Jixie qiangdu (Jan 2023)
RESEARCH ON EXPANSION METHOD OF TESTING DATA BASED ON PROBABILISTIC DISTRIBUTION FEATURES AND PROXY MODEL (MT)
Abstract
In view of the small number of data samples in the field test, a method of data expansion by using probability distribution and proxy model was proposed. This method determines the interval division and the number of sample points that need to be generated in each interval by analyzing the basic probability characteristics of the data. The sample points were generated based on the back propagation（BP） neural network method to build a semi-physical simulation system proxy model, and were selected by the histogram statistical method. Therefore, the additional sample points not only retain the probability characteristics of the original data, but also have the physical connotations. The expanded testing data improved the aircraft′s landing point coordinate information and the accuracy of the landing point data fusion model. The practicability and effectiveness of the method were verified through the field and semi-physical simulation experiments of the aircraft 534A respectively.
