Research on Flight Safety Indicators Based on Confidence and Principal Component Analysis

Abstract

Modern technology protects flight safety, especially in the specific research and application of flight quality monitoring, and similar studies are currently focusing on large-scale reading of flight data, and storing and analysing it. In this paper, the data from switching on the autopilot is extracted and the reliability is firstly investigated using the Cronbach's alpha reliability coefficient method. Considering the various types of data as the questions of the questionnaire, and the result of Min-Max normalisation of the data as the score of the questionnaire, the size of the reliability coefficients of the data for the eight flight segments was finally derived, and the reliability of the data was quantitatively described based on this. In order to filter the importance of factors reflecting flight safety, seven indicators related to flight safety were then extracted. Then, through principal component analysis, the importance of the indicators was analysed by the size of the coefficients, and the degrees of importance, from the largest to the smallest, were as follows: airspeed, ground speed, descent rate, altitude, and attitude.