DocumentCode :
1886057
Title :
Damage Identification for Transmission Tower Based on Support Vector Machine and RBF
Author :
Liu Chun-cheng ; Liu Jiao ; Tang Biao
Author_Institution :
State Key Lab. of Coastal & Offshore Eng., Dalian Univ. of Technol., Jilin, China
fYear :
2010
fDate :
25-26 Dec. 2010
Firstpage :
1
Lastpage :
4
Abstract :
Transmission tower occupies an important position in the event of transmission of electricity. The failure of transmission tower would cause serious economic losses. As a damage identification parameter, variation ratio of curvature mode has a great ability to damage location. In the field of damage location identification on transmission tower, variation ratio of curvature mode achieved good results even in the condition of tiny damage such as 1%. Support vector machine, as new machine learning algorithm, has shown its superiority of the ability of regression in the fields of damage identification. In this paper, the method of least squares support vector machine is applied to study on the damage extent identification of transmission tower. It is found that this method can extremely approach the targets even under the condition of little sample and it has accurate ability of damage extent identification.
Keywords :
learning (artificial intelligence); least squares approximations; poles and towers; power transmission economics; radial basis function networks; support vector machines; RBF; damage extent identification; damage identification parameter; economic loss; electricity transmission; least squares support vector machine; machine learning; radial basis function; transmission tower; Artificial neural networks; Finite element methods; Mathematical model; Poles and towers; Support vector machines; Training; Vibrations;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Engineering and Computer Science (ICIECS), 2010 2nd International Conference on
Conference_Location :
Wuhan
ISSN :
2156-7379
Print_ISBN :
978-1-4244-7939-9
Electronic_ISBN :
2156-7379
Type :
conf
DOI :
10.1109/ICIECS.2010.5677704
Filename :
5677704
Link To Document :
بازگشت