互信息和核熵成分分析的油中溶解气体浓度建模

doi:10.6040/j.issn.1671-9352.4.2021.247

摘要/Abstract

摘要： 针对变压器油中溶解气体浓度的预测问题,提出了一种基于互信息和核熵成分分析(KECA)的油中溶解气体浓度预测建模方法。首先,用标准互信息变量选择方法确定模型的输入变量并对选取的输入变量进行相重构;然后,利用Renyi熵信息测度确定KECA核参数并采用KECA对相空间进行特征提取;最后,以核熵成分作为机器学习极限学习机(ELM)的输入,建立变压器油中溶解气体浓度的预测模型。实验结果表明,与灰色模型、支持向量机、BP神经网络建模方法相比,本文提出的方法能够充分利用油中溶解气体浓度信息,因而具有较优的预测精度和泛化能力。

关键词: 油中溶解气体分析, 互信息, 机器学习, Renyi熵, 核熵成分分析, 极限学习机

Abstract: Aiming at the testing problem of dissolved gases concentration in transformer oil, a new prediction modeling method based on mutual information(MI)and kernel entropy component analysis(KECA)was proposed. Firstly, normalized mutual information feature selection method was used to select input variables and the phase reconstruction space were reconstructed for them. Then, feature extraction was carried out in the phase reconstruction space by using KECA, meanwhile, the kernel parameter of KECA was determined by Renyi information entropy. At last, kernel entropy components were extracted by KECA and then they were used as the inputs of extreme learning machine(ELM)which was employed to forecast dissolved gases concentration. Experimental results show that compared with grey model, support vector machine(SVM)and BP neural network(BPNN), the proposed model can sufficiently utilize the dissolved gases information, thus it has a better prediction and generalization.

Key words: dissolved gas-in-oil analysis, mutual information, machine learning, Renyi entropy, kernel entropy component analysis, extreme learning machine

中图分类号:

TP206.3

李颖,张国林. 互信息和核熵成分分析的油中溶解气体浓度建模[J]. 《山东大学学报(理学版)》, 2022, 57(7): 43-52.

LI Ying, ZHANG Guo-lin. Modeling for dissolved gases concentration based on mutual information and kernel entropy component analysis[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2022, 57(7): 43-52.

参考文献

[1] 肖燕彩, 陈秀海. 用灰色多变量模型预测变压器油中气体的方法[J]. 高电压技术, 2007, 33(8):98-101. XIAO Yancai, CHEN Xiuhai. Method for predicting dissolved gases in transformer oil by multivariable grey model[J]. High Voltage Engineering, 2007, 33(8):98-101.
[2] WANG M H. Grey-extension method for incipient fault forecasting of oil-immersed power transformer[J]. Electric Power Components and Systems, 2004, 32(10):959-975.
[3] LIAO Ruijin, ZHANG Hanbo, GRZYBOWSKI S, et al. Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers[J]. Electric Power Systems Research, 2011, 81(12):2074-2080.
[4] FEI Shengwei, SUN Yu. Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm[J]. Electric Power Systems Research, 2008, 78(3):507-514.
[5] 唐勇波, 桂卫华, 彭涛, 等. 基于互信息变量选择的变压器油中溶解气体浓度预测[J].仪器仪表学报, 2013, 34(7):1492-1498. TANG Yongbo, GUI Weihua, PENG Tao, et al. Prediction method for dissolved gases content in transformer oil based on variable selection of mutual information[J]. Chinese Journal of Scientific Instrument, 2013, 34(7):1492-1498.
[6] 龚双双, 陈钰枫, 徐金安, 等. 基于网络文本的汉语多词表达抽取方法[J]. 山东大学学报(理学版), 2018, 53(9):40-48. GONG Shuangshuang, CHEN Yufeng, XU Jinan, et al. Structural extraction of Chinese multiword expressions based on web text[J]. Journal of Shandong University(Natural Science), 2018, 53(9):40-48.
[7] 毛文涛, 蒋梦雪, 李源, 等. 基于异常序列剔除的多变量时间序列结构化预测[J]. 自动化学报, 2018, 44(4):619-634. MAO Wentao, JIANG Mengxue, LI Yuan, et al. Structural prediction of multivariate time series through outlier elimination[J]. Acta Automatic Sinica, 2018, 44(4):619-634.
[8] JENSSEN R. Kernel entropy component analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):847-860.
[9] LI Yangyang, WANG Yang, WANG Yuying, et al. Quantum clustering using kernel entropy component analysis[J]. Neurocomputing, 2016, 202(8):36-48.
[10] BAI Lili, HAN Zhennan, REN Jiajun, et al. Research on feature selection for rotating machinery based on supervision kernel entropy component analysis with whale optimization algorithm[J]. Applied Soft Computing, 2020, 92(1):1-10.
[11] 邓明月, 刘建昌, 许鹏, 等. 基于KECA 的非线性工业过程故障检测与诊断新方法[J]. 化工学报, 2020, 71(5):2151-2163. DENG Mingyue, LIU Jianchang, XU Peng, et al. Novel fault monitoring strategy for chemical process based on KECA[J]. Journal of Chemical Industry and Engineering, 2020, 71(5):2151-2163.
[12] XIA Yudong, DING Qiang, JING Nijie, et al. An enhanced fault detection method for centrifugal chillers using kernel density estimation based kernel entropy component analysis[J]. International Journal of Refrigeration, 2021, 129(2):290-300.
[13] BUI A T, IM J K, APLEY D W, et al. Projection-free kernel principal component analysis for denoising[J]. Neurocomputing, 2019, 357(9):163-176.
[14] TAO Xiaomin, CHANG Rui, LI Chenxi, et al. Density-sensitive robust fuzzy kernel principal component analysis technique[J]. Neurocomputing, 2019, 329(2):210-226.
[15] BATTITI R. Using mutual information for selecting features in supervised neural net learning[J]. IEEE Transactions on Neural Networks, 1994, 5(4):537-550.
[16] PENG H C, LONG F H, DING C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1226-1238.
[17] ESTEVEZ P A, PEREZ M C, ZURADA J M, et al. Normalized mutual information feature selection[J]. IEEE Transactions on Neural Networks, 2009, 20(2):189-201.
[18] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/2/3):489-501.
[19] HUANG Guangbin, ZHOU Hongming, DING Xiaojian, et al. Extreme learning machine for regression and multiclass classification[J]. Systems, Man, and Cybernetics, Part B: IEEE Transactions on Cybernetics, 2012, 42(2):513-529.
[20] 刘彬, 杨有恒, 赵志彪, 等. 一种基于正则优化的批次继承极限学习机算法[J]. 电子与信息学报, 2020, 42(7):1734-1742. LIU Bin, YANG Youheng, ZHAO Zhibiao, et al. A batch inheritance extreme learning machine algorithm based on regular optimization[J]. Journal of Electronics & Information Technology, 2020, 42(7):1734-1742.
[21] 许夙晖, 慕晓冬, 柴栋, 等. 基于极限学习机参数迁移的域适应算法[J]. 自动化学报, 2018, 44(2):311-317. XU Suhui, MU Xiaodong, CHAI Dong, et al. Domain adaption algorithm with ELM parameter transfer[J]. Acta Automatica Sinica, 2018, 44(2):311-317.
[22] KIM H S,EYKHOLT R, SALAS J D. Nonlinear dynamics, delay times, and embedding windows[J]. Physica D, 1999, 127(1/2):48-60.
[23] 张洪宾, 孙小端, 贺玉龙. 短时交通流复杂动力学特性分析及预测[J]. 物理学报, 2014, 63(4):51-58. ZHANG Honbin, SUN Xiaoduan, HE Yulong. Analysis and prediction of complex dynamical characteristics of short-term traffic flow[J]. Acta Physica Sinica, 2014, 63(4):51-58.
[24] REN Ting, LIU Shi, YAN Gaocheng. Temperature prediction of the molten salt collector tube using BP neural network[J]. IET Renewable Power Generation, 2016, 10(2):212-220.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed