导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2021, Vol. 42 ›› Issue (8): 525838-525838.doi: 10.7527/S1000-6893.2021.25838

• Article • Previous Articles     Next Articles

Flight training evaluation based on dynamic Bayesian network and fuzzy gray theory

LIU Hao1, WANG Hao1, MENG Guanglei2, WU Hao2, ZHOU Mingzhe2   

  1. 1. AVIC Shenyang Aircraft Design and Research Institute, Shenyang 110035, China;
    2. School of Automation, Shenyang Aerospace University, Shenyang 110136, China
  • Received:2021-04-15 Revised:2021-05-08 Published:2021-05-31
  • Supported by:
    Aeronautical Science Foundation of China (2016ZD54015)

Abstract: An evaluation method for flight training of warplanes is proposed based on dynamic Bayesian network and fuzzy gray theory. Firstly, the causal relationship between typical flight parameters and maneuver in the training process is analyzed. The maneuver recognition model based on dynamic Bayesian network is constructed according to expert experience and prior knowledge, and the maneuver recognition results are obtained by reasoning. Then, an evaluation index system of fighter flight training is established. The evaluation index of flight training is selected according to the results of fighter maneuver identification, and the index weight is determined by the comprehensive weighting method. Finally, the gray fuzzy evaluation matrix is established, and the evaluation results are obtained by calculating the flight data of each evaluation index in the flight training process. The experimental results show that the evaluation method proposed can recognize maneuver and evaluate flight training according to the parameters in the flight process, improving the efficiency of flight training evaluation.

Key words: dynamic Bayesian network, maneuver recognition, gray fuzzy evaluation matrix, flight training evaluation, evaluation index system

CLC Number: