemble and save your company thousands of dollars in Azure setup and management costs. Enroll your first PLCnext Control with IoT Ensemble for free. No credit card required. No Azure account required. It really is that simple.
Leave a Reply
You must be logged in to post a comment.