*Result*: 基于 GWO-BP 算法的合成旅战场装备 抢修任务排序研究.

*Addressing the limitations of traditional battlefield equipment repair task scheduling models, such as the lack of adaptive learning capabilities and the subjective and experience-based determination of indicator weights, this study proposes a repair task scheduling model based on the GWO (Grey Wolf Optimization) algorithm combined with a BP neural network. First, a task scheduling indicator system comprising 11 indicators is constructed from three dimensions: repair tasks, repair teams, and battlefield environments; Second, the GWO algorithm is used to optimize the weights and thresholds of the BP neural network, avoiding getting stuck in local optima; finally, the network is trained using synthetic brigade exercise data to obtain the optimal model. Experimental results show that the GWO-BP model significantly reduces prediction errors compared to the BP model, enabling precise prioritization of repair tasks and providing an objective and efficient solution for battlefield equipment repair decision-making in synthetic brigades. [ABSTRACT FROM AUTHOR]*

*针对传统战场装备抢修任务排序模型缺乏自适应学习能力以及指标权重确定主观性、经验化等问题, 提出 基于 GWO (灰狼优化算法) 优化 BP 神经网络算法的智能决策模型。 首先, 从任务累迫性、资源匹配度和环境威胁度 3 个维度构建包含 11 项指标的任务排序指标体系; 其次, 通过 GWO 算法优化 BP 神经网络的权值和阈值, 避免陷入 局部最优; 最后, 根据合成旅演训数据训练网络, 获得最优模型。 结果表明, GWO-BP 模型较 BP 模型预测误差显著 降低, 能够实现抢修任务的精准排序, 为合成旅战场装备抢修决策提供客观高效的解决方案。 [ABSTRACT FROM AUTHOR]*