A System Engineering Approach to Predictive Maintenance Systems: from needs and desires to logical architecture

Predictive maintenance is an important field of research to determine the exact moment to trigger maintenance actions. Despite the potential benefits of predictive maintenance in terms of maintenance cost reduction and safety improvement, its implementation faces many shortcomings. One of the main shortcomings is the lack of a systematic approach to developing predictive maintenance systems. Existing generic architectures like OSA-CBM remain insufficient to address all requirements for new systems. A systems engineering approach starting from the needs and desires obtained from the stakeholders until a logical architecture is a potential solution. Specific analysis on the needs and desires is used to elicit, classify and prioritize the requirements for an easier transition to designing the systems architecture. The architecture process builds on the ARCADIA method.