Data Selection Criteria for the Application of Predictive Maintenance to Centrifugal Pumps

The maintenance of vehicles and components is present inmost people’s daily lives, ranging from changing a privatevehicle’s oil to the failure prediction of an aircraft componentduring flight. Usually, the manufacturer’s maintenancerecommendation is a good solution when the cost is not toohigh, and the real application is used as indicated by the manufacturer.However, this recommendation can turn unfeasiblewhen there is a significant variation in operational conditionsor high maintenance costs. In these cases, the manufacturer’ssuggestion is typically conservative, leading to unnecessarilyhigh costs. Therefore, the challenge is to find the best approachfor optimizing a component’s maintenance, given thesystem in which it is integrated and the associated operationaland environmental conditions. Nevertheless, the available informationon the loads on the component also plays a role inthat choice. This paper proposes to combine case-specific informationwith generic degradation prediction models to obtainan acceptable but also affordable approach. The objectiveis to develop data selection criteria to indicate the parametersthat have a high impact on the failure prediction, in this case,of a generic impeller pump. Subsequently, the approach deliversto the user an indication of the component remaininguseful life using different operational scenarios.