Momentum is building, fast, for smart manufacturing. Here, Enterprise IoT Insights presents five more use cases from leading industrial IoT (IIoT) solutions providers. Also, check out the major new report on the state of smart manufacturing from Enterprise IoT Insights.
1 | DYNAMIC SCHEDULING | OSISOFT | STEEL (ARCELOR-MITTAL)
“ArcellorMittal owns an integrated iron mining facility in Canada with crushing, processing, a railroad and a port. In 2010, it launched a modernisation effort to increase production from 16 million tons to 26-30 million tons.
“Unfortunately, the price of ore plummeted in 2012 and some of the repairs – such as expanding the 54 year old bedrock port to accommodate newer ships – became impractical. It began to use PI System to better orchestrate activities of the the site, by timing railroad shipments to output at the mines or processing facility.
“By 2014, it increased production by 23 million tons. In 2015, it was 26 million tons, without further capital, adding $40 million in revenue. The budget to achieve that through modest software investments would be $75 million”
— Michael Kanellos, industry analyst, OSIsoft
2 | PREDICTIVE MAINTENANCE | TELIT | MACHINERY (MITSUBISHI)
“Mitsubishi Machinery needed an IoT platform that would allow for round-the-clock remote monitoring and reliable access to real-time device data.
“DeviceWISE platform provided the functionality and reliability it needed to power MC Remote 360, a robust production monitoring and support solution designed to provide transparency to machining processes.
“It can now detect problems before customers are even aware. Customers may grant technicians the ability to remotely tunnel into their machine to help resolve issues, upload or download programmes and push software updates.”
— Ricardo Buranello, vice president for IoT factory solutions, Telit
3 | DYNAMIC SCHEDULING | HITACHI | COMPUTERS (HITACHI)
“We make SCADA systems in our factory in Ōmika; these big-box computers, the size of refrigerators, used for supervisory control in power plants.
“They’re made to order. It is a low-volume, high variation game, and the orders always surprised the logic of the production flow. We’d get bottlenecks, our lead times would drag, and our customers would threaten to go elsewhere.
“So we built up a data set and an algorithm; it was the same agile process. The algorithm revealed the bottlenecks, and proposed how to re-sequence the orders, the people, the machines. We cut our the lead times in half. The Ōmika factory served as test-bed for us.”
— Greg Kinsey, vice president, Hitachi Vantara
4 | PREDICTIVE DOWNTIME | PTC | AUTO PARTS (HIROTEC)
Japanese automotive parts supplier HIROTEC is a $1.6 billion business, with 26 facilities in nine countries. It produces 11 million closures and five million exhaust systems each year. The OEM industry for car parts is crowded and competitive. Within this ecosystem, auto manufacturers can pit suppliers against each other to keep prices low. Unplanned downtime is a deal-breaker. One of HIROTEC’s priorities is continuous operations.
It sought to leverage predictive analytics to eliminate unplanned downtime entirely. To do this, it had to mix its IT and OT systems together, without diluting its resources or diverting focus from its core manufacturing priorities. “Historically, manufacturing groups have struggled to collaborate with IT. But we have to learn to work together, even if it means changing the way we work,” says Justin Hester, senior researcher at the company’s IoT laboratory.
HIROTEC appointed PTC to help it to develop and integrate new IoT software with its manufacturing systems. They deployed PTC’s ThingWorx as an on-premise cloud platform in HIROTEC’s data centre, running on HPE’s Gen9 servers, with edge processing functionality running on HPE’s Edgeline servers.
HIROTEC completed three pilots. The first captured and analysed data from eight computer numerical control (CNC) machines in its Detroit plant. The second saw the pair deploy the platform for remote visualisation of an automated exhaust system inspection line, featuring inspection robots, force sensors, laser measurement devices, and cameras.
Through the pilots, HIROTEC gained real-time visibility of its business operations, allowing it to address efficiency and throughput. The solution has also equipped HIROTEC to use machine learning to predict failures in critical systems, like its exhaust system inspection lines, and perform analysis of historical data to understand performance of its facilities.
The firm has seen a 100 per cent reduction in the time it takes to manually inspect production systems, and eliminated its need to invest in new CNC machines by improving the performance of old ones.
5 | PREDICTIVE QUALITY | OSISOFT | SAUSAGES (TYSON)
“At a facility that makes Jimmy Dean sausages, Tyson Meats discovered that some of the finished product was underweight, leading a larger-than-normal amount of giveaway production. It also had to halt the production line for two weeks pursuant to USDA regulations.
“With the PI System, Tyson was able to pinpoint the issue, a process change in ‘zone one’ of the oven. In the Jimmy Dean facility, the yield improvement after six months was 0.1 percent. It doesn’t sound like a lot, but it adds up to over 100 million pounds of sausage. That yield paid for the project itself.”
— Michael Kanellos, industry analyst, OSIsoft
To get a copy of the report, ‘Smart manufacturing: asset management, predictive maintenance, dynamic scheduling, and other use cases’, click here.
Table of Contents
