Main Content

什么是Hammerstein-Wiener模型?

When the output of a system depends nonlinearly on its inputs, sometimes it is possible to decompose the input-output relationship into two or more interconnected elements. In this case, you can represent the dynamics by a linear transfer function and capture the nonlinearities using nonlinear functions of inputs and outputs of the linear system. The Hammerstein-Wiener model achieves this configuration as a series connection of static nonlinear blocks with a dynamic linear block. Hammerstein-Wiener model applications span several areas, such as modeling electromechanical system and radio frequency components, audio and speech processing, and predictive control of chemical processes. These models have a convenient block representation, a transparent relationship to linear systems, and are easier to implement than heavy-duty nonlinear models such as neural networks and Volterra models.

您可以将Hammerstein-Wiener模型用作黑框模型结构,因为它为非线性模型提供了灵活的参数化。例如,您可以估计线性模型,并尝试通过向该模型添加输入或输出非线性来提高其保真度。您还可以将Hammerstein-Wiener模型用作灰色盒结构,以捕获有关过程特征的物理知识。例如,输入非线性可以代表执行器中的典型物理变换,而输出非线性可以描述常见的传感器特征。有关何时适合非线性模型的更多信息,请参见关于确定的非线性模型

Hammerstein-Wiener模型的结构

Hammerstein-Wiener模型描述动态系统你sing one or two static nonlinear blocks in series with a linear block. The linear block is a discrete transfer function that represents the dynamic component of the model.

This block diagram represents the structure of a Hammerstein-Wiener model:

在哪里,

  • F是转换输入数据的非线性函数((t)作为w((t)=F((((t))

    w((t),一个内部变量,是输入非线性块的输出,具有与((t)。

  • b/F是一个线性传输函数,可转换w((t)作为X((t)=((b/Fw((t

    X((t),一个内部变量,是线性块的输出,具有与y((t)。

    bandF在线性输出误差模型中类似于多项式。有关输出误差模型的更多信息,请参阅什么是多项式模型?

    为了nyoutputs andnu输入,线性块是包含条目的传输函数矩阵:

    b j ,,,, 一世 (( F j ,,,, 一世 ((

    在哪里j=1,2,...,nyand一世=1,2,...,nu

  • H是映射线性块的输出的非线性函数X((t)到系统输出y((t)作为y((t)=H((X((t))

因为F作用于线性块的输入端口,此功能称为输入非线性。同样,因为Hacts on the output port of the linear block, this function is called the输出非线性。如果您的系统包含多个输入和输出,则必须定义功能FandHFor each input and output signal. You do not have to include both the input and the output nonlinearity in the model structure. When a model contains only the input nonlinearityF,称为汉姆斯坦模型。Similarly, when the model contains only the output nonlinearityH,称为维纳模型。

该软件计算Hammerstein-Wiener模型输出y在三个阶段:

  1. Computew((t)=F((((t))来自输入数据。

    w((t)一世s an input to the linear transfer functionb/F

    The input nonlinearity is a static (无记忆)函数,其中输出的值给定时间t仅取决于时间的输入值t

    您可以将输入非线性配置为Sigmoid网络,小波网络,饱和度,死区,分段线性函数,一维多项式或自定义网络。您还可以删除输入非线性。

  2. 使用使用线性块的输出w((t)and initial conditions:X((t)=((b/Fw((t)。

    You can configure the linear block by specifying the orders of numeratorb和分母F

  3. Compute the model output by transforming the output of the linear blockX((t)你sing the nonlinear functionH作为y((t)=H((X((t)。

    Similar to the input nonlinearity, the output nonlinearity is a static function. You can configure the output nonlinearity in the same way as the input nonlinearity. You can also remove the output nonlinearity, such thaty((t)=X((t)。

Resulting models areidnlhw存储所有模型数据的对象,包括模型参数和非线性估计器。有关这些对象的更多信息,请参阅Nonlinear Model Structures

您可以估算Hammerstein-Wiener模型System Identification应用程序或在命令行中使用nlhw命令。您可以使用均匀采样的时间域输入数据来估计Hammerstein-Wiener模型。您的数据可以具有一个或多个输入和输出通道。您不能使用时间序列数据(仅输出)或频域数据进行估计。如果您有时间序列数据,请拟合非线性模型,请识别非线性ARX模型或非线性灰色盒模型。有关这些模型的更多信息,请参阅Identifying Nonlinear ARX Modelsand估计非线性灰色盒模型

也可以看看

|

Related Topics