计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 241100116-9.doi: 10.11896/jsjkx.241100116

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于机器学习的航材备件需求预测研究

王蕊1, 王智恺1, 钟一鸣1, 孙辉1, 杨凯欣2   

  1. 1 中国民航大学电子信息与自动化学院 天津 300300
    2 北京科技大学天津学院无人系统应用研究院 天津 301830
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 杨凯欣(kxyang@163.com)
  • 作者简介:ruiwang@cauc.edu.cn
  • 基金资助:
    天津市重点研发计划项目(22YFZCSN00210)

Research on Demand Forecasting for Aviation Spare Parts Based on Machine Learning

WANG Rui1, WANG Zhikai1, ZHONG Yiming1, SUN Hui1, YANG Kaixin2   

  1. 1 School of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China
    2 Unmanned System Application Research Institute,Tianjin College,University of Science and Technology Beijing,Tianjin 301830,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    Key Research and Development Program of Tianjin,China(22YFZCSN00210).

PDF (PC)

16

摘要： 为科学而精准地预测航空公司航材库存备件需求,制定合理的航材计划,从航材价格、重要度、维修间隔时间、装机数量等影响因素的角度出发,提出一种基于机器学习的航材备件需求预测方法。首先通过主成分分析(PCA)与K-means聚类将不同需求规律的备件降维可视化展示并分类,然后建立混合核极限学习机(HKELM)与随机森林(RF)的模型对分类后的数据进行多元回归预测,其中针对预测过程中参数选取困难的问题,采用麻雀搜索算法(SSA)迭代寻优两种模型的最优参数。最后,结合某航空公司机队运行数据进行实例分析,与反向传播(BP)神经网络、支持向量机(SVM)、最小二乘支持向量机(LSSVM)等预测方法进行比较,结果表明所提出的预测方法效果较好,其对航空公司航材计划工作具有一定的指导意义。

关键词: 航材需求预测, 降维聚类, 混合核极限学习机, 随机森林, 麻雀搜索算法

Abstract: To scientifically and accurately forecast the demand for aviation spare parts in airline inventories and develop rational material plans,this paper proposes a machine learning-based method.The approach considers factors such as spare part prices,importance,maintenance interval times,and installation quantities.Firstly,principal component analysis(PCA) and K-means clustering are applied to reduce dimensionality,enabling the visualization and classification of spare parts with different demand patterns.Then,it establishes hybrid kernel extreme learning machine(HKELM) and random forest(RF) models for multivariate regression predictions on the categorized data.To address the challenge of parameter selection in the prediction process,the sparrow search algorithm(SSA) is employed to iteratively optimize the optimal parameters of the two models.Finally,the method is validated with a case study using real operational data from a specific airline fleet.Its performance is compared with backpropagation(BP) neural networks,support vector machines(SVM),and least squares support vector machines(LSSVM).The results indicate that the proposed forecasting method achieves favorable outcomes and provides valuable guidance for airline material planning efforts.

Key words: Aviation material demand forecast, Dimensionality reduction clustering, Hybrid kernel extreme learning machine, Random forest, Sparrow search algorithm

中图分类号: 

  • TP181
[1]CAO Y C,LIU Y Z,SHEN D Y.Comparative analysis of de-mand forecasting models for replaceable parts in airline routes[J].Industrial Engineering,2022,25(6):101-109.
[2]FENG Y W,CHEN J Y,LIU J Q,et al.Review on the civil aircraft spare parts prediction and configuration management technology[J].Advances in Aeronautical Science and Engineering,2020,11(4):443-453.
[3]WANG R,QIN Y,SUN H.Research on location selection strate-gy for airlines spare parts central warehouse based on METRIC[J].Computational Intelligence and Neuroscience,2021,2021.
[4]SHAFI I,SOHAIL A,AHMAD J,et al.Spare parts forecasting and lumpiness classification using neural network model and its impact on aviation safety[J].Applied Sciences,2023,13(9):5475.
[5]WANG F.A review on demand forecasting methods for aviation materials based on different classifications[J].Science and Technology Innovation and Application,2015(26):58-59.
[6]CHEN Z L,XUE Y L.Research on Prediction Model of Aviation Material Consumption Based on Nonparametric Regression[J].Journal of Ordnance Equipment Engineering,2020,41(6):132-135.
[7]ZUO S,LU J J,TIAN L,et al.Application of simple movingaverage forecasting method in aviation material support[J].Scientific and Technological Information 2008,30(2):87-88.
[8]JOHNSTON F R,BOYLAN J E.Forecasting for Items with Intermittent Demand[J].Journal of the Operational Research Society,1996,47(1):113-121.
[9]SHI Y S,WANG W Q.Forecasting of aviation material demand based on improved triple exponential smoothing method[J].Computer Engineering and Design,2020,41(11):3118-3122.
[10]GUO F,LIU C Y,LI W L.Research on the prediction of aviation material consumption quota based on exponential smoothing method[J].Computer and Modernization,2012,205(9):163-165.
[11]CROSTONJ D.Forecasting And Stock Control For Intermit-Tent Demands[J].Operational Research Quarterly,1972,23(3):289-303.
[12]SYNTETOS A A,BOYLAN J E.On the Variance of Intermittent Demand Estimates[J].International Journal of Production Economics,2010,128(2):546-555.
[13]KAYA G O,SAHIN M,DEMIREL O F.Intermittent demand forecasting:a guideline for method selection[J].Sadhana,2020,45(1):51.
[14]WANG J,PAN X,WANG L,et al.Method of spare parts prediction models evaluation based on grey comprehensive correlation degree and association rules mining:A case study in aviation[J].Mathematical Problems in Engineering,2018,2018.
[15]ZHANG Y,HU Y,WANG H.Forecast of aviation material consumption based on an improved grey prediction model[J].Southern Agricultural Machinery,2020,51(1):60-62.
[16]ZHI L,XU G Y.Grey prediction of excessive consumption time of aviation materials[J].Journal of Xi’an University of Architecture and Technology(Natural Science Edition),2005(3):439-441.
[17]FENG Y W,CHEN J Y,LU C,et al.Civil aircraft spare parts prediction and configuration management techniques:review and prospect[J].Advances in Mechanical Engineering,2021,13(6):16878140211026173.
[18]GHOBBAR A A,FRIEND C H.Evaluation of forecasting me-thods for intermittent parts demand in the field of aviation:a predictive model[J].Computers & Operations Research,2003,30(14):2097-2114.
[19]LEVNER E,PERLMAN Y.CHENG T C E,et al.A Network Approach To Modeling The Multi-Echelon Spare-Part In-Ventory System With Backorders And Interval-Valued Demand[J].International Journal of Production Economics,2011,132(1):43-51.
[20]HUA Z,ZHANG B.A hybrid support vector machines and logistic regression approach for forecasting intermittent demand of spare parts[J].Applied Mathematics and Computation,2006,181(2):1035-1048.
[21]BABAI M Z,TSADIRAS A,PAPADOPOULOS C.On the empirical performance of some new neural network methods for forecasting intermittent demand[J].IMA Journal of Management Mathematics,2020,31(3):281-305.
[22]ZENG H R,FENG Y W,LU C,et al.Research on consumption forecasting of civil aircraft materials based on support vector regression[J].Advances in Aeronautical Engineering,2021,12(5):75-79.
[23]SUN S S,XU C K,HE Y Q.Prediction model of aviation material consumption based on RS-PSO-SVM[J].Journal of Nanjing University of Aeronautics and Astronautics,2021,53(6):881-887.
[24]LI H Q,CAI K L,HAO M,et al.Research on the prediction of aviation material carrying demand based on GRA-IPSO-SVM[J].Advances in Aeronautical Engineering,2022,13(6):166-172.
[25]ZENG H R,FENG Y W,LU C,et al.Prediction method of domestic civil aircraft material consumption based on improved Generative Adversarial Networks[J].Systems Engineering and Electronics,2022,10(25):1-9.
[26]FU W F,MU C H,LIU Y J.Adaptive prediction of aviationconsumable demand based on machine learning methods[J].Science Technology and Engineering,2022,22(11):4609-4617.
[27]GU Y X,XU C K,NI B.Support vector machine aviation material consumption prediction method considering whole process optimization[J].Fire Control and Command Control,2022,47(6):81-86
[28]CHEN Q,LAN X X,LIU X J.Large number interference signal identification based on PCA-RF algorithm[J].Mechanical and Electrical Engineering Technology,2023,52(8):176-180.
[29]WANG S,LIU L.Soil moisture data reconstruction algorithmbased on PCA-MC[J].Computer Science,2023,50(S2):458-463.
[30]LI K J,XU Y S,WEI B G,et al.Transformer top oil temperature prediction model based on PSO-HKELM[J].High Voltage Engineering,2018,44(8):2501-2508.
[31]XING L,LIU Y C.Internal trading identification based on PSO-HKELM[J].Journal of Changchun University of Technology,2024,45(3):282-288.
[32]XIE G M,LIU D Y,LIU M.Transformer fault identification based on multi-strategy improved MPA algorithm and HKELM[J].Journal of Electronic Measurement and Instrumentation,2023,37(4):172-182.
[33]LV Y S,ZHANG D L,BI Y J,et al.Transformer fault diagnosis based on improved kernel extreme learning machine[J].Electrical Age,2021(11):56-60.
[34]HU H,SONG C Z,GAO Y,et al.Research on aviation material consumption prediction based on random forest algorithm[J].Environmental Technology,2021,39(1):210-214.
[35]WANG R,XU X C,LU J.Short-term wind power forecasting based on sparrow search algorithm optimized variational mode decomposition and hybrid kernel extreme learning machine[J].Information and Control,2023,52(4):444-454.
[36]XUE J K,SHEN B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science & Control Engineering,2020,8(1):22-34.
[37]ZHANG S G,ZHANG B.Improved SSA-LSSVM short-termpower load forecasting model based on multiple noise reductions[J].Power Science and Engineering,2022,38(10):54-63.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发