中文摘要：

针对平面拟合、二次曲面拟合和GA-BP神经网络3种模型的各自特点和适用范围,为综合各模型优点、提高高程拟合的精度与可靠性,对比分析了不同非线性组合和线性组合方法,即RBF神经网络组合、加权最小二乘支持向量机（WLSSVM）组合和最优加权组合、最优非负变权组合等对GPS高程拟合精度的影响。理论分析和算例结果表明,不同组合方法对GPS高程拟合精度的影响不同,WLSSVM组合和最优非负变权组合的拟合效果较好,可靠性较强;最优非负变权组合能较好地控制残差极值,有效减小误差区间,且转换精度较高。

英文摘要：

Based on the characteristic and applicable scope of plane fitting, quadratic surface fitting and GA-BP neural networkmodels, nonlinear and linear combined methods are proposed to integrateadvan- tages of each model and improve the accuracy and reliability of height fitting. We consider an RBF neural networkcombination, a weighted least squares support vector machine （WLSSVM） portfolio, an optimal weighted combination and an optimal non-negative variable weight combination. The con- sequences of these different combined methodson GPS height fitting precisionare compared and ana- lyzed. The results showthat different combination methods generate different accuracy of GPS Height Fitting. The WLSSVM and optimal non-negative variable weight combinations are superior to the oth- ers.. they have stronger reliability, can better control the residual extremes, effectively shorten the er- ror range, and havehigher conversion accuracy.