An Application of Decision-Tree-Based Support Vector Machines to Fault Diagnosis for Transformer

Cui-ling Zhang (), Da-zhi Wang, Xue-chen Jiang and Yi Ning
Additional contact information
Cui-ling Zhang: Northeastern University
Da-zhi Wang: Northeastern University
Xue-chen Jiang: Northeastern University
Yi Ning: Northeastern University

A chapter in Proceedings of 20th International Conference on Industrial Engineering and Engineering Management, 2013, pp 473-485 from Springer

Abstract: Abstract Based on the uncertainty of generating mechanism, the complexity of data processing, and the limitations of transformer fault sample data access, the fault diagnosis model is established using the method of Vector projection on Decision-tree-based support vector machines, that combining one-to-rest with rest-to-rest classification can solve the multi-classification problem better currently. The method of Vector projection aiming at N classification problem, just construct (N − 1) SVM classifiers and have no unrecognized sector and the classify process is faster. The classification according to calculate center distance of class and divisibility measure among classes to determine five kinds of fault location of transformer, which has better generalization ability. Test show that this method comparing with traditional three ratio method and neural network increase correct-sentence rat in fault diagnosis, which has better utility value.

Keywords: Decision-tree; Fault diagnosis; Power transformer; Support vector machines; Vector projection (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-40063-6_48

Ordering information: This item can be ordered from
http://www.springer.com/9783642400636

DOI: 10.1007/978-3-642-40063-6_48

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().