To optimize the kill chain design process and enhance combat capabilities, this study investigates a kill chain optimization algorithm based on a hybrid swarm evolutionary meta-game.

Focusing on surface-to-air defense, a non-cooperative game model is developed to address decision-making challenges within kill chain optimization. The game involves UAVs, USVs, and the interplay between damage probability, weapon cost, and remaining USV capability. For UAVs, the game considers target illumination time and remaining UAV capability. A Nash equilibrium-based algorithm is proposed to solve these game models. Given the exponential growth in feasible solutions as the number of targets, sensing nodes, and strike nodes increases, the study introduces an evolutionary meta-game algorithm using real-number encoding to solve the problem efficiently.

The simulation results show that in the uniform attack mode, the optimal Nash equilibrium value decreases monotonically with iterations, effectively yielding optimal kill chain solutions for 8, 16, and 32 incoming targets. Compared to other algorithms, the proposed method outperforms in all metrics, validating its effectiveness.

The proposed hybrid swarm evolutionary meta-game algorithm effectively integrates multi-node resources in maritime operations and dynamically adjusts the allocation of sensing and strike nodes to achieve the rapid closure of the kill chain and optimal strategies. Future research can expand the scenarios and refine the model to include more missile types, complex attack patterns, and resource allocation priorities for different defense systems, further validating the algorithm's performance.

Aiming at the operation support scheduling of carrier-based aircraft, this paper proposes a scheduling optimization algorithm based on apprenticeship learning which can quickly generate a operation support schedule for a carrier-based aircraft fleet.

Using the apprenticeship learning method, the executed and unexecuted tasks in expert demonstrations are compared in pairs to construct a sample set, and the support task scheduling classifier is trained based on the deck features of aircraft carrier. On this basis, a support task apprenticeship learning algorithm for a carrier-based aircraft fleet is designed and compared with the traditional genetic algorithm （GA） in terms of solving solution, solving time and resource allocation.

The results show that the operation support schedule obtained by the apprenticeship scheduling algorithm is equivalent to that by the traditional GA, but the rate of convergence is increased nearly fourfold, and the support resources are more evenly distributed.

The apprenticeship scheduling algorithm proposed in this paper can adequately learn from expert experiences and solve the problem of static single-objective carrier-based aircraft support scheduling. As such, this study provides references for further research in the field of dynamic multi-objective carrier-based aircraft support scheduling.