Technology: Tire makers can ‘edge’ ahead in data analytics

London – Tire makers should look to a new scalable approach to data analysis to overcome current barriers to the creation of a fully information-enabled production environment at their plants.

This is according to Dominique Scheider, strategic account team leader, Rockwell Automation who believes many manufacturers are struggling to deal with the “patchwork of digital assets” at their facilities.

To increase productivity and agility, he notes that major players have adopted smarter plant-floor technologies and are effectively collecting relevant data from intelligent assets. 

That still leaves the major requirement to convert this data “into information that enables people at all levels of the organisation to work smarter and more productively,” said Scheider.

However, a traditional cloud-based approach cannot provide contextualised information quickly enough to support plant processes and staff, the Rockwell expert pointed out.

Instead, he believes that a scalable analytics platform offers an effiective way to distribute actionable intelligence across all levels of the organisation – on the ‘edge’, on-premises or in the cloud.

Edge computing is the practice of processing data near the edge of a network, where the data is being generated, instead of in a centralised data-processing location.

For example, Scheider cites a new analytics solution, which embeds analytics and machine learning capabilities at the ‘edge’ – and closest to the source of the information and plant-level decision makers.

“Delivered on a plug-in appliance, set-up is simple,” he explains. “No rewiring of existing smart sensors is required. Connect Ethernet and wait about five minutes while the solution crawls the industrial network and discovers smart assets.

“As devices are discovered, data is collected, and health and diagnostic dashboards are built and delivered.”

A scalable approach to analytics can have an immediate impact in many areas of tire manufacturing, the automation manager continued. 

This, he forecast, “will become increasingly important in complex applications like mixing and curing, where machine learning can have a dramatic effect on product quality, manufacturing agility and energy efficiency.

“The scalable approach enables tire producers to more deeply engage each level of the organisation in optimising its manufacturing process – from local engineering and maintenance to the top levels of the company. And from the device to the cloud.”