基于自组织神经网络的砂土液化评价
|
摘要
在分析自组织特征映射(SOFM)神经网络基本学习算法的基础上,从提高算法收敛速度和性能出发,提出了一种改进算法:根据实际应用并结合专家经验确定初始连接权值;采用高斯函数作为拓扑邻域函数;将算法分为粗调整和细调整两个阶段,分别采用不同的学习率和邻域函数,然后采用改进后的SOFM算法对砂土液化进行评价。实例研究表明,应用SOFM神经网络评价砂土液化高效可行,为砂土液化评价提供了新方法。
An improved algorithm for self-organizing feature map neural network is presented.In this algorithm,the expert experience and actual state are considered using training weight vectors,the Gauss weight neighborhood function is used to replace the square or circular function,and different descending functions of learning rate and neighborhood width are used in two learning periods.The improved algrithm is used to evaluate the sand liquefaction.The testing results of practical examples show that the method based on SOFM neural network is feasible and effective,and it provides a new approach to research sand liquefaction potential.
An improved algorithm for self-organizing feature map neural network is presented.In this algorithm,the expert experience and actual state are considered using training weight vectors,the Gauss weight neighborhood function is used to replace the square or circular function,and different descending functions of learning rate and neighborhood width are used in two learning periods.The improved algrithm is used to evaluate the sand liquefaction.The testing results of practical examples show that the method based on SOFM neural network is feasible and effective,and it provides a new approach to research sand liquefaction potential.
引文
[1]顾晓鲁,钱鸿缙.地基与基础[M].北京:中国建筑工业出版社,1996.
[2]陈奎,刘兴昌.砂土地震液化的神经网络预测[J].西北地震学报,2000,22(2):167-171.
[3]Davis R O,Berrill J B.Energy dissipation and seismicliquefaction in sands[J].Earthquake Engineering andStructure Dynamics,1982,10(1):68-70.
[4]陈文化,孙巨平,徐兵.砂土地震液化的研究现状及发展趋势[J].世界地震工程,1999,15(2):16-24.
[5]陈新民,罗国煜.地震砂土液化可能性的非确定性灰色预测法[J].桂林工学院学报,1997,17(2):106-109.
[6]D J Willshow.How patterned neural connections can beset up by self-organization[J].Proc Roy.Soc LondonB,1976,194:431-445.
[7]T Kohonen.Self-organized formation of topologicallycorrect feather maps[J].Biol,1982,43:59-69.
[8]石兆吉,张荣祥,顾宝和.砂土液化判别和评价综合方法研究[J].地震工程与工程振动,1997,19(1):82-87.
[9]GB 50011—2001建筑抗震设计规范[S].
[10]任文杰.人工神经网络在地基土液化判别及等级评价中的应用[D].天津:河北工业大学,2002.
[2]陈奎,刘兴昌.砂土地震液化的神经网络预测[J].西北地震学报,2000,22(2):167-171.
[3]Davis R O,Berrill J B.Energy dissipation and seismicliquefaction in sands[J].Earthquake Engineering andStructure Dynamics,1982,10(1):68-70.
[4]陈文化,孙巨平,徐兵.砂土地震液化的研究现状及发展趋势[J].世界地震工程,1999,15(2):16-24.
[5]陈新民,罗国煜.地震砂土液化可能性的非确定性灰色预测法[J].桂林工学院学报,1997,17(2):106-109.
[6]D J Willshow.How patterned neural connections can beset up by self-organization[J].Proc Roy.Soc LondonB,1976,194:431-445.
[7]T Kohonen.Self-organized formation of topologicallycorrect feather maps[J].Biol,1982,43:59-69.
[8]石兆吉,张荣祥,顾宝和.砂土液化判别和评价综合方法研究[J].地震工程与工程振动,1997,19(1):82-87.
[9]GB 50011—2001建筑抗震设计规范[S].
[10]任文杰.人工神经网络在地基土液化判别及等级评价中的应用[D].天津:河北工业大学,2002.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心