相对变换KPCA的变压器油击穿电压预测建模

doi:10.16182/j.issn1004731x.joss.201805005

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (5): 1657-1664.doi: 10.16182/j.issn1004731x.joss.201805005

相对变换KPCA的变压器油击穿电压预测建模

熊印国

宜春学院物理科学与工程技术学院,江西宜春 336000

收稿日期:2016-06-01 修回日期:2016-08-12 出版日期:2018-05-08 发布日期:2019-01-03
作者简介:熊印国(1974-),男,江西丰城,硕士,讲师,研究方向为复杂工业过程建模,故障诊断等。
基金资助:
国家自然科学基金(51366013)

Prediction Model for Breakdown Voltage of Transformer Oil Based on Relative Transformation and Kernel Principal Component Analysis

Xiong Yinguo

School of Physical Science and Engineering, Yichun University, Yichun 336000, China

Received:2016-06-01 Revised:2016-08-12 Online:2018-05-08 Published:2019-01-03

摘要/Abstract

摘要： 针对变压器油击穿电压的在线测量问题,提出基于相对变换(RT)核主元分析(KPCA)的变压器油击穿电压预测建模方法。分析与击穿电压关联密切的因素,通过相对变换将原始数据空间变换到相对空间,提高数据之间的可区分性;利用KPCA对相对空间进行特征提取,达到降低数据维数、滤除数据噪声、提取数据非线性特征的目的;将KPCA提取的主元变量作为核极限学习机(KELM)的输入,建立变压器油击穿电压预测模型并采用差分进化算法优化模型参数。与RTKPCA最小二乘支持向量机(LSSVM)、RTPCA-KELM和RTPCA-LSSVM方法进行比较,实验结果表明所提出的方法具有良好的预测精度和泛化能力。

关键词: 击穿电压, 相对变换, 核主元分析, 核极限学习机, 差分进化

Abstract: Aiming at the difficulty of measuring the breakdown voltage of transformer oil on line, a new prediction model for breakdown voltage of transformer oil is proposed based on relative transformation (RT) and kernel principal component analysis (KPCA). By analyzing the factors that are closely related to the breakdown voltage, the original data space is converted to the relative data space by relative transformation to improve the distinguishability between data. KPCA is employed in the relative space for the purpose of data dimension reduction, denoising and extracting nonlinear features. Kernel principal components extracted by KPCA are used as the input of kernel extreme learning machine (KELM) to establish the prediction model for breakdown voltage of transformer oil, and the parameters of prediction model are optimized by differential evolution algorithm. Compared with RTKPCA-LSSVM, RTPCA-KELM and RTPCA-LSSVM, the simulation results illustrate that the proposed prediction method has better prediction precision and generalization ability.

Key words: breakdown voltage, relative transformation, kernel principal component analysis, kernel extreme learning machine, differential evolution algorithm

中图分类号:

TP183

熊印国. 相对变换KPCA的变压器油击穿电压预测建模[J]. 系统仿真学报, 2018, 30(5): 1657-1664.

Xiong Yinguo. Prediction Model for Breakdown Voltage of Transformer Oil Based on Relative Transformation and Kernel Principal Component Analysis[J]. Journal of System Simulation, 2018, 30(5): 1657-1664.

参考文献

[1] 申巍, 范廷东, 曹雯, 等. 油纸绝缘简单模型的剩余击穿电压预测[J]. 高电压技术, 2011, 37(4): 910-915.
Shen Wei, Fan Tingdong, Cao Wen, et al.Residual breakdown voltage prediction of simple oil paper insulation model[J]. High Voltage Engineering, 2011, 37(4): 910-915.
[2] 李睿, 曹顺安, 盛凯. BP神经网络用于预测多参数关联变压器油的性能[J]. 计算机与应用化学, 2008, 25(6): 737-740.
Li Rui, Cao Shun’an, Sheng Kai.BP artificial neural network for the prediction of transformer oil performance with multi-parameter correlation[J]. Computers and Applied Chemistry, 2008, 25(6): 737-740.
[3] 王磊, 李桂香, 王元麒, 等. 基于LSSVM的天然气脱 CO₂膜分离在线软测量模型[J]. 系统仿真学报, 2014, 26(8): 1836-1840.
Wang Lei, Li Guixiang, Wang Yuanqi, et al.On-line soft measurement model for CO₂ separating from natural gas membrane separation process based on LSSVM[J]. Journal of System Simulation, 2014, 26(8): 1836-1840.
[4] 石怀涛, 刘建昌, 张羽, 等. 基于相对变换PLS的故障检测方法[J]. 仪器仪表学报, 2012, 33(4): 816-822.
Shi Huaitao, Liu Jianchang, Zhang Yu, et al.Fault detection method based on relative transformation partial least squares[J]. Chinese Journal of Scientific Instrument, 2012, 33(4): 816-822.
[5] 文贵华. 面向机器学习的相对变换[J]. 计算机研究与发展, 2008, 45(4): 612-618.
Wen Guihua.Relative transformation for machine learning[J]. Journal of Computer Research and Development, 2008, 45(4): 612-618.
[6] Shi H T, Liu J C, Xue P, et al.Improved relative- transformation principal component analysis based on Mahalanobis distance and its application for fault detection[J]. Acta Automatica Sinica (S1874-1029), 2013, 39(9): 1533-1542.
[7] 唐勇波, 彭涛, 熊印国, 等. 相对变换主元分析的变压器油击穿电压预测[J]. 仪器仪表学报, 2015, 36(7): 1640-1645.
Tang Yongbo, Peng Tao, Xiong Yinguo, et al.Breakdown voltage prediction method for transformer oil based on relative transformation principal component analysis[J]. Chinese Journal of Scientific Instrument, 2015, 36(7): 1640-1645.
[8] Lee J M, Yoo C, Choi S W, et al.Non-linear process monitoring using kernel principal component analysis[J]. Chemical Engineering Science (S0009-2509), 2004, 59(1): 223-234.
[9] 高智勇, 梁银林, 高建民, 等. 基于集成熵KPCA的复杂机电系统状态监测方法[J]. 计算机集成制造系统, 2015, 21(5): 1327-1333.
Gao Zhiyong, Liang Yinlin, Gao Jianmin, et al.State monitoring of complex electromechanical system based on integrated entropy of KPCA[J]. Computer Integrated Manufacturing Systems, 2015, 21(5): 1327-1333.
[10] Huang G B, Zhu Q Y, Siew C K.Extreme learning machine: theory and applications[J]. Neurocomputing (S0378-7796), 2006, 70(1): 489-501.
[11] 徐嘉明, 张卫强, 杨登舟, 等. 基于流形正则化极限学习机的语种识别系统[J]. 自动化学报, 2015, 41(9): 1680-1685.
Xu Jiaming, Zhang Weiqiang, Yang Dengzhou, et al.Manifold regularized extreme learning machine for language recognition[J]. Acta Automatica Sinica, 2015, 41(9): 1680-1685.
[12] 李新利, 李楠, 孙愉佳, 等. 火焰自由基成像和极限学习机在NOx排放预测中的研究[J]. 系统仿真学报, 2016, 28(5): 1179-1185.
Li Xinli, Li Nan, Sun Yujia, et al.Research on flame radical imaging and extreme learning machine to prediction of NOx emissions[J]. Journal of System Simulation, 2016, 28(5): 1179-1185.
[13] Huang G B, Zhou H, Ding X, et al.Extreme learning machine for regression and multiclass classification[J]. Systems, Man, and Cybernetics, Part B: IEEE Transactions on Cybernetics (S1083-4419), 2012, 42(2): 513-529.
[14] 刘念, 张清鑫, 刘海涛. 基于核函数极限学习机的微电网短期负荷预测方法[J]. 电工技术学报, 2015, 30(8): 218-224.
Liu Nian, Zhang Qingxin, Liu Haitao.Online short-term load forecasting based on ELM with kernel algorithm in micro-grid environment[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 218-224.
[15] 张文专, 龙文, 焦建军. 基于差分进化算法的混沌时间序列预测模型参数组合优化[J]. 物理学报, 2012, 61(22): 5061-5067.
Zhang Wenzhuan, Long Wen, Jiao Jianjun.Parameter determination based on composite evolutionary algorithm for reconstructing phase-space in chaos time series[J]. Acta Physica Sinica, 2012, 61(22): 5061-5067.
[16] 刘增良, 周松林, 周同旭. 基于IDE-WNN的短期风电功率预测及概率评估[J]. 系统仿真学报, 2016, 28(2): 476-482.
Liu Zengliang, Zhou Songlin, Zhou Tongxu.Short-term prediction of wind power based on IDE-WNN and probabilistic evaluation[J]. Journal of System Simulation, 2016, 28(2): 476-482.
[17] 邱晓红, 江阳, 李渤. 分形变异因子修正的差分进化算法[J]. 模式识别与人工智能, 2015, 28(2): 132-138.
Qiu Xiaohong, Jiang Yang, Li Bo.Fractal mutation factor correcting differential evolution algorithm[J]. Pattern Recognition and Artificial Intelligence, 2015, 28(2): 132-138.

相对变换KPCA的变压器油击穿电压预测建模

Prediction Model for Breakdown Voltage of Transformer Oil Based on Relative Transformation and Kernel Principal Component Analysis

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	余伟, 梁恒辉, 罗映. 一种改进差分进化算法的分数阶系统辨识研究[J]. 系统仿真学报, 2021, 33(5): 1157-1166.
[2]	孙灿, 周新宇, 王明文. 一种融合邻域搜索的多策略差分进化算法[J]. 系统仿真学报, 2020, 32(6): 1071-1084.
[3]	梅盼盼, 吴亮红, 张红强, 王慧莹. 含风电电力系统动态经济调度的差分纵横交叉优化[J]. 系统仿真学报, 2020, 32(6): 1179-1187.
[4]	王艳, 丁宇. 动态柔性作业车间优化调度与决策方法[J]. 系统仿真学报, 2020, 32(11): 2073-2083.
[5]	魏铭琦, 张天瑞, 高秀秀, 王淑梅. 基于DA-RKELM算法的光伏发电功率预测方法[J]. 系统仿真学报, 2020, 32(10): 2041-2051.
[6]	董泽, 马宁. 差分量子粒子群算法的分数阶混沌系统参数估计[J]. 系统仿真学报, 2019, 31(8): 1664-1673.
[7]	林雨谷, 王艳. 离散车间能效数据挖掘及调度优化[J]. 系统仿真学报, 2019, 31(12): 2702-2711.
[8]	王杰, 陈彬, 袁鹏, 马亮, 邱晓刚. 数据驱动的最优互惠避碰模型偏好速度研究[J]. 系统仿真学报, 2019, 31(12): 2731-2739.
[9]	徐继亚, 王艳, 严大虎, 纪志成. 融合KPCA与信息粒化的滚动轴承性能退化SVM预测[J]. 系统仿真学报, 2018, 30(6): 2345-2354.
[10]	张静华, 韩璞. 多算法多种群协同优化差分进化算法[J]. 系统仿真学报, 2018, 30(5): 1690-1699.
[11]	周颖, 陈阳, 岳彬. 改进的模型参考自适应在磨矿过程中的应用[J]. 系统仿真学报, 2018, 30(4): 1608-1614.
[12]	孙玉坤, 李曼曼, 黄永红. 基于改进在线核极限学习机的蓄电池SOC预测[J]. 系统仿真学报, 2018, 30(3): 969-975.
[13]	唐勇波, 熊印国. 相对变换主元分析特征提取的变压器故障诊断[J]. 系统仿真学报, 2018, 30(3): 1127-1134.
[14]	陈文杰, 王艳. 离散制造过程生产协同能耗优化调度方法[J]. 系统仿真学报, 2018, 30(11): 4367-4375.
[15]	王田田, 王艳, 纪志成. 基于改进极限学习机的滚动轴承故障诊断[J]. 系统仿真学报, 2018, 30(11): 4413-4420.