Interactive Performance Monitoring and Intelligent Decision-Making Methods for Aerospace Vehicles Navigation Systems

The purpose of this research is to design a multi-source integrated navigation algorithm based on interactive performance monitoring and intelligent decision-making. First, a hierarchical estimation and fusion architecture is developed for self-correction of navigation parameters. On the one hand, the error model of the augmented inertial navigation system is established to calibrate and compensate for systematic errors; on the other hand, the particle swarm optimization mechanism is introduced to dynamically optimize the filtering parameters, which makes the forward state estimation more accurate and maps the health level of each subsystem in real time. Secondly, the estimation error increment is used as the performance index, and an online evaluation unit based on an adaptive neuro-fuzzy inference system is embedded to realize independent and continuous performance monitoring. Finally, the evaluation unit calculated the effective ratio of navigation parameters in real time, injected the adjustment amount into the reverse correction link, and completed autonomous decision-making through process-level correction and terminal output evaluation. Results demonstrate that the method enables real-time performance evaluation and error correction, improving accuracy and reliability. The algorithm can monitor, evaluate and correct the running state of an aerospace vehicles navigation system, thereby alleviating accuracy and reliability degradation during long-duration flights and in complex environments.