基于最小二乘支持向量机和粒子群算法的两相流含油率软测量方法.pdfVIP

第 30 卷 第 2 期 中 国 电 机 工 程 学 报 Vol.30 No.2 Jan.15, 2010 86 2010 年 1 月 15 日 Proceedings of the CSEE ©2010 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2010) 02-0086-06 中图分类号：O 359 文献标志码：A 学科分类号：470·20 基于最小二乘支持向量机和粒子群算法的 两相流含油率软测量方法 张春晓，张涛 (天津大学电气与自动化工程学院，天津市 南开区 300072) Soft Measurement Method for Oil Holdup of Two Phase Flow Based on Least Squares Support Vector Machine and Particle Swarm Optimization ZHANG Chun-xiao, ZHANG Tao (School of Electrical Engineering and Automation, Tianjin University, Nankai District, Tianjin 300072, China) ABSTRACT: In order to improve the measurement accuracy 油率与温差和总流量的关系进行训练，通过改进的 PSO 优 of oil holdup of oil-water two phase flow, a modeling 化 LSSVM 的参数，建立了含油率的优化模型，并用测试数 methodology of oil holdup based on least squares support 据对含油率的模型进行了比较。实验结果表明，基于改进的 vector machine (LSSVM) and modified particle swarm PSO-LSSVM 含油率模型比 PSO-LSSVM 和遗传算法–最小 optimization(PSO) was proposed. The measured total flux of 二乘支持向量机模型运算速度快，比理论修正模型测量精度 oil-water and temperature difference between upstream and 高，含油率在 4%~60% 时，平均测量误差为 0.93% 。 downstream of the heater were employed as inputs, and the oil 关键词：热式油水两相流；含油率；铂电阻；最小二乘支持 holdup was used as output of LSSVM, the relation between 向量机；粒子群算法；遗传算法 input and output was trained and the ideal model of oil holdups was obtained by applying a modified PSO to determine the 0 引言 optimal parameters of LSSVM automatically. The Modified