论文部分内容阅读
信用评价是选择武器装备承制商的重要手段.以国标为基础,结合承制商具体情况确定了信用评价指标体系.分析了传统信用评价方法的不足,对经典BP神经网络的误差函数进行优化,优化后的网络模型收敛速度更快,预测精度更高.构建BP神经网络武器装备承制商信用评价模型,仿真实验表明武器装备承制商信用评价可以选用BP神经网络模型.
Credit evaluation is an important means to choose the weapon equipment contractor.Based on the national standard, combined with the specific situation of the contractor, the credit evaluation index system is determined.Analyzing the shortcomings of the traditional credit evaluation methods and optimizing the error function of the classical BP neural network , The optimized network model has faster convergence rate and higher prediction accuracy.Based on BP neural network, the author constructs a credit evaluation model for the contractor of weapons and equipment, and the simulation results show that the BP neural network model can be used to evaluate the credit rating of weapon equipment contractors.