Where has 5G been deployed to enable predictive maintenance?

As a part of the Worcestershire 5G project, Mazak successfully deployed automated remote predictive maintenance. Taking advantage of 5G’s ability to process large amounts of data, the factory is now able to provide real-time analysis of machine status and feed this information to a cloud system. The company’s spindles are usually only removed for corrective maintenance after an issue or failure occurs but with the arrival of 5G, early warning signs of damage are available; this reduces repair costs, as well as downtime. 

The 5GEM project is enabling Vacuum Furnace Engineering to use 5G connected sensors to remotely monitor car vacuum furnace’s performance, state of health and environmental factors in order to streamline their maintenance process. Properly maintaining the furnace is vital to ensure a high-quality bond, but maintenance typically requires the machine to be taken out of service, interrupting production.  With downtime for the manufacturer costing up to £100,000 per day, 5G and a shift to predictive maintenance could have huge financial implications.  The organisation is also using 5G to develop digital twins which can be used to work out solutions to issues without stopping the production line.

vacuum furnace engineering quote

GF Machining in Switzerland is using 5G for predictive maintenance of high-speed milling machines.  The speed and acceleration of the machines means extremely low latency is required and 5G fits the bill. The failure rate of the milling process has been greatly reduced, saving the manufacturer EUR30 million per plant per year as a result. Smart Factory (SKT) has likewise deployed 5G-AI Machine Vision to automatically identify product defects. A 12-megapixel camera takes 24 pictures from various directions and sends them to a cloud server, where AI checks for any defects and filters out defective products with robotic arms; it is able to filter out defective products in less than eight seconds. At Shell, Pernis tests are carried out with UHD cameras and the use of Machine Learning for preventive maintenance. This makes it possible to inspect approximately 160,000 km of pipelines very efficiently and accurately in order to pre-detect and execute necessary maintenance, which ensures inspection of pipelines runs faster and more efficiently.