基于样本分位数原理的飞参数据异常值检测算法

Flight Data Outliers Detection Method Based on Sample Quantile

为了提高飞行数据处理精度,提出了一种基于样本分位数的飞参数据异常值检测算法。首先通过设置时间序列窗口,对记录的飞参数据进行遍历检测;然后对每个窗口内的数据进行样本分位数提取,并将提取的样本分位数组成的时间序列与原始飞参记录数据进行对比,实现飞参数据异常值检测。通过对飞参数据的仿真实验分析可知,采用样本分位数方法无须进行复杂的参数及内部设置,可有效提取出飞参数据中的异常值,为后续飞参数据处理提供了理论基础。

In order to improve the accuracy of flight data processing,an outlier detection algorithm based on sample quantile was proposed.The flight parameter data were traversed by setting time series window,and then the sample quantile was extracted from the data in each window,and the time series composed of the extracted sample quantile was compared with the original flight parameter data to realize the abnormal value detection of flight parameter data.Through the simulation analysis of the flight parameter data,it can be seen that the sample quantile algorithm can effectively extract the outliers from the flight parameter data without complicated parameters and internal settings,which provides a theoretical basis for the subsequent flight parameter data processing.