一种基于transformer模型的飞行器操纵品质评估方法
By using a transformer-based approach that combines flight mission performance and multimodal physiological signals, an automated prediction model is constructed. This solves the problems of subjectivity and high cost associated with the traditional Cooper-Harper method, achieving scientific rigor and consistency in handling quality assessment. It is applicable to complex aircraft and diverse pilot groups.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIHANG UNIV
- Filing Date
- 2026-04-09
- Publication Date
- 2026-07-17
AI Technical Summary
The traditional Cooper-Harper method relies on subjective evaluation, resulting in inconsistent and costly assessments of aircraft handling qualities. It is difficult to adapt to the needs of complex aircraft and diverse pilot groups, and existing technologies have failed to effectively integrate flight performance and physiological signals for unified evaluation.
A transformer-based approach is adopted, which combines flight mission performance and multimodal physiological signals. A predictive model is constructed through convolutional units and self-attention mechanisms to achieve automated prediction of handling quality levels. Cross-pilot adaptation is performed using few-sample fine-tuning and dynamic weight freezing.
It improves the scientific rigor and consistency of handling quality assessment, shortens the design verification cycle, reduces costs, and is applicable to pilots with varying experience levels.
Smart Images
Figure CN121998517B_ABST