基于GRA-IPSO-SVM的航材携行需求预测研究

Research on Forecasting of Aviation Material Carrying Demand Based on GRA-IPSO-SVM

异地执行飞行任务中航材需求的准确预测是做好携行保障的主要内容之一,为此提出灰色关联分析(GRA)与改进粒子群优化(IPSO)算法及支持向量机(SVM)相结合的航材预测方法。首先运用GRA对航材携行需求的影响因素进行分析;其次引入活性因子和非线性惯性系数改进粒子群优化算法,并通过IPSO对SVM参数进行寻优;最后使用优化后的SVM模型预测航材需求。结果表明:基于GRA-IPSO-SVM的航材预测方法预测的均方根误差比基于PSO-SVM的预测方法下降0.16,平均绝对百分比误差下降2.18%,预测时间减少0.7 s。

Accurate prediction of aviation material requirements for off-site missions is one of the main elements of a good trip assurance,therefore,the method combining gray relation analysis(GRA),improved particle swarm optimization(IPSO)algorithm and support vector machine(SVM)is proposed for predicting aviation material.Firstly,GRA is applied to analyze the factors influencing the demand for aviation materials carrying.Secondly,the particle swarm optimization algorithm is improved by introducing activity factors and non-linear inertia coefficients,and the SVM parameters are optimized by IPSO.Finally,the optimized SVM model is used to predict the demand for aviation materials.The results show that,the root mean square error predicted by aviation material prediction method based on GRA-IPSO-SVM is decreased by 0.16 than that of by using the method based on PSO-SVM,the mean absolute percentage error is decreased by 2.18%,and the prediction time is decreased by 0.7 s.