DocumentCode :
1284424
Title :
Statistical Machine Learning and Dissolved Gas Analysis: A Review
Author :
Mirowski, Piotr ; LeCun, Yann
Author_Institution :
Stat. & Learning Res. Dept., Alcatel-Lucent Bell Labs., Murray Hill, NJ, USA
Volume :
27
Issue :
4
fYear :
2012
Firstpage :
1791
Lastpage :
1799
Abstract :
Dissolved gas analysis (DGA) of the insulation oil of power transformers is an investigative tool to monitor their health and to detect impending failures by recognizing anomalous patterns of DGA concentrations. We handle the failure prediction problem as a simple data-mining task on DGA samples, optionally exploiting the transformer´s age, nominal power and voltage, and consider two approaches: 1) binary classification and 2) regression of the time to failure. We propose a simple logarithmic transform to preprocess DGA data in order to deal with long-tail distributions of concentrations. We have reviewed and evaluated 15 standard statistical machine-learning algorithms on that task, and reported quantitative results on a small but published set of power transformers and on proprietary data from thousands of network transformers of a utility company. Our results confirm that nonlinear decision functions, such as neural networks, support vector machines with Gaussian kernels, or local linear regression can theoretically provide slightly better performance than linear classifiers or regressors. Software and part of the data are available at http://www.mirowski.info/pub/dga.
Keywords :
Gaussian processes; data mining; failure analysis; learning (artificial intelligence); neural nets; power engineering computing; power transformer insulation; regression analysis; support vector machines; transformer oil; DGA; Dissolved Gas analysis; Gaussian kernels; anomalous pattern recognition; binary classification; data-mining task; failure detection; insulation oil; local linear regression; logarithmic transform; long-tail distributions; network transformers; neural networks; nonlinear decision functions; power transformers; statistical machine learning; support vector machines; time-to-failure; utility company; Dissolved gas analysis; Oil insulation; Pattern recognition; Power transformers; Predictive models; Statistical analysis; Support vector machines; Artificial intelligence; neural networks; power transformer insulation; prediction methods; statistics; transformers;
fLanguage :
English
Journal_Title :
Power Delivery, IEEE Transactions on
Publisher :
ieee
ISSN :
0885-8977
Type :
jour
DOI :
10.1109/TPWRD.2012.2197868
Filename :
6301810
Link To Document :
بازگشت