Remaining Useful Life Prediction of Filters in Nuclear Power Plants

Abstract

To function effectively, nuclear power plants rely on the effective filtration of air, water, and process fluids, examples of which include: inlet sea water, reactor coolant, plant drinking water, and moderator purification. Filtration assets degrade over time which impairs their filtering performance and reduces the flow rate. Being able to determine remaining useful life (RUL) of a filter could result in benefits, particularly when moving from a time-based to a condition-based maintenance strategy which would optimize filter replacement procedure and reduce early replacement of filters which are still fit for purpose. For many filter types a time based strategy is sufficient, but for strategically important assets, such as fuelling machines, there are benefits to be gained from the development of predictive maintenance strategies. In this paper we propose a predictive condition-based strategy using differential pressure data as a surrogate for filter health. The key objective in this work was the creation of a model that could predict a filter asset RUL. The differential pressure for 7-14 days is predicted by a heuristic based regression model the history of each filter. This approach has been demonstrated using a civil nuclear generation application, but could but applied to wider applications. While this model is still undergoing on-site evaluation, it has been estimated that the overall lifetime cost reduction, for this specific application, will be operationally significant once this methodology has been implemented on reactor.