为解决航材备件需求预测中，因航材消耗影响因素多，样本数据量少从而造成预测效果差等问题。提出一种基于主成分分析（principal component analysis, PCA）与改进粒子群算法（improved particle swarm optimization, IPSO）及最小二乘支持向量机（least square support vector machine, LSSVM）的航材备件需求预测模型，首先利用主成分分析法筛选出航材备件主要影响因素，然后使用改进粒子群算法优化最小二乘支持向量机参数组合，最后使用筛选结果及优化参数组合完成PCA-IPSO-LSSVM航材备件需求预测模型训练。与其他4个预测模型相比，PCA-IPSO-LSSVM模型预测精度最高，测试集的均方根误差（root mean squared error, RMSE）和平均相对误差（mean relative error, MRE）分别为3.24和4.23%，表明模型具有较好的预测精度和拟合效果。

In order to solve the problem of poor forecasting effect due to the large number of influencing factors of aviation material consumption and small amount of sample data. A prediction model for aircraft spare parts demand based on principal component analysis (PCA), improved particle swarm optimization (IPSO), and least squares support vector machine (LSSVM) was proposed. Firstly, the principal component analysis method was used to screen the main influencing factors of aviation spare parts, and then the improved particle swarm optimization algorithm was used to optimize the least square support vector machine parameter combination, and finally the selection results and optimization parameter combination were used to complete the PCA-IPSO-LSSVM aviation spare parts demand prediction model training. The results show that compared with the other four prediction models, the PCA-IPSO-LSSVM model has the highest prediction accuracy, and the RMSE and MRE of the test set are 3.24 and 4.23%, respectively, indicating that the model has good prediction precision and fitting effect.