An ontology for maintenance activities and its application to data quality

Maintenance of assets is a multi-million dollar cost each year for asset intensive organisations in the defence, manufacturing, resource and infrastructure sectors. These costs are tracked though maintenance work order (MWO) records. MWO records contain structured data dates, costs, identification unstructured text describing required, example ‘replace leaking pump’. Our focus this paper on quality activity terms (e.g. replace, repair, adjust inspect). We present two contributions paper. First, we propose reference ontology terms. use natural language processing to identify seven core their synonyms from 800,000 MWOs. provide elucidations these Second, demonstrate an application-level using industrial case. The end-to-end NLP-ontology pipeline identifies issues with 55% centrifugal pump over 8 years. For 33% where verb was not provided text, can infer relevant class. selection informed by ISO 14224 15926-4 standards conforms ISO/IEC 21838-2 Basic Formal Ontology (BFO). application ontologies presented here how augment management processes ontological workflows improve quality.