论文部分内容阅读
针对传统航空装备维修费用预测方法难以计算得到满意结果的问题,建立遗传算法优化支持向量机的航空装备维修费用预测模型。将遗传算法与支持向量机相结合,利用遗传算法对支持向量机的参数进行优化,通过实例对GA-SVM模型的应用进行分析对比。结果表明:在航空装备维修费用预测中,该模型比SVR、BP神经网络、偏最小二乘回归以及传统普通多元线性回归方法,具有更高预测精度和泛化能力。
Aiming at the difficulty of calculating the satisfactory results for the prediction of the maintenance cost of traditional aviation equipment, a prediction model of the maintenance cost of aviation equipment based on the genetic algorithm optimization support vector machine is established. The genetic algorithm is combined with support vector machine (SVM), and the parameters of SVM are optimized by genetic algorithm. The application of GA-SVM model is analyzed and compared through examples. The results show that the model has higher prediction accuracy and generalization ability than SVR, BP neural network, partial least-squares regression and traditional generalized multiple linear regression in the prediction of aviation equipment maintenance cost.