Airborne Defense Strategy Prediction Based on RReliefF-PCA Optimized Gaussian Regression Models
摘要
This paper explores the intrinsic relationship between infrared countermeasures and missile miss distance in the context of airborne infrared decoy flares as a typical self-defense interference application. A Gaussian Process Regression (GPR) model with a squared exponential kernel function is employed to predict the parameters of airborne defense strategies. The study proposes the use of RReliefF-PCA for feature selection and dimensionality reduction, thereby eliminating feature redundancy in the regression model. A multivariate regression prediction model is established based on the principal component factors of the strategy and the miss distance. The paper presents an optimal deployment strategy for maximizing the interference effectiveness of infrared decoy flares. Additionally, it suggests the use of efficient maneuvering and evasion strategies to enhance the aircraft's ability to avoid and escape from missiles.