首页> 外文会议>2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)论文集 >Hammerstein Model Identification of Continuous Stirred Tank Reactor Based on Least Squares Support Vector Machines
【24h】

Hammerstein Model Identification of Continuous Stirred Tank Reactor Based on Least Squares Support Vector Machines

机译:基于最小二乘支持向量机的连续搅拌釜反应器Hammerstein模型辨识

获取原文

摘要

A novel LSSVM-ARX Hammerstein model structure is proposed for a continuous stirred tank reactor (CSTR). LSSVM with a radial basis function (RBF) kernel is used to represent the static nonlinear block in the Hammerstein model. The dynamic linear part of the model is realized by a linear autoregression model with exogenous input (ARX). The linear model parameters and the static nonlinearity can be obtained simultaneously by solving a set of linear equations followed by singular value decomposition. Identification results of CSTR indicate that the proposed Hammerstein model has higher prediction accuracy in comparison with the traditional Hammerstein model, and it can approximate the dynamic behavior of the plant efficiently.
机译:提出了一种新颖的LSSVM-ARX Hammerstein模型结构,用于连续搅拌釜反应器(CSTR)。具有径向基函数(RBF)内核的LSSVM用于表示Hammerstein模型中的静态非线性块。该模型的动态线性部分是通过具有外部输入(ARX)的线性自回归模型实现的。通过求解一组线性方程式,然后进行奇异值分解,可以同时获得线性模型参数和静态非线性。 CSTR的识别结果表明,与传统的Hammerstein模型相比,提出的Hammerstein模型具有更高的预测精度,可以有效地近似植物的动态行为。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号