KPLS-SVM在缺失飞参数据估计中的应用

飞行参数的缺失给飞行事故调查工作带来了很大困难.将核的偏最小二乘法与支持向量机耦合,建立基于状态匹配的飞行参数估计模型可以较好地解决缺失飞参数据的估计问题.首先将初始输入映射到高维特征空间,进而利用偏最小二乘法在特征空间中提取对缺失飞参数据影响较强的得分向量, 最后将提取的得分向量作为输入建立支持向量机模型.既克服了输入变量间的相关性问题, 又降低了支持向量机的输入维数.仿真也说明了使用该方法估计缺失飞行参数的可行性和有效性.

Application of KPLS-SVM to Lost Flight Parameter Data Estimation

The absence of flight parameter brings the difficulty to flight accident investigation Coupling partial least square method and support vector machines, the forecasting model of flight parameter based on the state fitting is established, which can estimate the lost flight parameter efficiently The original inputs are firstly mapped into a high dimensional feature space, then the important score vectors to the flight parameter are extracted in the feature space, lastly, the model of support vector machines which inputs are the score vectors extracted is established It can not only solve the relativity between inputs variables but also reduce the input dimensions in support vector machines model Simulation indicates that the method is valid and efficient for lost flight parameter estimation.