论文部分内容阅读
费用估算是民用飞机成本管理的核心内容,直接关系到民用飞机项目的成败。针对民用飞机费用估算问题展开研究,把GM(0,N)模型与BP神经网络算法相结合,应用BP神经网络对建立的GM(O,N)模型估计值进行再次优化,二者的组合模型能有效提高估算精度。模型构建步骤如下:首先构建原始GM(0,N)模型并根据该模型求出样本的费用估算值;以GM(0,N)模型的参数变量、样本估计值为输入,实际值为期望输出建立BP神经网络并在mat lab里训练;利用训练后的组合模型对民用飞机的费用进行估算。以民用飞机费用估算为仿真实例,分别使用多元线性回归、传统的GM(O,N)模型,和该方法建立费用估算模型,对目标机种的费用做出估算,分析估算结果,表明该模型具有更好的拟合与估算效果。
Cost estimation is the core of civil aircraft cost management, which is directly related to the success or failure of civil aircraft project. Aiming at the civil aircraft cost estimation problem, the GM (0, N) model is combined with the BP neural network algorithm, and the estimated value of the established GM (O, N) model is optimized again by BP neural network. Can effectively improve the accuracy of estimation. The model building steps are as follows: Firstly, the original GM (0, N) model is constructed and the estimated cost of the sample is obtained according to the model; the parameterized variables of the GM (0, N) model and the estimated sample values are input, Establish BP neural network and train in mat lab; use the combined model after training to estimate the cost of civil aircraft. Taking the estimation of civil aircraft cost as a simulation example, we use multiple linear regression and traditional GM (O, N) model respectively to establish the cost estimation model and estimate the cost of the target aircraft. The estimation results show that the model Have better fitting and estimating effect.