Monitoring Complex Assets using Patterns in Signal data (MCAPS)

In this project, Cybula, a research intensive SME, will work with EDF's nuclear operating business in the UK and their R&D group in France to further develop and evaluate its' pattern recognition software methods for use as an alerting and diagnostic modelling system to monitor a range of assets. The proposed data modelling approach will use an abnormality detection system (AURAalert) which uses Cybula's optimised search engine to compare current performance of a continuously monitored system against large, reference data containing individual instances of normal performance. A proto-type system was developed as part of a previous TSB nuclear feasibility study. AURAalert will be linked to Cybula's SDE search software so that EDF can search for similar events in archived data across fleets of assets. The project aims to test the system on a range of assets.