基于KPCA-LSSVM的硅锰合金熔炼过程炉渣碱度预测研究.pdfVIP

学兔兔 第3l卷 第3期 仪 器 仪 表 学 报 Vo1．31 No．3 2010年3月 Chinese Journal of Scientific Instrument Mar．201O 基于KPCA．LSSVM的硅锰合金熔炼 过程炉渣碱度预测研究 唐春霞，阳春华，桂卫华，朱红求 (中南大学信息科学与工程学院 长沙 410083) 摘 要：针对硅锰合金熔炼过程中炉渣碱度在线检测困难、离线化验滞后大，难以实现实时控制的问题，提出了一种基于核主 元分析(KPCA)与最小二乘支持向量机(LSSVM)相结合的预测方法。该方法通过KPCA去除样本数据的噪声，提取输入数据 空间中的非线性主元，然后利用LSSVM回归算法建立硅锰合金熔炼炉炉渣碱度预测模型，工业生产过程数据仿真结果表明，与 SVM或LSSVM建模方法相比，KPCA—LSSVM预测模型的测量精度高、跟踪性能好，能满足炉渣碱度的在线测量要求。 关键词：炉渣碱度；硅锰合金；核主元分析；最小二乘支持向量机 中图分类号：TP273 文献标识码：A 国家标准学科分类代码：510．80 KPCA and LSSVM model-based slag basicity prediction for silicomanganese smelting process Tang Chunxia，Yang Chunhua，Gui Weihua，Zhu Hongqiu (School ofInformation Science and Engineering，Central South University，Changsha 410083，China) Abstract：To overcome the difficulty that slag basicity can not be effectively controlled in silicomanganese smelting process due to lack of real—time on—line instrumentation，a predicting method is proposed by combining the Kernel Principal Component Analysis(KPCA)with the Least Square Suppo~Vector Machine(LSSVM)．Using KPCA，it is possible to denoise the input data and capture the high—ordered nonlinear principal components in input data space，and with LSSVM we can establish a prediction model between the featured principal components and the pri— mary variable for the slag basicity in a silicomanganese furnace smelting process．Simulation results show that the KPCA-LSSVM model has higher accuracy and better tracking performance compared with SVM or LSSVM models，SO the proposed method can satisfy the requirements of on·line measurement of slag basicity． Key words：slag basicity；silicomanganese；kernel princi