Artificial Intelligence Technique for Solving Weapon Target Assignment

Weapon Target Assignment (WTA) problem, a critical challenge in military operations, involves optimally allocating defensive or offensive weapons to neutralize incoming threats while maximizing operational efficiency. This NP-hard combinatorial optimization problem becomes computationally intractable with conventional methods as the scale increases, necessitating advanced artificial intelligence techniques. This paper proposes a novel meta-heuristic approach, the Gaining-Sharing Knowledge-Based Algorithm (GSK), to solve the WTA problem efficiently. Inspired by the human processes of acquiring and sharing knowledge, GSK employs a dynamic balance between exploration (gaining knowledge through diverse search spaces) and exploitation (sharing knowledge to refine solutions), enabling robust convergence toward near-optimal assignments. The algorithm including its distinct “junior” and “senior” phases, enhance its ability to avoid local optima while addressing the complex constraints of WTA, such as resource limitations, threat priorities, and engagement costs. Through extensive simulations on benchmark WTA scenarios, the proposed GSK-based approach demonstrates superior performance compared to state-of-the-art meta-heuristics, including Binary Particle Swarm Optimization (BPSO), ant colony optimization (ACO), integer particle swarm optimization (IPSO) and sine cosine algorithm (SCA)in terms of solution quality, convergence speed, and scalability. The results highlight GSK's potential as a reliable decision-support tool for real-time defense systems, offering a balance between computational efficiency and tactical effectiveness.