| 基于贝叶斯正则化BP神经网络的砂土地震液化研究 |
| |
| 引用本文： | 林志红,项伟. 基于贝叶斯正则化BP神经网络的砂土地震液化研究[J]. 安全与环境工程, 2011, 18(2): 23-27 |
| |
| 作者姓名： | 林志红 项伟 |
| |
| 作者单位： | 林志红,LIN Zhi-hong(中交第二公路勘察设计研究院有限公司,武汉,430056;中国地质大学工程学院,武汉,430074);项伟,XIANG Wei(中国地质大学工程学院,武汉,430074) |
| |
| 摘 要： | 砂土地震液化的影响因素具有高度的非线性关系,而神经网络在处理非线性问题上具有其独特的优越性.本文在探讨输人层模式的选择以及砂土液化影响因素的基础上,采用改进的贝叶斯正则化方法和"提前停止"算法建立了砂土地震液化预测模型,通过实例计算和模型评价,表明本模型的计算结果与规范法、改进的Seed简化法以及基于传统BP网络算法的...
|
| 关 键 词： | 贝叶斯正则化 BP神经网络 Seed简化法 砂土地震液化 |
Analysis on Sand Seismic Liquefaction by Bayesian Regulated BP-Neural Networks |
| |
| LIN Zhi-hong,XIANG Wei. Analysis on Sand Seismic Liquefaction by Bayesian Regulated BP-Neural Networks[J]. Safety and Environmental Engineering, 2011, 18(2): 23-27 |
| |
| Authors: | LIN Zhi-hong XIANG Wei |
| |
| Affiliation: | LIN Zhi-hong1,2,XIANG Wei1(1.Second Highway Consultants Co.,Ltd.,China Communications Construction Corporation,Wuhan430056,China,2.Faculty of Engineering,China University of Geosciences,Wuhan 430074,China) |
| |
| Abstract: | The affecting factors of sand seismic liquefaction are highly nonlinear and the neural network has originality in processing non-linear problems.Based on the study of the selection of input layer model and the affecting factors of sand seismic liquefaction,the model for predicting sand liquefaction is built utilizing Bayesian regularization method and early stopping method.Through practical computation examples and the assessment of the model,the model is manifested to have much more accurate results and le... |
| |
| Keywords: | Bayesian regularization BP neural network Seed's simplified method sand seismic liquefaction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
