Industrial Internet of Things (IIoT) Journey – Reducing Scrap:
A large North American plant we work with had to reduce the amount of scrap they were generating to 2%.
Not an easy task, right?
By using Azure Machine Learning we helped them to create models with historical sensor data, which were then used on real-time sensor data to predict scrap.
HOW?
We worked with them to build a predictive machine learning solution with Azure Machine Learning, Azure IoT Hub, Azure Stream Analytics, and Power BI. Azure Iot Hub consolidates sensor data from an on-premises system. Azure Stream Analytics formats data for storage and passes it to Azure Machine Learning for prediction modeling. Then Power BI displays real-time production dashboards of sensor data and live prediction results to operators.
As you read this, these solutions are live in one plant and are being rolled out to a second. The remaining three U.S. plants will follow.
Once this solution is rolled out to all five plants, this customer expects to save $2 million at EACH PLANT annually through predictive scrap reduction. They are already seeing 6-7% increase in yield at the first plant.
We got our 2%.
Check out our case study in this video: