As billions of new and legacy devices become connected in the Internet of Things (IoT), manufacturers need solutions that make sense of disparate data sources and deliver a holistic picture of factory health to solve key challenges and generate new revenue streams. In his blog post below, Robin Martin, VP Technology and Manufacturing Group, GM Assembly Test Manufacturing at Intel, writes about a pioneering pilot for manufacturing that powerfully demonstrates how companies can use IoT and big data analytics to implement cost-saving tools like predictive maintenance that can revolutionize factory productivity. ~ David McKinney
IoT and big data analytics bring tremendous automation potential to the factory. With big data technology, we can merge and correlate rapidly growing data sets—which can lead to real-time responses and increased margins, productivity, and efficiency. Manufacturers, in particular, want to continuously improve output while reducing costs and responding to fluctuating customer demands. Whether you’re building cars or widgets, you can use IoT and big data analytics—supported by higher compute performance, open standards, the availability of industry know-how, and the influx of highly skilled data statisticians—to improve product quality, gain insights into root causes of manufacturing issues, increase throughput, and reduce machine failures and downtime. At Intel, smart factories—and the productivity efficiencies they can deliver to customers—are a key focus. In 2013, Assembly and Test Manufacturing (ATM) decided to pilot the use of Internet of Things and big data analytics to improve efficiency in our own factories.
“We had hundreds of employees engaged across our manufacturing network that were using these Internet of Things building blocks to solve other problems across our manufacturing world. And really what [the pilot] unleashed is a power of innovation and creativity that I’ve never seen.” – Frank Jones, VP Operations and Group Marketing, Internet of Things Group
ATM is an Intel network of state-of-the-art factories that assemble and test millions of units for our customers each year. The scale and complexity of our operations requires decisions to be made with indicators that can be constantly improved and made available in real time. In this high-volume, high-mix manufacturing environment with thousands of tools and parameters, clear visibility of the shop floor with a strong tie-in to supply chain and resources planning is critical for success.
Before we implemented this pilot, visibility into production issues was highly fragmented. We could make improvements to individual pieces and parts of the manufacturing process, but it was difficult to get a complete, integrated view of the issues. This pilot allowed us to make a dramatic shift: We now have a scalable end-to-end solution with real-time indicators to act on, which makes it possible to get the most out of our equipment and helps our factories be more efficient and productive. These new efficiencies are forecasted to save us millions of dollars annually. Furthermore, it’s an excellent example of Intel collaborating with the ecosystem on available components, including gateways, servers, big data solutions, and analytics software:
An Intel® Atom™ processor-based gateway by Mitsubishi Electric, called the Mitsubishi Electric C Language Controller of MELSEC-Q series*, is used to aggregate and securely ingest data into the big data analytics server.1 Read more about this collaboration »
The PowerEdge* VRTX was selected to host the big data and analytics software in a private cloud setting as an on-premise server.2
Big data: Cloudera
Cloudera Enterprise Data Hub* offers a unified platform for big data by providing one place to store, process, and analyze all of their data.3
Analytics: Revolution R Enterprise* from Revolution Analytics
The software provides a seamless, secure data bridge between analytics solutions and enterprise software, thereby solving a key integration problem faced by businesses adopting R-based analytics alongside existing IT infrastructure.4
We know that no single company can create the Internet of Things. By working together, we are truly making great strides. I couldn’t agree more with Frank’s closing remarks from the video above:
“We’re just at the beginning of what [IoT and big data] can help us do in our own manufacturing. I believe other industries will be able to do the same and I think we have unleashed a whole new generation of innovation.”
Read our whitepaper to learn all the details: Optimizing Manufacturing with the Internet of Things.