作者：金星, 徐婷, 王盛慧, 李冰岩, 秦石凌, 张永恒
作者单位：长春工业大学电气与电子工程学院, 吉林 长春 130012
关键词：在线检测;窑尾分解率;软测量;粒子群算法;支持向量回归机
摘要：
为实现水泥窑尾分解率的实时在线检测，利用软测量技术在解决工业在线测量问题中的优势，提出一种改进的粒子群参数优化的支持向量回归机算法（IPSO-SVR），即通过粒子群算法对支持向量机模型核心参数进行优化选择，并在粒子群算法中引入自适应惯性权重的思想，克服粒子群算法容易出现早熟收敛、陷入局部极值的缺点，最终建立起基于IPSO-SVR的窑尾分解率软测量模型。将其与基于交叉验证法（CV）和未改进粒子群算法优化SVR参数的软测量模型进行仿真对比实验，实验表明：该IPSO-SVR模型具有更佳的预测能力，窑尾分解率预测相关系数达0.857 5，预测最大相对误差不超过1.14%，平均相对误差为0.75%，可进一步运用到诸如水泥生产等大型工业的产品分解率预测中。
Soft sensor measurement research on resolution ratio of cement kiln tail based on IPSO-SVR
JIN Xing, XU Ting, WANG Shenghui, LI Bingyan, QIN Shiling, ZHANG Yongheng
College of Electrical and Electronic Engineering, Changchun University of Technology, Changchun 130012, China
Abstract: A support vector regression (SVR) algorithm optimized by improved particle swarm optimization (IPSO) is proposed in this paper to realize the real-time online detection of cement kiln tail resolution ratio.IPSO-SVR is based on soft sensor measurement technique which solves the problem that some important industrial process parameters cannot be directly online measured.Adaptive inertia weight is introduced into PSO to avoid premature convergence and getting trapped in local extremum.The cement kiln tail resolution ratio soft sensor measurement model based on IPSO-SVR is built with the core parameter selection of SVR optimized by using IPSO.Simulation experiment proves that IPSO-SVR has a better forecasting ability compared with model based on SVR optimized by cross validation and PSO-SVR.The correlation coefficient is 0.857 5.The maximum relative error is 1.14%,and the average relative error is 0.75%.It shows that IPSO-SVR can be further applied to the prediction of product resolution ratio in large scale industries such as cement production.
Keywords: online detection;resolution ratio of kiln tail;soft sensor measurement;particle swarm algorithm;support vector regression machine
2016, 42(11): 89-93 收稿日期: 2016-5-23;收到修改稿日期: 2016-5-23
基金项目: 吉林省科学技术厅计划项目（20150203003SF）
作者简介: 金星(1976-),男,吉林长春市人,副教授,主要研究领域为测控技术与智能系统。
参考文献
[1] 李斌怀,郭俊才.预分解窑水泥生产综合技术及操作实例[M].武汉:武汉理工大学出版社,2006:132-141.
[2] 刘文长,张亚珍,游良俭.用BS-I型测碳仪测定入窑生料分解率[J].水泥,2003(5):39-40.
[3] 刘洪林,于加滨.氧化钙法快速测定入窑生料分解率[J].四川水泥,2004(2):53.
[4] 曹宏芳,付忠广,齐敏芳.PSO-SVM软测量方法在火电厂煤质发热量测量中的应用[J].热能动力工程,2014,6(29):731-735.
[5] 孙彦广,高克伟,陶百生.基于智能技术的刚水温度软测量[J].仪器仪表学报,2002(S2):753-755.
[6] 周志成.基于支持向量机的软测量建模[J].自动化技术与应用,2005,24(8):8-10.
[7] 孟倩,马小平,周延.改进的粒子群支持向量机预测瓦斯涌出量[J].矿业安全与环保,2015,42(2):2-4.
[8] PEI J F,ZHU Y M.Modeling and prediction the glass transition temperature of vinyl polymers by using hybrid PSO-SVR method[J].Journal of Theoretical and Computational Chemistry,2013,12(3):5-13.
[9] QIN T C,ZENG S K.Robust prognostics for state of health estimation of lithium-ion batteries based on an improved PSO-SVR model[J].Microelectronics Reliability,2015,55(3):1280-1284.
[10] 段鹏君.水泥生料分解率温度过程建模方法研究[D].沈阳:东北大学,2012.
[11] 刘慧.新型干法水泥生产窑尾分解率软测量研究[D].济南:济南大学,2010.
[12] 熊伟丽,徐保国.基于PSO的SVR参数优化选择方法研究[J].系统仿真学报,2006,18(9):2442-2445.
