大型飞机的研制往往存在多种难以预见的不确定性因素,而且目前国内大型客机研制经验缺乏,相关的性能参数和研制成本的历史数据稀少,并存在多重相关性等问题,因此,文中引入了偏最小二乘回归方法,以客机的机体特征及性能特征作为多因变量,建立了一种多因变量对单一自变量的成本预测回归模型,并将部分客机性能参数和成本数据导入成本预测回归模型进行验证.实例分析表明,基于偏最小二来回归法(Partial leastsquares reqression,PLSR)构建的费用估算关系(Cost estimating relationship,CER)模型相对传统预测模型有很大的改善,预测的精度更高,更能体现客机研制成本与前期的性能要求之间的关系.%The development of large-size airplane often bring a variety of unforeseen uncertainties. Partial least-squares regression (PLSR) method is introduced to aircrafts in third generation for the lack of parameters of the performance and the cost data in relevant. The existence of multiple correlation between the values are observed. A single independent variable regression model for prediction of cost is established with aircraft characteristics and performance characteristics as the multi-dependent variables. And then the relevant data published by the Boeing and Airbus is introduced into the prediction model for the empirical study. Case analysis shows that, compared with the traditional prediction model, the cost estimating relationship (CER) model constructed based on PLSR improves the forecast accuracy, and reflects relationship between the research and development (R&.D) costs and the previous requirements.
展开▼
