Maneuver strategy recognition technology for enemy combat aircraft based on Bayesian deep learning

• الحاوية / القاعدة: Shenzhen Daxue xuebao. Ligong ban
• المؤلفون الرئيسيون: YUAN Yinlong, ZHANG Sijie, CHENG Yun, HUA Liang
• التنسيق: مقال
• اللغة: الإنجليزية
• منشور في: Science Press (China Science Publishing & Media Ltd.) 2025-07-01
• الموضوعات: artificial intelligence; bayesian deep learning; variational inference; probabilistic modeling; maneuver strategy recognition; gradient balance factor; intelligent assisted combat system
• الوصول للمادة أونلاين: https://journal.szu.edu.cn/en/#/digest?ArticleID=2746

Enhancing identification of enemy combat aircraft maneuver strategies is a critical factor in improving air combat decision-making capabilities. As traditional deep learning models often show overconfidence in complex and variable combat environment, and it is difficult to evaluate the uncertainty, a combat aircraft maneuver strategy recognition method based on Bayesian deep learning is proposed. The method employs Bayesian variational inference and multivariate Gaussian distribution to construct a multi-layer perceptron-based Bayesian deep learning (BDL-MLP) probabilistic model. A gradient balancing factor is introduced to reduce the imbalance between complexity cost gradient and likelihood cost gradient, and then Bayes backpropagation algorithm is used for model training and parameter optimization. Based on the virtual air combat simulation platform AirFlightSim developed in Unity3D software, BDL-MLP, multilayer perceptron (MLP), AlexNet and LeNet models are used to classify and evaluate the data sets of combat aircraft motion scenes with varying degrees of blur (blur radii of 0, 15, 31, 45, and 61 pixels, respectively). Results show that , on the five datasets constructed with the aforementioned blur radii, the maneuver strategy identification accuracy of the BDL-MLP model showed average improvements of 0.43%, 0.99%, 1.19%, 1.98%, and 2.36% compared to the MLP, AlexNet, and LeNet models, respectively. Moreover, the BDL-MLP model has the best performance in robustness and feature extraction abilities for complex data, and can quantify the prediction uncertainty. The strategy recognition method of combat aircraft maneuvering based on Bayesian deep learning can provide valuable insights for the research and development of military intelligent auxiliary combat decision-support systems.