基于红狐优化支持向量机回归的船舶备件预测  

Ship spare parts prediction based on red fox optimized support vector regression

作　　者：孟冠军[1] 杨思平 钱晓飞[2] MENG Guanjun;YANG Siping;QIAN Xiaofei(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China;School of Management,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]合肥工业大学机械工程学院,安徽合肥230009 [2]合肥工业大学管理学院,安徽合肥230009

出　　处：《合肥工业大学学报(自然科学版)》2025年第1期25-31,共7页Journal of Hefei University of Technology:Natural Science

基　　金：国家重点研发计划资助项目(2019YFB1705303);国家自然科学基金资助项目(72271077)。

摘　　要：针对以往船舶备件需求预测精度不高,无法满足船舶综合保障的实际问题,文章建立一种基于改进红狐优化算法(improved red fox optimization,IRFO)的支持向量机回归(support vector regression,SVR)的船舶备件预测模型。为进一步提高红狐优化算法(red fox optimization,RFO)的寻优精度,重构其全局搜索公式,并融合精英反向学习策略。采用基准测试函数对IRFO算法进行仿真实验,实验表明,IRFO算法比RFO算法、粒子群算法、灰狼优化算法寻优能力更强,综合性能更优。基于船舶备件历史数据,建立IRFO-SVR船舶备件预测模型,通过对比其他模型的预测结果,表明IRFO-SVR的预测效果更佳。Aiming at the problem that the prediction accuracy of ship spare parts demand is not high and cannot meet the comprehensive support of ships,a ship spare parts prediction model based on support vector regression(SVR)optimized by improved red fox optimization(IRFO)is established.To further improve the optimization accuracy of red fox optimization(RFO),its global search formulation is reconstructed and elite opposite learning(EOL)strategy is incorporated.Then the benchmark function is used to simulate the IRFO algorithm.The results show that IRFO has better comprehensive performance and stronger optimization ability than RFO,particle swarm optimization(PSO)and grey wolf optimization(GWO).Based on the historical data of ship spare parts,an IRFO-SVR prediction model of ship spare parts is established.By comparing the prediction results of other models,it shows that the prediction effect of IRFO-SVR is better.

关 键 词：船舶备件预测 红狐优化算法(RFO) 支持向量机回归(SVR) 精英反向学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] U672.71[自动化与计算机技术—控制科学与工程]