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

LinkedIn
Twitter
Twitter link

Machine-based edge platform cuts data costs

29 January, 2019

Siemens has developed a hardware platform for edge applications that captures and processes  manufacturing data at the point of production. Based on an embedded Simatic IPC227E industrial PC, the platform can process large volumes of data from machinery almost in real-time, bridging the gap between local and cloud-based data processing. Siemens says that, by processing large volumes of data in advance and sending only relevant data to the cloud or a company's own IT infrastructure, its Industrial Edge platform will help users to cut the costs of data storage and transmission.

The edge device, which has an enclosed, all-metal housing, is designed for flexible, maintenance-free operation in harsh conditions. It connects directly to automation components at the machine level. It can be commissioned rapidly using pre-installed software. Software applications on the device can be kept up-to-date using functional, feedback-free updates.

The edge device supports protocols that transmit data to Siemens’ MindSphere cloud-based IoT system. In future, it will also support Message Queuing Telemetry Transport (MQTT), allowing the flexible exchange of data with other systems and clouds.

Siemens is using the edge technology itself in a factory in Amberg, Germany, where it manufactures Simatic products. Milling operations on a PCB (printed circuit board) cutting machine in the plant produce a fine dust which can cause the machine’s spindle bearings to jam, leading to unplanned downtime. To prevent this from happening, several of the machine's operating parameters are now analysed using artificial intelligence that detects any anomalies in the spindle behaviour that could indicate the possibility of an impending failure.

Siemens’ rugged edge device can analyse data on or near machinery

This is done by transmitting data picked up by sensors to an edge device where a machine-learning algorithm assesses anomalies in real time. Any rise above a threshold value indicates that the machine might fail soon. The edge application can predict bearing erosion and machine downtime 12–36 hours before a failure occurs. This allows the machine spindle to be changed during the next scheduled service, thus avoiding costly unplanned downtime.




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