AI Prototype Monitors Drone Propeller Health Using Flight Logs

Researchers have developed a Metamorphic Artificial Age Score (AAS) decision-support prototype designed for monitoring the health of drone propellers. This system addresses the challenge where propeller faults might not manifest as a single clear diagnostic signal but rather as distributed effects across various flight-log channels. The prototype processes historical flight logs to calculate six key health-related indicators: trajectory tracking error, attitude instability, thrust-command burden, motor-command imbalance, ESC-command instability, and battery-level stress. These indicators are then normalized against a healthy baseline and evaluated using specific scoring policies and metamorphic adequacy relations. In controlled evaluations, the AAS successfully identified different severity levels of propeller defects, assigning cases to routine monitoring, maintenance review, or mandatory inspection based on the observed operational channel burdens. This multi-indicator approach provides a robust decision-support layer for post-flight maintenance prioritization and enhances autonomous system oversight.