ZHOU Ping，YOU Lei， LIU Ji-ping， ZHANG Xing. Centre Temperature Estimation of Blast Furnace Cross Temperature Measuring Based on M-SVR and RVFLNs[J]. Journal of Northeastern University:Natural Science, 2017, 38(5): 614-619.
[1]Jian L，Gao C H，Li L，et al.Application of least squares support vector machines to predict the silicon content in blast furnace hot metal ［J］.ISIJ International，2008，48(11):1659-1661.
[2]Yuan M，Zhou P.Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA ［J］.Journal of Iron and Steel Research，International，2015，22(6):487-495.
[3]Zhao J，Liu Y，Zhang X P，et al.A MKL based on-line prediction for gasholder level in steel industry ［J］.Control Engineering Practice，2012，20:629-641.
[4]Zhou P，Yuan M，Wang H，et al.Multivariable dynamic modeling for molten iron quality using online sequential random vector functional-link networks with self-feedback connections ［J］.Information Sciences，2015，325(12):237-255.
[5]Tuia D，Verrelst J，Alonso L，et al.Multioutput support vector regression for remote sensing biophysical parameter estimation ［J］.IEEE Geoscience and Remote Sensing Letters，2011，8(4):804-808.
[6]Sanchez F，Cumplido D P，Arenas G，et al.SVM multiregression for non linear channel estimation in multiple-input multiple-output systems ［J］.IEEE Transactions on Signal Processing，2004，52(8):2298-2307.
[7]Pao Y H，Takefuji Y.Functional-link net computing:theory，system architecture，and functionalities ［J］.Computer，1992，25(5):76-79.
[8]Han H G，Wang L D，Qiao J F.Hierarchical extreme learning machine for feedforward neural network ［J］.Neurocomputing，2014，128(5):128-135.
[9]Schmidt W F，Kraaijveld M，Duin R P W.Feedforward neural networks with random weights ［C］//1992 Pattern Recognition Conference B:Pattern Recognition Methodology and Systems.Cydney，1992:1-4.
[10]Martens H，Martens M.Modified Jack-knife estimation of parameter uncertainty in bilinear modelling by partial least squares regression ［J］.Food Quality & Preference，2000，99(11):5-16.
[11]Saracoglu I，Topaloglu S，Keskinturk T.A genetic algorithm approach for multi-product multi-period continuous review inventory models ［J］.Expert Systems with Applications，2014，41(18):8189-8202.
[12]Gao X X，Yang H X，Lin L，et al.Wind turbine layout optimization using multi-population genetic algorithm and a case study in Hong Kong offshore ［J］.Journal of Wind Engineering and Industrial Aerodynamics，2015，139:89-99.(上接第613页)取表征过程内在特征的少数主要变量，因此PCA和ICA广泛应用于线性工业流程的过程监测.基于核函数的KPCA和KICA通过非线性映射，巧妙地将一个非线性问题转化为线性问题，因此被广泛应用于非线性过程监测中.2) 上述算法均有自身的适用条件，如果在监测过程中不考虑工业过程的数据特性，盲目选择监测算法，则可能给出错误结论.3) 本文提出的基于数据特性分析的方法，对于先验知识未知的过程，检验过程数据的相关特性，并根据检验结果及各监测算法的适用条件自动选择合适的监测算法，从而有效解决了各方法对过程数据的限制问题，提高了监测性能.4) 仿真验证了该方法选择的监测算法效果良好，进一步证明了该方法可行有效.
