集合经验模态分解主成分分析分解消噪下的支持向量机组合模型预测

doi:10.11772/j.issn.1001-9081.2015.03.766

计算机应用 ›› 2015, Vol. 35 ›› Issue (3): 766-769.DOI: 10.11772/j.issn.1001-9081.2015.03.766

集合经验模态分解主成分分析分解消噪下的支持向量机组合模型预测

桑秀丽^1,2, 肖清泰^1,2, 王华^1,2, 韩继光^3,4

1. 昆明理工大学质量发展研究院, 昆明 650093;
2. 省部共建复杂有色金属资源清洁利用国家重点实验室(昆明理工大学), 昆明 650093;
3. 云南农业大学机电工程学院, 昆明 650093;
4. 昆明理工大学土木工程学院, 昆明 650500

收稿日期:2014-10-10 修回日期:2014-11-14 出版日期:2015-03-10 发布日期:2015-03-13
通讯作者: 韩继光
作者简介:桑秀丽(1980-),女,山东泰安人,教授,博士,主要研究方向:数据挖掘;肖清泰(1989-),男,山东菏泽人,硕士研究生,主要研究方向:数据挖掘;王华(1965-),男,湖北咸宁人,教授,博士生导师,博士,主要研究方向:质量工程;韩继光(1977-),男,山东临沂人,讲师,博士研究生,主要研究方向:数学模型
基金资助:
国家自然科学基金资助项目(51406071,71363249);云南省科技支撑项目(KKSTJ201358015);云南省教育厅重点基金资助项目(2012Z101)

Support vector machine combined model forecast based on ensemble empirical mode decomposition-principal component analysis

SANG Xiuli^1,2, XIAO Qingtai^1,2, WANG Hua^1,2, HAN Jiguang^3,4

1. Quality Development Institute, Kunming University of Science and Technology, Kunming Yunnan 650093, China;
2. State Key Laboratory of Complex Nonferrous Metal Resources Clear Utilization (Kunming University of Science and Technology), Kunming Yunnan 650093, China;
3. Faculty of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming Yunnan 650093, China;
4. Faculty of Civil Engineering and Mechanics, Kunming University of Science and Technology, Kunming Yunnan 650500, China

Received:2014-10-10 Revised:2014-11-14 Online:2015-03-10 Published:2015-03-13

摘要/Abstract

摘要：

针对工业现场间歇性非平稳时间序列中的特征提取与状态预测问题,提出了一种基于集合经验模态分解(EEMD)、主成分分析(PCA)和支持向量机(SVM)的预测新方法。首先,利用EEMD算法对间歇性非平稳时间序列进行多时间尺度分析,得到一组不同尺度的本征模函数(IMF)分量;然后,基于"3σ"原则估计噪声能量,自适应确定累计贡献率,利用PCA算法去除IMF中存在的噪声,降低特征维数和冗余度;最后,在确定SVM关键参数的基础上,以主分量作为输入变量预测未来。实例测试效果显示:平均绝对误差(MAE)、均方误差(MSE)、平均绝对误差百分比(MAPE)和均方误差百分比(MSPE)分别为514.774,78.216,12.03%和1.862%。实验结果表明:风能场输出功率时间序列经过EEMD算法和PCA算法的进一步消去噪声处理,在抑制混频现象发生的同时降低了非平稳性,使得最后进行SVM预测的精度较未经PCA处理更高。

关键词: 间歇性非平稳时间序列, 集合经验模态分解, 主成分分析, 支持向量机, 组合模型预测

Abstract:

To solve the problem of feature extraction and state prediction of intermittent non-stationary time series in the industrial field, a new prediction approach based on Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA) and Support Vector Machine (SVM) was proposed in this paper. Firstly, the intermittent non-stationary time series was analyzed by multiple time scales and decomposed into a couple of IMF components which possessed the different scales by the EEMD algorithm. Then, the noise energy was estimated to determine the cumulative contribution rate adaptively on the basis of 3-sigma principle. The feature dimension and redundancy were reduced and the noise in IMF was removed by using PCA algorithm. Finally, on the basis of the determining of SVM key parameters, the principal components were regarded as input variables to predict future. Instance's testing results show that Mean Average Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE) and Mean Squared Percentage Error (MSPE) were 514.774, 78.216, 12.03% and 1.862%, respectively. It is concluded that the SVM prediction of the time series of output power of wind farm possesses a higher accuracy than not using PCA because the frequency mixing phenomena was inhibited, the non-stationary was reduced and the noise was further eliminated by EEMD algorithm and PCA algorithm.

Key words: intermittent non-stationary time series, Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA), Support Vector Machine (SVM), combination model forecast

中图分类号:

桑秀丽, 肖清泰, 王华, 韩继光. 集合经验模态分解主成分分析分解消噪下的支持向量机组合模型预测[J]. 计算机应用, 2015, 35(3): 766-769.

SANG Xiuli, XIAO Qingtai, WANG Hua, HAN Jiguang. Support vector machine combined model forecast based on ensemble empirical mode decomposition-principal component analysis[J]. Journal of Computer Applications, 2015, 35(3): 766-769.

参考文献

[1] FAN J, YAO Q. Nonlinear times series[M]. Beijing: Higher Education Press, 2011:1-6.(范剑青,姚琦伟.非线性时间序列——建模、预报及应用[M].北京:高等教育出版社, 2011:1-6.)
[2] ZHU X, WANG Z, LI Y, et al. A hybrid short-term load forecasting method combined with LS-SVM and BP neural network based on EEMD[J]. Mathematics in Practice and Theory, 2012,42(8):151-158.(朱祥和,王子琦,李严,等. 基于EEMD的LS-SVM和BP神经网络混合短期负荷预测[J].数学的实践与认识,2012,42(8):151-158.)
[3] WANG W, FEI P, YI X. Prediction of China stock market based on EMD and neural network[J]. Systems Engineering Theory and Practice, 2010,30(6):1027-1033.(王文波,费浦生,羿旭明.基于EMD与神经网络的中国股票市场预测[J]. 系统工程理论与实践, 2010,30(6):1027-1033.)
[4] XU X, XU G, WANG X, et al. Empirical mode decomposition and its application[J]. Acta Electronica Sinca, 2009,37(3):581-585.(徐晓刚,徐冠雷,王孝通,等.经验模式分解(EMD)及其应用[J].电子学报,2009,37(3):581-585.)
[5] DOU D, LI L, ZHAO Y. Fault diagnosis of rolling bearings using EEMD-Renyi entropy and PCA-PNN[J]. Journal of Southeast University: Natural Science Edition, 2011,41(S1):107-111.(窦东阳,李丽娟,赵英凯.基于EEMD-Renyi熵和PCA-PNN的滚动轴承故障诊断[J].东南大学学报:自然科学版,2011,41(S1):107-111.)
[6] WANG W, ZHANG X, WANG X. Empirical mode decomposition de-noising method based on principal component analysis[J]. Acta Electronica Sinca, 2013,41(7):1425-1430.(王文波,张晓东,汪祥莉.基于主成分分析的经验模态分解消噪方法[J].电子学报,2013,41(7):1425-1430.)
[7] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings Royal Society of London A: Mathematical Physical and Engineering, 1998,454(1971):903-995.
[8] HUANG N E, SHEN Z, LONG S R. A new view of nonlinear water waves: the Hilbert spectrum[J]. Annual Review Fluid Mechanics, 1999,31(1):417-457.
[9] WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009,1(1):1-41.
[10] QU C, LU T, TAN Y. A modified empirical mode decomposition method with applications to signal denoising[J]. Acta Automatica Sinica, 2010,36(1):67-73.(曲从善,路廷镇,谭营.一种改进型经验模态分解及其在信号消噪中的应用[J].自动化学报,2010,36(1):67-73.)
[11] KOPSINIS Y, MCLAUGHLI S. Development of EMD-based denoising methods inspired by wavelet thresholding[J]. IEEE Transactions on Signal Processing, 2009,57(4):1351-1362.
[12] MAO M, GONG W, ZHANG L, et al. Short-term photo voltaic generation forecasting based on EEMD-SVM combined method[J]. Proceedings of the CSEE, 2013,33(34):17-24.(茆美琴,龚文剑,张榴晨,等.基于EEMD-SVM方法的光伏电站短期出力预测[J].中国电机工程学报,2013,33(34):17-24.)
[13] CHEN Y. Short-term prediction of wind power and photo voltaic power generation[D]. Hangzhou: Zhejiang University, 2013.(陈垣毅.风能及光伏发电功率短期预测方法研究[D].杭州:浙江大学,2013.)
[14] FUNAHSHI K I. On the approximate realization of continuous mappings by neural networks[J]. Neural Networks, 1989,12(5):183-192.
[15] BAO Y. Research on the analysis and predictive algorithm of financial time series based on support vector machine[D]. Dalian: Dalian Maritime University, 2013.(鲍漪澜.基于支持向量机的金融时间序列分析预测算法研究[D].大连:大连海事大学,2013.)
[16] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feed-forward networks are universal approximators[J]. Neural Networks, 1989,12(5):359-366.

集合经验模态分解主成分分析分解消噪下的支持向量机组合模型预测

Support vector machine combined model forecast based on ensemble empirical mode decomposition-principal component analysis

PDF

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

[1]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[2]	王心, 朱浩华, 刘光灿. 卷积鲁棒主成分分析[J]. 计算机应用, 2021, 41(5): 1314-1318.
[3]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[4]	李凯, 李洁. 基于pinball损失的结构模糊多分类支持向量机算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3104-3112.
[5]	陆荣秀, 陈明明, 杨辉, 朱建勇. 基于溶液图像时序特征的元素组分含量动态监测系统[J]. 计算机应用, 2021, 41(10): 3075-3081.
[6]	童林, 官铮. 改进鲸鱼优化支持向量机的交通流量模糊粒化预测[J]. 计算机应用, 2021, 41(10): 2919-2927.
[7]	陈利霞, 班颖, 王学文. 基于张量核范数与3D全变分的背景减除[J]. 计算机应用, 2020, 40(9): 2737-2742.
[8]	郑延斌, 韩梦云, 樊文鑫. 基于二维主成分分析与卷积神经网络的手写体汉字识别[J]. 计算机应用, 2020, 40(8): 2465-2471.
[9]	张健铭, 施元昊, 徐正蓺, 魏建明. 基于误差预测的自适应UWB/PDR融合定位算法[J]. 计算机应用, 2020, 40(6): 1755-1762.
[10]	黄功, 赵永平, 谢云龙. 基于局部密度的加权一类支持向量机算法及其在涡轴发动机故障检测中的应用[J]. 计算机应用, 2020, 40(3): 917-924.
[11]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[12]	王杨, 赵红东. 基于改进粒子群优化的支持向量机与情景感知的人体活动识别[J]. 计算机应用, 2020, 40(3): 665-671.
[13]	赵一, 段兴, 谢仕义, 梁春林. 面向特定目标自识别的交通图像语义检索方法[J]. 计算机应用, 2020, 40(2): 553-560.
[14]	李卉, 杨志霞. 基于Rescaled Hinge损失函数的多子支持向量机[J]. 计算机应用, 2020, 40(11): 3139-3145.
[15]	王海鹏, 降爱莲, 李鹏翔. 牛顿-软阈值迭代鲁棒主成分分析算法[J]. 计算机应用, 2020, 40(11): 3133-3138.