Dissolved gas analysis method based on novel feature prioritisation and support vector machine

Created by W.Langdon from gp-bibliography.bib Revision:1.4215

  author =       "Chenghao Wei and Wenhu Tang and Qinghua Wu",
  journal =      "IET Electric Power Applications",
  title =        "Dissolved gas analysis method based on novel feature
                 prioritisation and support vector machine",
  year =         "2014",
  month =        sep,
  volume =       "8",
  number =       "8",
  pages =        "320--328",
  keywords =     "genetic algorithms, genetic programming, SVM",
  DOI =          "doi:10.1049/iet-epa.2014.0085",
  ISSN =         "1751-8660",
  abstract =     "Dissolved gas analysis (DGA) has been widely used for
                 the detection of incipient faults in oil-filled
                 transformers. This research presents a novel approach
                 to DGA feature prioritisation and classification, which
                 considers not only the relations between a fault type
                 and specific gas ratios but also their statistical
                 characteristics based on data derived from on site
                 inspections. Firstly, new gas features are acquired
                 based on the analysis of current international gas
                 interpretation standards. Combined with conventional
                 gas ratios, all features are then prioritised by using
                 the Kolmogorov-Smirnov test. The rankings are obtained
                 by using their values of maximum statistic distance.
                 The first three features in ranking are employed as
                 input vectors to a multi-layer support vector machine,
                 whose tuning parameters are acquired by particle swarm
                 optimisation. In the experiment, a bootstrap technique
                 is implemented to approximately equalise sample numbers
                 of different fault cases. A common 10-fold
                 cross-validation technique is employed for performance
                 assessment. Typical artificial intelligence classifiers
                 with gas features extracted from genetic programming
                 are evaluated for comparison purposes.",
  notes =        "Dept. of Electr. Eng. & Electron., Univ. of Liverpool,
                 Liverpool, UK

                 Also known as \cite{6894472}",

Genetic Programming entries for Chenghao Wei Wenhu Tang Qinghua Wu