Intelligent Speed and Attitude Tuning for Surface-to-Air Missiles Based on Neural Networks
Nguyen Van Nam1*, Nguyen Trung Hieu1
Abstract
This paper presents an intelligent speed and attitude tuning method for surface-to-air missiles (SAMs based on artificial neural networks. The proposed neural network is designed to learn the nonlinear relationship between missile kinematic states, attitude dynamics, and engagement conditions, enabling real-time adaptive tuning of speed and attitude commands during flight. Unlike conventional fixed-parameter or rule-based tuning strategies, the neural network dynamically adjusts control parameters to cope with target maneuvers, model uncertainties, and rapidly changing interception scenarios. A nonlinear missile–target engagement model is developed, and the neural network-based tuning module is integrated with a conventional guidance law to form an intelligent guidance and control architecture. The neural network is trained offline using representative engagement data and is capable of generalizing to unseen target maneuvers during online operation. Simulation results under various scenarios, including highly maneuvering and high-speed targets, demonstrate that the proposed approach significantly improves interception accuracy, reduces miss distance, and enhances attitude stability compared with traditional tuning methods. The results confirm that neural network-based speed and attitude tuning provides an effective and practical solution for modern surface-to-air missile systems operating in complex air-defense environments.
Keywords:
Surface-to-Air Missile, Neural Network, Air-To-Air Missiles , Speed and Attitude Tuning; Intelligent Guidance and Control; Adaptive Control; Highly Maneuvering Targets
