基于M-LS-SVR的变压器油中溶解气体浓度预测

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1820 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To predict the concentration of dissolved gases in transformer oil, we proposed mixed least square support vector regression (M-LS-SVR) algorithm in this paper. This algorithm combined linear and nonlinear kernel functions as prediction function, the mixed scaling factor was chosen adaptively by real data. The experiment results showed that this method had less prediction error, lower complexity and better generalization ability than those of the current popular methods, such as BP neural network, support vector machine regression (SVR) and least squares support vector machine regression (LS-SVR).

Key words： power transformer dissolved gas analysis concentration prediction least squares support vector machine regression

Published: 13 January 2016

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Li Hongchao
	Wang Weigang
	Dong Xuemei

Cite this article:

Li Hongchao,Wang Weigang,Dong Xuemei. Concentration Prediction of Dissolved Gases in Transformer Oil based on M-LS-SVR[J]. Electrical Engineering, 2016, 17(1): 76-80.

URL:

http://dqjs.cesmedia.cn/EN/Y2016/V17/I1/76

[1] 张公永, 李伟. 基于灰色最小二乘支持向量机的变压器油溶解气体预测[J]. 电力学报, 2012, 27(2): 111-115.
[2] 任双赞, 曹晓珑, 钟力生. 变压器油中腐蚀性硫对铜导线及油浸绝缘纸特性影响[J]. 电工技术学报, 2011, 26(10): 129-135.
[3] 王学磊, 李庆民, 李成榕, 等. 基于统计分布和相关分析的变压器油中溶解气体注意值计算方法(英文)[J]. 高电压技术, 2013(8): 1960-1965.
[4] 肖燕彩, 陈秀海. 变压器油中故障特征气体体积分数的预测[J]. 中国电力, 2007, 40(3): 53-55.
[5] 张丽萍, 杨柳, 黄锷, 等. 综合灰色模型在电力变压器故障预测中的应用[J]. 陕西电力, 2013, 41(10): 44-47.
[6] 毛自娟. 基于灰色马尔可夫模型的变压器油中溶解气体体积分数预测[J]. 高压电器, 2012, 48(10): 47-51, 57.
[7] 司马莉萍, 舒乃秋, 左婧, 等. 基于灰关联和模糊支持向量机的变压器油中溶解气体浓度的预测[J]. 电力系统保护与控制, 2012, 40(19): 41-46.
[8] 胡导福, 文闪闪, 何益鸣. 基于BP神经网络的变压器故障诊断及其应用[J]. 电力科学与技术学报, 2008, 23(2): 72-75.
[9] 曲朝阳, 计超, 郭晓利, 等. 基于传递函数自我优化的BP网络算法改进[J]. 电测与仪表, 2014, 51(11): 56-59, 64.
[10] Dong Xiucheng, Wang Shouchun, Sun Renjin, et al. Design of artificial neural networks using a genetic algorithm to predict saturates of vacuum gas oil[J]. Petroleum Science, 2010, 7(1): 118-122.
[11] 黄世震, 林淑玲. 基于GSA-BP神经网络的压力传感器温度补偿[J]. 电子器件, 2013, 36(5): 680-684.
[12] 张小奇, 朱永利, 王芳. 基于支持向量机的变压器油中溶解气体浓度预测[J]. 华北电力大学学报, 2006, 33(6): 6-9.
[13] Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: cambridge univer- sity press, 2005.
[14] Xu Yongli, Chen Dirong. Partially-Linear Least- Squares regularized regression for system identifi-
cation[J]. IEEE Transactions on Automatic Control, 2009, 54(11): 2637-2641.
[15] 李方方, 赵英凯, 颜昕. 基于Matlab的最小二乘支持向量机的工具箱及其应用[J]. 计算机应用, 2006, 26(z2): 358-360.