The several ones that have more lager sensitivity to embankment settlement are found out . then , aimed at the traditional three - layer bp network ' s shortages : easily getting into local minimum value and slow convergence , the modification combined momentum method with self - adaptation study velocity is made , and one improved bp network is put forward . finally , according to the results from above sensitivity analyses , the nonlinear model main parameters of each natural layer in roadbed are approximately rectified using the improved bp network technology founded on its stronger nonlinear mapping capacity and the settlement measurements 采用非线性有限元程序，对邓肯-张模型中8个参数与路堤沉降的关系进行了详细分析，找到了影响沉降的主要参数；接着，针对传统的三层bp网络具有收敛速度慢、易陷入局部极小点等不足，对其进行了修正，提出了改进的bp神经网络模型；最后，根据上述灵敏度分析结果，基于改进的bp网络模型较强的非线性映射能力和前期沉降实测资料，对路基中各天然土层的非线性模型主要参数进行了反分析修正； ( 4 )路堤沉降计算一维法中考虑应力历史、侧向变形的研究。
This thesis presented a modified genetic operators in clustering analysis , and firstly introduced good point set - based clustering algorithm - gameans , which characterized by inferior sensitivity to initial , robustness , and removable premature , and also firstly presented a hybrid method with ga and gameans . experiment show that the hybrid method with general performances can find better clustering results 文中讨论了聚类分析的遗传操作改进方法，首次提出了基于佳点集ga的聚类算法gameans ，降低了传统聚类算法对初始化的要求，具有收敛快、较强的稳健性和可避免早熟的特点。
