基于熵理论的复杂装备费用测算模型

Complex equipment cost estimation model based on entropy theory

为了提高航空器、飞机等大型复杂装备的费用预测精度,根据相似信息优先原理和熵理论,将相似装备的选取看作是一个信息融合的过程,引入距离熵和灰关联熵,构建综合相似度指标来度量装备样本与待预测装备之间的相似程度,对不同样本进行赋权,建立加权最小二乘法对装备费用进行预测。针对装备样本数量小于参数数量的情形,通过构建装备参数对费用的驱动效应矩阵及计算相应熵权,选择熵权较大的参数作为测算模型的自变量。通过实例对比分析,表明基于熵理论的加权回归测算模型具有较高的预测精度和稳定性。

In order to improve the cost prediction accuracy of large and complex equipment such as aircraft and airplanes,based on the principle of similar information priority and entropy theory,the selection of similar equipment is regarded as a process of information fusion,and distance entropy and grey relational entropy are introduced to construct a comprehensive similarity index in order to measure the similarity between the equipment sample and the equipment to be predicted,assign weights to different samples,and establish a weighted least squares method to predict equipment costs.In the situation where the number of equipment samples is less than the number of parameters,the cost driven effect matrix is established and the calculation of the corresponding entropy weight is performed by constructing equipment parameters.The parameter with larger entropy weight is selected as the independent variable of the prediction model.The comparative analysis of examples shows that the weighted regression calculation model based on entropy theory has high prediction accuracy and stability.