Drones air-materials demands predictions method based on partial least squares model

LI Wenqiang, DUAN Zhenyun, ZHAO Wenhui

Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (5) : 1354-1360.

PDF(934 KB)
中国科学院数学与系统科学研究院期刊网
PDF(934 KB)
Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (5) : 1354-1360. DOI: 10.12011/1000-6788(2018)05-1354-07

Drones air-materials demands predictions method based on partial least squares model

  • LI Wenqiang, DUAN Zhenyun, ZHAO Wenhui
Author information +
History +

Abstract

According to the problems of less sample data, the influence factors are complex and changeable, and the low prediction accuracy of inventory requirements in drones air-materials demands, giving a systematical analysis of drones air-materials demands ways under the existing classical small sample, there is an unique advantage to use least squares regression methods to small sample data and variable muticorreiation. A drones air-materials demands predictions method based on partial least squares model is proposed. Selecting the parameters of flight hours, flight lift landing numbers, proficiency degree of operator, unusual temperature and humidity in the environment, fault rate of air-materials, skill level of serviceman and so on, the principle of partial least square method and model modeling step are analyzed, and the model of drones air-materials demands predictions is built, the influence factors of the material are studied. The experiment results indicate that the precision of prediction model is improved, the absolute relative errors of mean were 4.87%, in the predict results, it indicating this ways can apply to drones air-materials demands prediction, and can meet practical need.

Key words

drones / small sample / partial least squares algorithm / air-materials demands prediction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
LI Wenqiang , DUAN Zhenyun , ZHAO Wenhui. Drones air-materials demands predictions method based on partial least squares model. Systems Engineering - Theory & Practice, 2018, 38(5): 1354-1360 https://doi.org/10.12011/1000-6788(2018)05-1354-07

References

[1] 郭峰, 刘臣宇, 李卫灵.基于指数平滑法的航材消耗定额预测研究[J].计算机与现代化, 2012(9):163-165. Guo F, Liu C Y, Li W L. Research on spares consumption quota prediction based on exponential smoothing method[J]. Computer and Modernization, 2012(9):163-165.
[2] 程新, 张乾, 王海.基于数理统计的航材备件预测方法研究[J].航空维修与工程, 2013(4):56-57. Cheng X, Zhang Q, Wang H. Study on material requirement estimation method based on mathematical statistics[J]. Maintenance & Engineering, 2013(4):56-57.
[3] 陈侠, 王拓, 王磊,等.通用飞机航材需求预测方法分析研究[J].沈阳航空航天大学学报, 2014, 31(6):84-86. Chen X, Wang T, Wang L, et al. Analysis of prediction methods for air material demand about general aircraft[J]. Journal of Shenyang Aerospace University, 2014, 31(6):84-86.
[4] 孙臣良, 郑伟, 赵涛, 等.基于数据挖掘和小波神经网络的航材消耗预测方法[J].海军航空工程学院学报, 2014, 29(3):236-237. Sun C L, Zheng W, Zhao T, et al. Prediction method of air material consumption based on data mining and WNN[J]. Journal of Naval Aeronautical and Astronautical University, 2014, 29(3):236-237.
[5] 翟胜路, 张作刚, 李元垒.战时航材需求预测[J].四川兵工学报, 2011, 32(10):11-13. Zhai S L, Zhang Z G, Li Y L. Demand forecast of air materiel spare parts in war[J]. Journal of Sichuan Ordnance, 2011, 32(10):11-13.
[6] 郭峰, 易#
[2] 钺, 史玉敏.基于灰色预测的航材消耗定额模型[J].计算机与现代化, 2011(10):35-36. Guo F, Yi Y Y, Shi Y M. Spares consumption quota model based on gray prediction[J]. Computer and Modernization, 2011(10):35-36.
[7] 华晓旭.民航航材库存模型预测控制研究[J].自动化与仪表, 2014, 29(2):38-41. Hua X X. Research of model predictive control on the air material inventory[J]. Automation & Instrumentation, 2014, 29(2):38-41.
[8] 尚琦坤, 陈云翔.任务驱动下航材需求量的GA-GM-BP预测[J].火力与指挥控制, 2013, 38(4):78-79. Shang Q K, Chen Y X. GA-GM-BP forecast study of demand-quantity in driving[J]. Fire Control & Command Control, 2013, 38(4):78-79.
[9] 李连,孙聪,苏涛,等.基于排队论的可修航材需求预测算法设计与实现[J].科学技术与工程, 2013, 13(1):215-216. Li L, Sun C, Su T, et al. The design of repairable air-material-requirement forecast based on queuing theory[J]. Science Technology and Engineering, 2013, 13(1):215-216.
[10] Tae C P, Tae Y K, Yeong K Y. Prediction of the melt flow index using partial least squares and support vector regression in high-density polyethylene (HDPE) process[J]. Korean Journal of Chemical Engineering, 2010, 27(6):1662-1668.
[11] Facco P, Doplicher F, Bezzo F, et al. Moving average PLS soft sensor for online product quality estimation in an industrial batch polymerization process[J]. Journal of Process Control, 2009, 19(3):520-529.
[12] 王惠文, 吴载斌, 孟洁.偏最小二乘回归的线性与非线性方法[M].北京:国防工业出版社, 2006:75-83. Wang H W, Wu Z B, Meng J. Least-squares regression-linear and nonlinear methods[M]. Beijing:National Defense Industry Press, 2006:75-83.
[13] 钟诗胜, 雷达.一种可用于航空发动机健康状态预测的动态集成极端学习机模型[J].航空动力学报, 2014, 29(9):2088-2089. Zhong S S, Lei D. A dynamic ensemble extreme learning machine model for aircraft engine health condition prediction[J]. Journal of Aerospace Power, 2014, 29(9):2088-2089.
[14] 汪华东, 郭嗣琮, 岳立柱.基于结构元理论的模糊多元线性回归模型[J].系统工程理论与实践, 2014, 34(10):2628-2636. Wang H D, Guo S C, Yue L Z. An approach to fuzzy multiple linear regression model based on the structured element theory[J]. Systems Engineering-Theory & Practice, 2014, 34(10):2628-2636.
[15] 周炳海, 徐佳惠.基于支持向量机的多载量小车实时调度[J].吉林大学学报(工学版), 2016, 46(6):2028-2030. Zhou B H, Xu J H. VM-bassed real-time scheduling approach of multin-load carries[J]. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(6):2028-2030.
[16] 朱飞翔, 李本威,赵勇,等.基于核主元分析方法的燃气涡轮发动机燃烧系统实时监测与诊断[J].航空动力学报, 2016, 31(6):1454-1455. Zhu F X, Li B W, Zhao Y, et al. Real-time monitor and diagnosis of combustion system based on kernel principal component analysis[J]. Journal of Aerospace Power, 2016, 31(6):1454-1455.
[17] 李松, 刘力军,翟曼.改进粒子群算法优化BP网络的短时交通流预测[J].系统工程理论与实践, 2012, 32(9):2045-2049. Li S, Liu L J, Zhai M. Prediction for short-term traffic flow based on modified PSO optimized BP neural network[J]. Systems Engineering-Theory & Practice, 2012, 32(9):2045-2049.

Funding

National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2014BAF08B01)
PDF(934 KB)

408

Accesses

0

Citation

Detail
Sections
Recommended

/

〈 〉