Predictive maintenance minimizes downtime and optimizes periodic maintenance by moving from scheduled to smart maintenance planning, letting the health state of the machine, rather than a periodic time interval, decide when to carry out maintenance.
Traditional predictive maintenance relies on models trained on significant amounts of data including both positive and negative data points (data from well-functioning devices and data including failures). To avoid the need of all that data, Ekkono’s SDK enables predictive maintenance based on health indicators and incremental learning. The incremental approach builds upon the health monitor use case where the learning starts with a short initial training period to determine the normal state of the equipment. The normal state is then used for drawing conclusions about current and future maintenance needs. Working with predictive maintenance gives you the possibility to schedule maintenance well in time to minimize downtime and optimize maintenance efforts.
Time based maintenance results in a non-optimized maintenance of equipment and the risk of missing out on early indications of failure, leading to unscheduled downtime.
Train a machine learning model to be able to predict future system health. Using incremental learning, the result is a personalized predictive maintenance system, tailored to the specific device.
Apply conditions on the predicted future system health to determine if maintenance is required, now or in the near future, triggering automated maintenance alerts.