Visible to the public Rapid labelling of SCADA data to extract transparent rules using RIPPER

TitleRapid labelling of SCADA data to extract transparent rules using RIPPER
Publication TypeConference Paper
Year of Publication2014
AuthorsGodwin, J.L., Matthews, P.
Conference NameReliability and Maintainability Symposium (RAMS), 2014 Annual
Date PublishedJan
KeywordsAccuracy, catastrophic failure, Condition index, condition monitoring, data mining, failure analysis, failure model, Gears, Indexes, Inspection, knowledge based systems, Mahalanobis distance, maintenance engineering, mean kappa statistic, mechanical engineering computing, prognosis, RIPPER rule learner, robust prognostic condition index, Robustness, rule extraction, SCADA data rapid labelling, SCADA systems, supervisory control and data acquisition, wind turbine gearbox degradation, wind turbine SCADA data, wind turbines

This paper addresses a robust methodology for developing a statistically sound, robust prognostic condition index and encapsulating this index as a series of highly accurate, transparent, human-readable rules. These rules can be used to further understand degradation phenomena and also provide transparency and trust for any underlying prognostic technique employed. A case study is presented on a wind turbine gearbox, utilising historical supervisory control and data acquisition (SCADA) data in conjunction with a physics of failure model. Training is performed without failure data, with the technique accurately identifying gearbox degradation and providing prognostic signatures up to 5 months before catastrophic failure occurred. A robust derivation of the Mahalanobis distance is employed to perform outlier analysis in the bivariate domain, enabling the rapid labelling of historical SCADA data on independent wind turbines. Following this, the RIPPER rule learner was utilised to extract transparent, human-readable rules from the labelled data. A mean classification accuracy of 95.98% of the autonomously derived condition was achieved on three independent test sets, with a mean kappa statistic of 93.96% reported. In total, 12 rules were extracted, with an independent domain expert providing critical analysis, two thirds of the rules were deemed to be intuitive in modelling fundamental degradation behaviour of the wind turbine gearbox.

Citation Key6798456