Data fusion/data mining-based architecture for condition-based maintenance

Condition-based maintenance (CBM) is a maintenance philosophy wherein equipment repair or replacement decisions are based on the current and projected future health of the equipment. The constituents and sub-processes within CBM include sensors and signal processing techniques that provide the mechanism for condition monitoring, and decision support models. Since past research has been dominated by condition monitoring techniques for specific applications, the maintenance community lacks a generic CBM architecture that would be relevant across different domains. This paper attempts to fulfil that need by proposing a combined data fusion/data mining-based architecture for CBM. Data fusion, which is extensively used in defence applications, is an automated process of combining information from several sources in order to make decisions regarding the state of an object. Data mining seeks unknown patterns and relationships in large data sets; the methodology is used to support data fusion and model generation at several levels. In the architecture, methods from both these domains analyse CBM data to determine the overall condition or health of a machine. This information is then used by a predictive maintenance model to determine the best course of action for maintaining critical equipment.