论文部分内容阅读
为了克服部附件送修费用的一般模型不能方便进行敏感性分析的缺点,考虑设计阶段下输入数据采集的可行性,应用偏最小二乘回归理论,通过变量投影重要度分析,筛选出重量、价格、平均非计划拆卸时间、平均车间修理时间、SRU的个数5个参数。采用对数线性关系式,构建了部附件送修费用的参数模型,并通过实际值与回归值的误差分析验证了该模型的可靠度。根据得到的参数模型和工程经验,确定了各参数的单一函数表达式及其取值范围;结合切线斜率即敏感度的事实,仿真计算了各个参数变化的显著敏感区间。结果表明,该模型精度较高,能方便进行敏感性分析,可作为飞机设计阶段工程人员选择合适部附件的实用工具。
In order to overcome the shortcomings of the general model of the cost of sending and receiving parts and accessories, we can consider the feasibility of the input data collection in the design stage and apply the partial least squares regression theory. Through the analysis of the importance of variable projection, we can choose the weight, price , The average unscheduled disassembly time, the average workshop repair time, the number of SRU 5 parameters. Logarithmic linear relationship was used to build a parametric model for the cost of sending and receiving accessories for parts and accessories. The reliability of the model was verified by error analysis between the actual value and the regression value. According to the obtained parametric model and engineering experience, the single function expression of each parameter and its range of values are determined. Based on the fact that the slope of the tangent is sensitive, the significant sensitive interval of each parameter change is simulated. The results show that this model has high precision and can be used for sensitivity analysis easily. It can be used as a practical tool for engineers to choose appropriate accessories in the design phase.