Pipeline for machine reading of unstructured maintenance work order records

Conference Publishing

A/Prof Wei Liu

Authors: Yiyang Gao, Caitlin Woods, Tim French, Melinda Hodkiewicz

2020-11-01

Publication

Research Publishing, Singapore

Research Publishing, Singapore. ISBN/DOI: 978-981-14-8593-0

Proceedings of the 30th European Safety and Reliability Conference and
the 15th Probabilistic Safety Assessment and Management Conference
Edited by Piero Baraldi, Francesco Di Maio and Enrico Zio
Copyright ESREL2020-PSAM15 Organizers.

Quality Indicators

Not Peer Reviewed

Relevance to the Centre

Relevant to the work of Theme 1 - Maintenance work order records contain vital information including inspection data, asset health observations and records of work planned and executed. Our challenge is the extraction and tagging of machine-readable text to support calculation of asset performance metrics such as mean time to failure. This paper a text processing pipeline for MWO records. The pipeline has outperformed a base pipeline that uses only POS tags to distinguish between maintenance item, activity, and state in MWO records.

DOI: 978-981-14-8593-0