Outlier detection method of Integrated Modular Avionics system operation data

The Integrated Modular Avionics system is highly integrated, and intermittent failures occur throughout its life cycle. With the increase of IMA operation service time, the frequency of intermittent failures also increases, which is reflected in the health monitoring data that the completion time of IMA functions continues to increase until the failure threshold is exceeded. In this paper, based on the fact that the IMA function completion time of a certain type of aircraft increases with the increase of the number of flight take-off and landing under three different fault modes, the K-means clustering algorithm is used to detect and analyze the outliers of the function completion time data, and the influence of different fault modes on the IMA working condition is initially confirmed. It lays a foundation for further determining the basis of IMA fault process and health classification, and carrying out health management work such as IMA fault diagnosis life prediction.