共建共享双层策略驱动的复杂装备组合优化求解

考虑共建共享的复杂装备组合优化是适应联合作战和装备发展需求的一种新的装备发展规划理念，不仅需要统筹考虑共建阶段各研发单位的资源高效整合，还需兼顾共享阶段中预期运用场景下的资源共享、相互配合等不同约束。为了高效获得优质的组合规划与组合选择方案，本文研究了共建共享双层策略驱动的复杂装备组合优化问题。首先，综合考虑共建和共享策略，对装备研发组合规划问题和装备组合选择问题进行分析和建模。然后，设计了深度神经网络辅助的分支定界启发式方法，通过可学习的模型在分支选择和修剪的过程中给出合理的建议。最后，通过侦察预警监视装备组合优化作为案例，验证了本文所构建模型和提出的算法的有效性。

Combinatorial optimization solution of complex equipment driven by contribution and sharing two-tier strategy

Combinatorial optimization of complex equipment considering constribution and sharing is a new equipment development concept that meets the needs of joint operations and equipment development. It needs to consider not only the integration of resources from different institutions in the construction step, but also different constraints under the expected application scenarios in the sharing step. To efficiently obtain a high-quality portfolio planning plan, the problem of complex equipment combinatorial optimization driven by contribution and sharing two-tier strategy is analyzed and modeled, and then a deep neural network assisted branch and bound heuristic method is designed, with a learnable model used to give reasonable results in the process of branch selection and pruning. Finally, the effectiveness of the proposed model and algorithm is demonstrated by a case of intelligence, surveillance and reconnaissance armament system of systems.