Asset Management Automation Predictive Maintenance Reliability Sensors

Predictive Maintenance Explores Edge Computing

Grant Gerke | July 27, 2018

Image shows a crosscutting functions across edge computing architectures via the Industrial Internet Consortium.

Changing asset management processes and technology for an established manufacturer can seem like running two marathon races. The good thing about recent digital solutions is the ability to add to existing legacy equipment, with no need rip-and-replace.

And, many end users are adopting agile project approaches in rolling out new digital outcomes.

>> Related Content | White Paper: Introduction to Edge Computing in IIoT

Then there’s cloud or edge computing. Edge-computing perception may trigger images of climbing Pike’s Peak without gear, but many suppliers like Paris, France-based Schneider Electric are offering compact solutions to enable edge or cloud processing.

The definition of edge computing is simple.

According to the Needham, Mass-based Industrial Internet Consortium, “edge computing is a decentralized computing infrastructure in which computing resources and application services can be distributed along the communication path from the data source to the cloud. That is, computational needs can be satisfied ‘at the edge,’ where the data is collected, or where the user performs certain actions.”

The big difference between the edge and cloud computing is where the machine modeling or processing is done. An edge processing application allows all the machine or equipment data to stay in the field or the “edge” and not push a huge stream of data to the cloud for analytics.

In the case of Schneider-Electric’s oil and gas solution, the updated Realift Rod Pump controller allows developers to run predictive analytics in either the cloud or at the edge.

“IoT edge provided an easy way to package and deploy our machine learning application,” says Matt Boujonnier, analytics application architect at Schneider Electric. Traditionally, machine learning is something that has only run in the cloud, but for many IoT scenarios that isn’t good enough, because you want to run your application as close as possible to any events. Now we have the flexibility to run it in the cloud or at the edge or wherever we need it to be.”

For the machine learning component, Schneider Electric relies on Redmond, Wash.-based Microsoft’s Azure Machine Learning and Azure IoT Edge. Basically, the platforms allow you to run custom logic on your devices — such as the Deschutes Brewery application here. In the case of Schneider Electric’s oil and gas solution, the controller is promoting predictive analytics to reduce trips to shale and traditional oil fields.

The white paper, above, from the Industrial Internet Consortium has many case studies and this prefaces the section.

“When clouds were first introduced, the trend was to ‘shift everything into the cloud,’ but, due to network latency and the cost to transmit a large amount of data, more logical tasks remained at the edge. With the improvement of the processing power and capability, the amount of tasks performed on the edge will continue to grow.

Below is an example of predictive maintenance application:

A connected elevator uses many sensors for gathering data on noise, vibration, temperature, etc. The operational status of the elevator can then be derived from analyzing the sensed data. With elevators connected to edge computing devices, and the sensed data uploaded to the cloud, elevator operators can obtain the running status of all of their elevators. Elevator technicians are then able to perform predictive maintenance using edge computing data, and data in the cloud, to check and maintain those elevators selectively that are more likely to fail based upon analytics

>> White Paper: Introduction to Edge Computing in IIoT

FEATURED VIDEO

CURRENT ISSUE

EP1807cover

ABOUT THE AUTHOR

Grant Gerke

Grant Gerke

View Comments

Sign up for insights, trends, & developments in
  • Machinery Solutions
  • Maintenance & Reliability Solutions
  • Energy Efficiency
Return to top