论文部分内容阅读
备件库存消耗预测是多因素综合影响下的非线性、小样本预测问题,且不同备件消耗的影响因素有所差异。针对上述问题,提出了一种基于灰色关联分析和支持向量机回归相结合的备件库存消耗预测方法。首先利用灰色关联分析计算出各影响因子与备件库存消耗的灰色关联度,量化了各因子对备件库存消耗的影响程度;再将筛选出的主因子作为支持向量机的输入,并利用遗传算法对支持向量机参数进行寻优,避免人为选择参数的盲目性,从而有针对性地对机体不同备件进行预测。最后,通过实证分析,验证了该方法应用于备件库存消耗预测的有效性和优越性,预测精度高于传统的备件预测模型。
Spare parts inventory prediction is a nonlinear and small sample prediction problem under the influence of multi-factors, and the influencing factors of different spare parts consumption are different. In view of the above problems, this paper proposes a prediction method of spare parts inventory consumption based on gray relational analysis and support vector machine regression. Firstly, the gray relational analysis was used to calculate the gray relational degree between each factor and the stock of spare parts, and the influence of each factor on the inventory consumption of spare parts was quantified. Then, the selected main factor was used as input of support vector machine and genetic algorithm Support vector machine parameters optimization, to avoid the blindness of the human choice of parameters, which targeted the different parts of the body to predict. Finally, through the empirical analysis, the validity and superiority of this method in spare parts inventory forecasting are verified, and the prediction accuracy is higher than the traditional spare part prediction model.