

Integrated Modular Avionics (IMA) system realizes the residence of various avionics functions on standardized hardware and integration also brings some problems such as resource defect spread and functional error cross-linking. To make sure the health of the aircraft, it is essential to carry out a comprehensive health assessment of the IMA system. This paper proposes an IMA system health assessment method based on random forest. First, build the IMA system health assessment framework and transform the mapping that affects the health of the IMA system and the health status of the IMA system into the classification problem in supervised learning. Then give a health assessment method based on random forest, and through incremental learning, the new data generated during the operation of the IMA system can improve the evaluation effect in real-time. Finally, through the system health dataset to realize a comprehensive evaluation of the health status of the IMA system. The results show that the method can perform a comprehensive health assessment with high accuracy for the IMA system.