Health assessment method of front landing gear hydraulic retraction and extension system based on GRNN

With the continuous development of civil aircraft health management technology, the status monitoring data of important aircraft systems and components are constantly enriched. The health status of the front landing gear hydraulic retraction system has a great impact on the take-off and landing of the aircraft. Although the system has multi-dimensional monitoring parameters, it is difficult to effectively use the system monitoring data to accurately evaluate its health status. Aiming at the health assessment problem of the front landing gear hydraulic retraction system, this paper builds a simulation model of the system through AMESim software modeling, and studies the influence of the performance changes of hydraulic component parameters on the front landing gear retraction performance. The performance data of the front landing gear retraction actuator at different levels of failure are used as the original data, and the characterization parameters such as retraction time and maximum flow rate are extracted. A health index construction method based on generalized regression neural network (GRNN) is proposed, which can more effectively evaluate the health status of the system. Its effectiveness and accuracy are proved by method comparison.