金秀章,刘潇

• 1:华北电力大学控制与计算机工程学院

摘要(Abstract)：

针对最小二乘支持向量机(LSSVM)在利用现场数据建模时难以适应不同工况,鲁棒性较差的问题,提出了一种基于在线自适应修正的鲁棒LSSVM模型。该方法以总的预报误差大小作为阈值,根据不同工况自适应更新参数,从而提高模型对数据的适应性;同时采用模糊隶属度对向量机优化问题中的误差平方项赋予动态权值,增强模型的抗噪声能力。将该方法应用于电厂实际数据对一次风量的预测,并与普通LSSVM模型相比,结果表明该算法所建立的模型鲁棒性强、预测精度高。该模型可满足不同工况下数据的实时预测和估计,为各种在线监测系统提供了良好的数据支持。

关键词(KeyWords)： 在线自适应控制;鲁棒性;最小二乘支持向量机;模糊隶属度;一次风量;软测量

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 金秀章,刘潇

参考文献(References)：

• [1]MAHMOUD T A.Adaptive control scheme based on the least squares support vector machine network[J].International Journal of Applied Mathematics&Computer Science,2011,21(4):685-696.
• [2]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.DING Shifei,QI Bingjuan,TAN Hongyan.An overview on theory and algorithm of support vector machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
• [3]顾亚祥,丁世飞.支持向量机研究进展[J].计算机科学,2011,38(2):14-17.GU Yaxiang,DING Shifei.Advances of support vector machines(SVM)[J].Computer Science,2011,38(2):14-17.
• [4]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9:293-300.
• [5]顾燕萍,赵文杰,吴占松.最小二乘支持向量机的算法研究[J].清华大学学报(自然科学版),2010(7):1063-1066.GU Yanping,ZHAO Wenjie,WU Zhansong.Least squares support vector machine algorithm[J].Journal of Tsinghua University(Science and Technology),2010(7):1063-1066.
• [6]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015(2):26-32.WANG Kai,GUAN Shaoqing,WANG Lingxiang,et al.A combined forecasting model for wind power predication based on fuzzy information granulation and least squares support vector machine[J].Power System Protection and Control,2015(2):26-32.
• [7]刘吉臻,吕游,杨婷婷.基于变量选择的锅炉NOx排放的最小二乘支持向量机建模[J].中国电机工程学报,2012,32(20):102-107.LIU Jizhen,LV You,YANG Tingting.Least squares support vector machine modeling on NOx emission of boilers based on variable selection[J].Proceedings of the CSEE,2012,32(20):102-107.
• [8]王贺,胡志坚,张翌晖,等.基于聚类经验模态分解和最小二乘支持向量机的短期风速组合预测[J].电工技术学报,2014(4):237-245.WANG He,HU Zhijian,ZHANG Yihui,et al.A hybrid model for short-term wind speed forecasting based on ensemble empirical mode decomposition and least squares support vector machines[J].Transactions of China Electrotechnical Society,2014(4):237-245.
• [9]赵超,戴坤成.自适应加权最小二乘支持向量机的空调负荷预测[J].重庆大学学报,2016(1):55-64.ZHAO Chao,DAI Kuncheng.Modeling air-conditioning load forecasting based on adaptive weighted Least squares support vector machine[J].Journal of Chongqing University,2016(1):55-64.
• [10]赵超,戴坤成.基于自适应加权最小二乘支持向量机的短期电力负荷预测[C]//第25届中国过程控制会议论文集.中国自动化学会过程控制专业委员会,2014:6.ZHAO Chao,DAI Kuncheng.Short-term load forecasting based on adaptive weighted least squares support vector machine[C]//Proceedings of the 25th China Process Control Conference.China Society of Automation Process Control Professional Committee,2014:6.
• [11]周欣然,滕召胜.一种在线稀疏LSSVM及其在系统建模中的应用[J].湖南大学学报(自然科学版),2010(4):37-41.ZHOU Xinran,TENG Zhaosheng.An online sparse LSS VM and its application in system modeling[J].Journal of Hunan University(Natural Science),2010(4):37-41.
• [12]张淑宁,王福利,何大阔,等.在线鲁棒最小二乘支持向量机回归建模[J].控制理论与应用,2011(11):1601-1606.ZHANG Shuning,WANG Fuli,HE Dakuo,et al.Modeling method of online robust least-squares-supportvector regression[J].Control Theory&Applications,2011(11):1601-1606.
• [13]刘新文,王雪松.可逆分块矩阵的逆矩阵的求法[J].衡阳师范学院学报,2008(3):29-31.LIU Xinwen,WANG Xuesong.The method of inverse matrix of the inversable block matrix[J].Journal of Hengyang Normal University,2008(3):29-31.
• [14]邵伟明,田学民.基于快速留一交叉验证法的在线递推最小二乘支持向量机建模方法[J].青岛科技大学学报(自然科学版),2012(5):510-514.SHAO Weiming,TIAN Xuemin.On-line recursive least squares support vector machine modeling method based on FLOO-CV[J].Journal of Qingdao University of Science and Technology(Natural Science Edition),2012(5):510-514.
• [15]刘京礼.鲁棒最小二乘支持向量机研究与应用[D].合肥:中国科学技术大学,2010.LIU Jingli.Robust least squares support vector machine research and application[D].Hefei:University of Science and Technology of China,2010.
• [16]吴永存,陈卫.基于机器学习的火电机组一次风量软测量技术[J].电站系统工程,2014(4):61-64.WU Yongcun,CHEN Wei.Soft sensor for thermal power units primary air flow based on machine learning[J].Power System Engineering,2014(4):61-64.
• [17]金秀章,韩超.KPCA-LSSVM在磨煤机一次风量预测中的应用[J].自动化仪表,2015(3):62-67.JIN Xiuzhang,HAN Chao.Application of KPCALSSVM in prediction of the primary air flow of pulverizer[J].Process Automation Instrumentation,2015(3):62-67.