The global site of the UK's leading magazine for automation, motion engineering and power transmission
28 March, 2024

LinkedIn
Twitter
Twitter link

IIC testbed will apply machine learning to maintenance

20 September, 2017

The Industrial Internet Consortium (IIC) has launched a testbed project aimed at accelerating machine learning for predictive maintenance in high-volume manufacturing. The Smart Factory Machine Learning for Predictive Maintenance Testbed is being led by the Industrial IoT/Industry 4.0 specialist, Plethora IIoT, and the programmable semiconductor manufacturer, Xilinx. Other companies supplying equipment for the testbed include Bosch Software Innovations, Microsoft and National Instruments.

The testbed will explore machine-learning techniques and evaluate algorithmic approaches for time-critical predictive maintenance. This knowledge will lead to actionable insights, allowing manufacturers to move away from traditional preventative maintenance to predictive maintenance, thus minimising unplanned downtime and optimising system operation.

The ultimate aim is to help manufacturers to boost availability, improve energy efficiency and extend the lifespans of their high-volume CNC manufacturing production systems.

“Testbeds are the major focus and activity of the IIC and its members,” explains IIC executive director, Dr Richard Mark Soley. “We provide the opportunity for both small and large companies to collaborate and help solve problems that will drive the adoption of IoT applications in many industries.

“The smart factory of the future will require advanced analytics – like those this testbed aims to provide – to identify system degradation before system failure,” he adds. “This type of machine learning and predictive maintenance could extend beyond the manufacturing floor to have a broader impact to other industrial applications.”

Technologies developed as part of the IIC predictive maintenance testbed will undergo a pilot trial at an Etxe-Tar factory in Spain.

Plethora IIoT’s team leader, Javier Diaz, points out that downtime can cost manufacturers as much as $22,000 per minute. “Therefore, unexpected failures are one of the main players in maintenance costs because of their negative impact due to reactive and unplanned maintenance action,” he says. “Being able to predict system degradation before failure has a strong positive impact on machine availability: increasing productivity and decreasing downtime, breakdowns and maintenance costs.

“We’re excited to lead this testbed with Xilinx and work alongside some of the leading players in IIoT technologies,” Diaz continues. “This is a unique opportunity to test together machine-learning technologies with those involved in the testbed at different development levels, starting from the lab through production environments, where a real deployment solution is utilised.”

The predictive maintenance testbed will be developed initially in a laboratory setting in Spain, then move into a controlled production environment at the Etxe-Tar plant, also in Spain, before finally being deployed at an unnamed automotive OEM’s manufacturing facility.




Magazine
  • To view a digital copy of the latest issue of Drives & Controls, click here.

    To visit the digital library of past issues, click here

    To subscribe to the magazine, click here

     

Poll

"Do you think that robots create or destroy jobs?"

Newsletter
Newsletter

Events

Most Read Articles