The University of Sheffield's Advanced Manufacturing Research Centre (AMRC) is a network of world-leading research and innovation centres working with advanced manufacturing companies around the globe to transform industrial and economic performance.
To support this objective, AMRC's machining group analyses a huge amount of data generated by the manufacturing process. But with some queries taking up to 12 minutes to run on the local database, it needed a better way to securely capture and process data.
Amido provided strategic guidance and engineering capabilities to help AMRC's Machining Group understand and deploy cloud-native technologies that would accelerate its innovation drive.
Amido's discovery phase saw us spend time on site to learn about the Machining Group's objectives, processes, challenges and future requirements. We discovered that monitoring was restricted to a LAN-attached PC and an on-premise data warehouse that couldn’t scale with the data acquisition.
As a result, we recommended securely transferring data to the Microsoft Azure Data Lake cloud service.
Moving the data from the manufacturing process into the cloud means it can be stored securely and then structured for analysis. The data can’t be intercepted in transit and it is immediately encrypted by Microsoft Azure.
Amido’s cloud-based solution was shown to be a wholesale replacement of the AMRC Machining Group’s previous telemetry data processing technology, providing the capability to capture, analyse and report on big data insights from across the entire factory floor for the first time.
Data was structured for analysis and machine learning using Azure’s IoT Hub, Stream Analytics, Databricks (Spark), Data Lake Storage and PowerBI.
The secure, scalable, cost-effective solution delivered stronger manufacturing process performance and machine tool diagnostics could predict maintenance of a machine tool or even prevent the failure of a part.
The solution allows the AMRC Machining Group to scale up and down in minutes, meeting demand while remaining cost-effective.
Machine learning can identify anomalies hidden in huge amounts of data that were previously overlooked, predicting machine tool maintenance requirements.
Microsoft Azure ensured data was secure both in transit and while being stored.