Flight Trainee Performance Evaluation Using Gradient Boosting Decision Tree, Particle Swarm Optimization, and Convolutional Neural Network (GBDT-PSO-CNN) in Simulated Flights

• Published in: Aerospace 2024-05, Vol.11 (5), p.343
• Main Authors: Shang, Lei, Wang, Haibo, Si, Haiqing, Wang, Yonghu, Pan, Ting, Liu, Haibo, Li, Yixuan
• Format: Article
• Language: English
• Subjects: Accuracy; Aeronautics; Aircraft; Algorithms; Artificial neural networks; Aviation; Business metrics; Civil aviation; Computer simulation; Data collection; Decision trees; Design; Flight simulation; flight skills; Flight training; GBDT; Learning; Literature reviews; Mathematical optimization; Neural networks; Parameter identification; Particle swarm optimization; Performance evaluation; Physiology; Pilots; PSO-CNN; Skills; Training
• ISSN: 2226-4310; 2226-4310
• DOI: 10.3390/aerospace11050343

Flight simulation training is one of the most important methods in early-stage civil aviation flight training. In this regard, flight simulation competitions are effective tools for evaluating the flight skills of trainees. In this study, a model is developed for evaluating the flight skills of trainees by integrating GBDT (Gradient Boosting Decision Tree), PSO (Particle Swarm Optimization), and CNNs (Convolutional Neural Networks). Flight data from simulations is employed for model training. Initially, performance data and scores are gathered from a simulated flight competition platform. The GBDT algorithm is then applied to filter and identify essential flight parameters from the collected data. Subsequently, the PSO-CNN model is utilized to train on the extracted flight parameters. The proposed GBDT-PSO-CNN model achieves a recognition rate of 93.8% on the test dataset. This assessment system is of significant importance for improving the specific maneuvering skill level of flight trainees.