基于支持向量机的重力匹配算法

为了在重力异常特征微弱区域内实现重力辅助导航以及提高惯性导航系统在重力异常特征明显区域内的定位精度和匹配率,提出了基于支持向量机的重力匹配算法.研究了支持向量机学习样本的选取、支持向量机参数和重力粗糙度的关系,构造了用于重力匹配算法的支持向量机.经计算仿真研究表明,通过选择适当的支持向量机参数,可以实现重力辅助导航,算法在重力特征显著的区域具有较高的匹配率,组合导航系统的定位误差在一个重力图网格左右.

Gravity Matching Algorithm Based on Support Vector Machine

In order to improve the locating precision and matching rate of the inertial navigation system in regions with significant gravity anomaly characteristic,also for the realization of gravity aided navigation in the regions with insignificant gravity anomaly characteristic,a gravity matching algorithm based on SVM(support vector machine) was proposed.The selection of training samples for SVM,the relationship between the parameters of the SVM and the gravity roughness were studied.Then a SVM was constructed for gravity matching.Simulation results show that gravity aided navigation can be implemented by selecting appropriate parameters of SVM.It is also showed that higher matching rate can be achieved in regions with notable gravity anomaly characteristic and the matching precision of the integrated navigation system is approximately one grid on gravity anomaly map.