Integrating plant and process information as a basis for automated plant diagnosis tasks

Effective use of integrated process and plant knowledge may significantly increase the accuracy and reliability of automated plant diagnostics. State-of-the-art diagnosis methods, however, do not exploit the whole richness of information found in process facilities mainly due to the difficulties entailed for its collection and timely retrieval. In an effort to contribute towards the exploitation of such knowledge, this paper presents concepts to classify, integrate, and facilitate the access to relevant data as a basis for automated plant diagnosis tasks. The proposed integration is based on the Formalized Process Description Guideline VDI/VDE 3682 and comprises four fundamental information sources, namely plant connectivity, plant dimension specific-, plant component specific-, and process specific-knowledge. The resulting model is described in the data format CAEX/AutomationML, which allows for seamless and effective information exchange among different diagnostic tools. Further concepts for data access and visualization are presented in this contribution.