Predictive maintenance (also known as ‘condition/health monitoring’) refers to the intelligent monitoring of equipment to avoid future failures. In contrast to conventional preventive maintenance, the maintenance schedule is not determined by a prescribed timeline; instead, it is determined by analytic algorithms, such as machine learning, using data collected from equipment sensors and/or via simulation.
Predictive maintenance offers the following benefits for operators and equipment manufacturers:
– reduces equipment downtime by identifying issues before failure, thereby enabling convenient scheduling of equipment service and extending equipment lifetime
– determines the root cause of the failure, enabling appropriate service to be performed without utilising resources to determine a diagnosis
– avoids the unnecessary costs of maintenance and unexpected failures
– improves safety and product quality.
Algorithms and data are critical to predictive maintenance success. Sensor data is first preprocessed using advanced statistical and signal processing techniques; it is then combined with predictive modelling techniques, such as machine learning, to estimate equipment health.
Once tested, predictive maintenance algorithms may be used in an operational setting within an IT environment, such as a server or cloud. Alternatively, algorithms may be implemented in an embedded system directly on the equipment, allowing for faster response times and significantly reducing the amount of data sent over the network.
Willingham, D and Xie, Y, 2017. Predictive maintenance modelling for bearing-based equipment, in Proceedings Iron Ore 2017, pp 627–630 (The Australasian Institute of Mining and Metallurgy: Melbourne).