CIESC Journal

• 传递现象 • 上一篇    下一篇

基于最小二乘支持向量回归机的光管污垢特性预测

徐志明;文孝强;孙媛媛;孙灵芳   

  1. 东北电力大学能源与机械工程学院;华北电力大学能源与动力工程学院

  • 出版日期:2009-07-05 发布日期:2009-07-05

Forecasting fouling characteristics of plain tube based on least squares-support vector machine for regression

XU Zhiming;WEN Xiaoqiang;SUN Yuanyuan;SUN Lingfang   

  • Online:2009-07-05 Published:2009-07-05

摘要:

搭建了污垢实验系统以测得管壁温度和出、入口温度等参数,并将这些参数作为模型的输入变量,以污垢热阻值作为模型的输出变量,利用最小二乘支持向量回归机搭建了污垢预测模型,对光管的污垢特性进行了预测。一方面,通过与测量结果相比较,验证所搭建的模型是合理可行的;另一方面,通过对多次预测结果分析比较得出,该模型不但适用于流速、水浴温度、材质等参数为定值的情况,而且当这些参数发生改变时,该模型也是适用的。

Abstract:

A fouling test system was set up and the least squares-support vector machine for regression (LS-SVMR)was built to predict the fouling characteristics of the plain tube,with input vectors of tube wall temperature, inlet and outlet temperatures and output vector of fouling resistance.The model was proved to be reasonable and feasible by comparing predictions and measurement results.The results showed that the model is applicable not only to the conditions that water flow, ambient temperature, and material parameters are constant, but also to the conditions when they change.