摘要：Maintenance management and engineering practice has progressed to adopt approaches which aim to reach maintenance decisions not by means of pre-specified plans and recommendations but increasingly on the basis of best contextually relevant available information and knowledge, all considered against stated objectives. Different methods for automating event detection, diagnostics and prognostics have been proposed, which may achieve very high performance when appropriately adapted and tuned to serve the needs of well defined tasks. However, the scope of such solutions is often narrow and without a mechanism to include human contributed intervention and knowledge contribution. This paper presents a conceptual framework of integrating automated detection and diagnostics and human contributed knowledge in a single architecture. This is instantiated by an e-maintenance platform comprising tools for both lower level information fusion as well as for handling higher level knowledge. Well structured maintenance relationships, such as those present in a typical FMECA study, as well as on the job human contributed compact knowledge are exploited to this end. A case study presenting the actual workflow of the process in an industrial setting is employed to pilot test the approach.
