Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Power System and Clean Energy》 2017-10
Add to Favorite Get Latest Update

Power Transformer State Assessment Based on Decision Tree Integration Algorithm

LI Wei;SONG Yongqiang;GUO Wendong;SONG Shijun;WANG Jie;Wuzhong Power Supply Company,State Grid Ningxia Electric Power Company;  
Aiming at the difficulties of transformer fault diagnosis and low accuracy of single decision tree classification,this paper proposes a transformer state evaluation method based on the decision tree integration algorithm for auxiliary diagnosis.The system first uses the multi-objective binary coding genetic algorithm to select effective classification features from 14 features of the dissolved gas in transformer, and then uses these features to train a series basis decision tree classifiers, and uses the genetic algorithm to select the decision tree of higher precision to form a strong classifier to improve the classification performance, and finally the system uses the D-S fusion rules to fuse the basis classifiers' results to get the final diagnosis. The simulation results show that the proposed algorithm not only improves the classification performance of the decision tree, but also improves the diagnostic accuracy of power transformer failures and has good practicability.
【Fund】: 国家自然科学青年基金项目(61101249)~~
【CateGory Index】: TM41
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved