Picture of athlete cycling

Open Access research with a real impact on health...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of Open Access research papers by Strathclyde researchers, including by researchers from the Physical Activity for Health Group based within the School of Psychological Sciences & Health. Research here seeks to better understand how and why physical activity improves health, gain a better understanding of the amount, intensity, and type of physical activity needed for health benefits, and evaluate the effect of interventions to promote physical activity.

Explore open research content by Physical Activity for Health...

Rough set theory applied to pattern recognition of partial discharge in noise affected cable data

Peng, Xiaosheng and Wen, Jinyu and Li, Zhaohui and Yang, Guangyao and Zhou, Chengke and Reid, Alistair and Hepburn, Donald M. and Judd, Martin D. and Siew, W. H. (2016) Rough set theory applied to pattern recognition of partial discharge in noise affected cable data. IEEE Transactions on Dielectrics and Electrical Insulation. ISSN 1070-9878 (In Press)

Text (Peng-etal-IEEETDEI2016-Rough-set-theory-applied-to-pattern-recognition-of-partial-discharge)
Peng_etal_IEEETDEI2016_Rough_set_theory_applied_to_pattern_recognition_of_partial_discharge.pdf - Accepted Author Manuscript

Download (941kB) | Preview


This paper presents an effective pattern recognition method, Rough Set (RS), for interference signals rejection and Partial Discharge (PD) signals recognition from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and flowchart of RS based pattern recognition. Secondly, PD testing of five types of artificial defects of ethylene-propylene rubber (EPR) cable are carried out and data pre-processing and feature extraction are employed to generate PD and interference samples. Thirdly, RS based PD and interference signals recognition are presented and are proved with more than 99% accuracy for 4000 samples. Fourthly, RS based PD recognition from different sources are presented and the recognition accuracy of five types of PD signals is more than 93% when certain kinds of signal discretisation and attribute reduction methods combination are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) method are studied and compared with RS theory to further present the advantages and disadvantages of the method. The proposed RS method is proved with higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems if enough training samples of the cable types are generated.