...
首页> 外文期刊>Journal of power sources >Identification of the Hammerstein model of a PEMFC stack based on least squares support vector machines
【24h】

Identification of the Hammerstein model of a PEMFC stack based on least squares support vector machines

机译:基于最小二乘支持向量机的PEMFC堆Hammerstein模型的辨识

获取原文
获取原文并翻译 | 示例
           

摘要

This paper reports a Hammerstein modeling study of a proton exchange membrane fuel cell (PEMFC) stack using least squares support vector machines (LS-SVM). PEMFC is a complex nonlinear, multi-input and multi-output (MIMO) system that is hard to model by traditional methodologies. Due to the generalization performance of LS-SVM being independent of the dimensionality of the input data and the particularly simple structure of the Hammerstein model, a MIMO SVM-ARX (linear autoregression model with exogenous input) Hammerstein model is used to represent the PEMFC stack in this paper. The linear model parameters and the static nonlinearity can be obtained simultaneously by solving a set of linear equations followed by the singular value decomposition (SVD). The simulation tests demonstrate the obtained SVM-ARX Hammerstein model can efficiently approximate the dynamic behavior of a PEMFC stack. Furthermore, based on the proposed SVM-ARX Hammerstein model, valid control strategy studies such as predictive control, robust control can be developed.
机译:本文报道了使用最小二乘支持向量机(LS-SVM)对质子交换膜燃料电池(PEMFC)堆进行Hammerstein建模研究。 PEMFC是一个复杂的非线性,多输入多输出(MIMO)系统,很难通过传统方法进行建模。由于LS-SVM的泛化性能与输入数据的维数以及Hammerstein模型的特别简单的结构无关,因此使用MIMO SVM-ARX(带有外源输入的线性自回归模型)Hammerstein模型来表示PEMFC堆栈在本文中。通过求解一组线性方程式,然后进行奇异值分解(SVD),可以同时获得线性模型参数和静态非线性。仿真测试表明,所获得的SVM-ARX Hammerstein模型可以有效地逼近PEMFC堆栈的动态行为。此外,基于提出的SVM-ARX Hammerstein模型,可以开发有效的控制策略研究,例如预测控制,鲁棒控制。

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