Kernel-based support vector machines for automated health status assessment in monitoring sensor data
No Thumbnail Available
Identifiers
Publication date
2018-03-01
Advisors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Export
Abstract
This paper presents a novel algorithm to assess the health status in monitoring sensor data using a kernel-based support vector machine (SVM) approach. Today, accurate fault prediction is a key issue raised by maintenance. In particular, automatically modelling the normal behaviour from condition monitoring data is probably one of the most challenging problems, specially when there is limited information of real faults. To overcome this difficulty, a data-driven learning framework based on nonparametric density estimation for outlier detection and ν-SVM for normality modelling, with optimal bandwidth selection, is proposed. A health score based on the log-normalisation of the distance to the separating hyperplane is also provided. Experimental results obtained when analysing the propagation of a critical fault over time in a marine diesel engine demonstrate the validity of the algorithm. The predictions of normality models learned were compared to those of the k-nearest neighbours (kNN) method. Low false positive rates on healthy data and improved prediction capacities are achieved.
Description
Publisher Copyright: © 2017, Springer-Verlag London Ltd.
Keywords
Bandwidth selection , Condition monitoring , Fault prediction , Health status assessment , Kernel density estimator , Machine learning , Normality modelling , Support vector machines , Control and Systems Engineering , Software , Mechanical Engineering , Computer Science Applications , Industrial and Manufacturing Engineering
Type
Citation
Diez-Olivan , A , Pagan , J A , Khoa , N L D , Sanz , R & Sierra , B 2018 , ' Kernel-based support vector machines for automated health status assessment in monitoring sensor data ' , International Journal of Advanced Manufacturing Technology , vol. 95 , no. 1-4 , pp. 327-340 . https://doi.org/10.1007/s00170-017-1204-2