How predictive maintenance helps BMW enhance production efficiency

BMW Group is rolling out cloud-based predictive maintenance solutions for its production systems across its global network to enhance their efficiency and sustainability. This technology uses sensors, data analytics and artificial intelligence (AI) to carry out predictive maintenance of systems based on their current condition instead of following a rule-based approach of maintenance at regular intervals.

The predictive approach ensures that there are no unscheduled downtimes in production while also contributing to sustainability of resources by ensuring optimum system availability. The technology works by monitoring equipment and status data to forecast system failures before they actually happen. Data is used to decide when to replace components as a precaution so as to prevent unnecessary downtimes.

This data is provided to the cloud-based system directly from the manufacturing systems which are connected only once, via a gateway, and then constantly transmit data – usually once a second. There are individual software modules within the platform that can be switched on and off flexibly, as needed, to accommodate changing requirements immediately.

Through predictive maintenance, repairs can be carried out more accurately and in a more cost- and resource-efficient way. Extending running times prolongs the service life of tools and systems significantly. For example, systems in mechanical drivetrain production manufacture a conventional engine or casing for an electric motor every minute. To keep them going and in good condition, predictive maintenance uses simple statistical models to detect any anomalies. If discrepancies are found, it issues visual warnings and alerts to inform employees that maintenance is due.

In the bodyshop of the manufacturing facility, welding guns perform about 15,000 spotwelds each per day. Data from welding guns around the world is collected by specially developed software and sent to the cloud to be collated and analysed with the help of algorithms. All the data is displayed on a dashboard for worldwide use to support the maintenance processes.