针对天基信息支援体系效能评估中存在的主观性强与复杂性高的问题，提出一种基于投影梯度神经网络的天基信息 支援体系效能评估方 法。首先，基于国防部体系框架(Department of Defense Architecture Framework，DoDAF)视图产品与包以德循环(observation，orientation，decision，action，OODA)梳理体系作战流程，进而建立评估指标体系，并基于离散事件仿真生成效能评估数据样本。然后，基于Rosen-反向传播(back propagation，BP)神经网络构建效能评估代理模型，并通过对权重参数的限制来解决在效益型指标下评估模型难以解释的问题。最后，对仿真样本进行评估模型验证试验，结果表明所提方法在天基信息支援体系效能评估中相较于传统BP神经网络计算性能提升超过50％，能够为天基信息支援体系效能评估提供技术支撑。
Modeling and effectiveness evaluation method of space-based information support system
Aiming at the problem of strong subjectivity and high complexity in the effectiveness evaluation of space-based information support system,a projection gradient neural network-based effectiveness evaluation method for space-based information support system is proposed.Firstly,based on the Department of Defense Architecture Framework(DoDAF)optical products and observation-orientation-decision-action(OODA)loop are used to sort out the system operational process,and then the evaluation index system is established,and the data samples for effectiveness evaluation are generated based on the discrete-event simulation.Then,the effectiveness evaluation agent model is constructed based on the Rosen-back propagation(BP)neural network,and the restriction of the weight parameter is used to solve the problem that the evaluation model is difficult to be interpreted under the efficiency-type indexes.Finally,a validation test of the evaluation model is conducted on the simulation samples,and the results show that the proposed method can improve the computational performance by more than 50％compared with the traditional BP neural network in the effectiveness evaluation of space-based information support systems,which can provide technical support for the evaluation of the effectiveness of space-based information support systems.
space-based information support systemneural networkprojection gradient methodeffectiveness evaluation
NETL
NSTL
万方数据
