用bp神经网络原理对水流挟沙力的研究.htm

MATLAB的神经网络算法,数学建模使用挺好的~~~~~~~~~~~~~

      <P class=MsoNormal 
      style="TEXT-INDENT: 21pt; TEXT-ALIGN: left; mso-layout-grid-align: none; mso-char-indent-count: 2.0; mso-char-indent-size: 10.5pt" 
      align=left><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">ＢＰ网络的学习，由四个过程组成：输入模式由输入层经隐含层向输出层的</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">模式顺传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN"> 
      过程，网络的希望输出与实际输出之差的误差信号由输出层向输入层逐层修正连接权的</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">误差逆传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">过程，由</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">模式顺传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">与</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">误差逆传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">的反复交替进行的网络</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">记忆训练</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN"> 
      过程，网络趋向收敛即网络的全局误差趋向极小值的</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">学习收敛</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">过程。归结起来为，</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">模式顺传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">→</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">误差逆传播</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">→</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">记忆训练</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">→</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">“</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">学习收敛</SPAN><SPAN 
      style="FONT-FAMILY: Arial; mso-bidi-font-size: 10.0pt; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN; mso-ascii-font-family: 宋体">”</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">过程。ＢＰ网络学习规 
      则有时也称广义</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">δ规则。</SPAN><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN"><O:P> 
      </O:P></SPAN></P>
      <P class=MsoNormal 
      style="TEXT-INDENT: 21pt; TEXT-ALIGN: left; mso-layout-grid-align: none; mso-char-indent-count: 2.0; mso-char-indent-size: 10.5pt" 
      align=left><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">作者将BP算法引入水流挟沙力的研究中，通过对总计34组水槽试验资料的训练和预测，表明ANN在该领域的光明前景。<O:P> 
      </O:P></SPAN></P>
      <P class=MsoNormal style="TEXT-ALIGN: left; mso-layout-grid-align: none" 
      align=left><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN"><B>1　水流挟沙能力的影响因素<O:P> 
      &nbsp;</B> </SPAN></P></TD>
    <TD vAlign=top width="34%">
      <P align=center><IMG height=173 src="用BP神经网络原理对水流挟沙力的研究.files/05-tu1.gif" 
      width=287 border=0></P>
      <P class=MsoNormal style="LINE-HEIGHT: 100%; mso-layout-grid-align: none" 
      align=center><FONT size=2><SPAN 
      style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt"><B>图1 
      BP网络<BR></B></SPAN><SPAN lang=EN-US 
      style="mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt">Fig.1 
      BP Neural Network<O:P> </O:P></SPAN></FONT></P></TD></TR></TBODY></TABLE>
<P class=MsoNormal 
style="TEXT-INDENT: 21pt; TEXT-ALIGN: left; mso-layout-grid-align: none; mso-char-indent-count: 2.0; mso-char-indent-size: 10.5pt" 
align=left><SPAN 
style="FONT-FAMILY: 宋体; mso-bidi-font-size: 10.0pt; mso-hansi-font-family: Arial; mso-bidi-font-family: Arial; mso-font-kerning: 0pt; mso-ansi-language: ZH-CN">水流挟沙能力是指在一定的水流泥沙条件下单位水体所能挟带和输送的悬移质中的床沙质数量。在研究解决工程泥沙问题时，水流的挟沙能力规律是最关键的问题。因此水流挟沙能力一直是工程界和学术界研究的核心理论问题，受到人们的普遍关注。目前常用的水流挟沙能力公式主要有两种形式。一种是输沙率形式，一种是含沙量的表达形式。而以含沙量表达时，最常用的武汉水院公式结构形式为<SUP>［7］</SUP>