[1]田德红,何建敏.基于变异粒子群优化与深度神经网络的航空弹药消耗预测模型[J].南京理工大学学报(自然科学版),2018,42(06):716.[doi:10.14177/j.cnki.32-1397n.2018.42.06.012]
 Tian Dehong,He Jianmin.Aviation ammunition consumption prediction model based onmutated particle swarm optimization and deep neural network[J].Journal of Nanjing University of Science and Technology,2018,42(06):716.[doi:10.14177/j.cnki.32-1397n.2018.42.06.012]
点击复制

基于变异粒子群优化与深度神经网络的航空弹药消耗预测模型()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
42卷
期数:
2018年06期
页码:
716
栏目:
出版日期:
2018-12-30

文章信息/Info

Title:
Aviation ammunition consumption prediction model based onmutated particle swarm optimization and deep neural network
文章编号:
1005-9830(2018)06-0716-06
作者:
田德红何建敏
东南大学 经济管理学院,江苏 南京 211189
Author(s):
Tian DehongHe Jianmin
School of Economics and Management,Southeast University,Nanjing 211189,China
关键词:
变异粒子群优化 深度神经网络 航空弹药 组合预测模型
Keywords:
mutated particle swarm optimization deep neural network aviation ammunition combination forecasting model
分类号:
TJ410.1
DOI:
10.14177/j.cnki.32-1397n.2018.42.06.012
摘要:
为了提高航空弹药的供应保障效率,将变异粒子群优化(MPSO)融入深度神经网络(DNN),研究航空弹药训练消耗预测问题。通过DNN确定网络各层的最优激活函数,基于MPSO参数寻优得到网络各层最优的权值和阈值,进而构建MPSO与DNN融合的航空弹药训练消耗预测模型。实验研究表明,该文组合预测模型在对5年数据的预测中均方误差为0.000 9,与粒子群优化-深度神经网络(PSO-DNN)模型、DNN模型以及反向传播神经网络(BPNN)模型相比具有更好的预测性能。
Abstract:
The forecasting of aviation ammunition training consumption is studied based on the mutated particle swarm optimization(MPSO)and the deep neural network(DNN)to improve the efficiency of supply. The optimal activation functions of each layer of the network are determined by the DNN,the optimal weights and thresholds of each layer of the network are obtained by the MPSO,and the aviation ammunition consumption prediction model MPSO-DNN is constructed. Experimental studies show the MPSO-DNN has a mean square error of 0.0009 in the prediction of five-year data. Compared with particle swarm optimization-deep neural network(PSO-DNN),DNN and back propagation neural network(BPNN),MPSO-DNN has better predictive performance.

参考文献/References:

[1] Yu Jie,Shen Shoulin,Wang Sanxi. Simulation of demand of ammunition based on BP neural network algorithm[J]. Journal of System Simulation,2009,21(9):2734-2736.
[2]陈利安,肖明清,程相东. 航空弹药平时消耗量预测模型对比[J]. 弹箭与制导学报,2010,30(3):239-242.
Chen Li’an,Xiao Mingqing,Chen Xiangdong. Comparison of peacetime aviation ammunition consumption forecast models[J]. Journal of Projectiles,Rockets,Missiles and Guidance,2010,30(3):239-242.
[3]Fan Shengli,Bai Yanqi,Zhang Yaokun,et al. Method of ammunition consumption intelligent prediction oriented on equipment combat[J]. Journal of Academy of Armored Force Engineering,2011,25(1):22-27.
[4]孙云聪,万华. Elman和BP网络应用于航空训练弹药需求预测的对比研究[J]. 舰船电子工程,2017,37(3):100-103.
Sun Yuncong,Wan Hua. Comparative study on the application of Elman and BP neural network in aviation training ammunition requirement forecasting[J]. Ship Electronic Engineering,2017,37(3):100-103.
[5]周一鸣,王茜,杨硕. 动态灰色模型在航空弹药维修器材消耗规律中的应用[J]. 物流科技,2017,40(7):135-137.
Zhou Yiming,Wang Qian,Yang Shuo. The application of dynamic gray forecast model on the consumption rule of aviation ammunition spares[J]. Logistics Sci-tech,2017,40(7):135-137.
[6]Cho K,Merrienboer B,Gulcehre C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL]. https://www.researchgate.net/publication/262877889_Learning_Phrase_Representations_using_RNN_Encoder-Decoder_for_Statistical_Machine_Translation,2018-11-27.
[7]Nguyen A,Yosinski J,Clune J. Deep neural networks are easily fooled:High confidence predictions for unrecognizable images[EB/OL]. https://www.researchgate.net/publication/269280482_Deep_Neural_Networks_Are_Easily_Fooled_High_Confidence_Predictions_for_Unrecognizable_Images,2018-11-27.
[8]孙康,李千目,李德强. 基于级联卷积神经网络的人脸检测算法[J]. 南京理工大学学报,2018,42(1):40-47.
Sun Kang,Li Qianmu,Li Deqiang. Face detection algorithm based on cascaded convolutional neural network[J]. Journal of Nanjing University of Science and Technology,2018,42(1):40-47.
[9]Wan Dingsheng,Xiao Yan,Zhang Pengcheng,et al. Hydrological big data prediction based on similarity search and improved BP neural network[C]//2015 IEEE International Congress on IEEE Big Data(BigData Congress). Atlantic City,New Jersey,USA:Stony Brook University,2015:343-350.
[10]Jiang Xudong,Cao Junxing,Cai Ziwei. Prediction of TOC based on pre-stack inversion and double hidden layer BP neural network[C]//AIP Conference Proceedings. Melville,New York,USA:AIP Publishing,2017:1-6.
[11]邹强,王城超,贾汝娜,等. 战时弹药消耗预测方法研究[J]. 兵器装备工程学报,2017,38(9):12-16.
Zou Qiang,Wang Chengchao,Jia Runa,et al. Research on prediction methods of wartime ammunition consumption[J]. Journal of Ordnance Equipment Engineering,2017,38(9):12-16.
[12]齐浩淳,黄大鹏,魏久南,等. 基于BP神经网络的高寒山地弹药消耗需求分析研究[J]. 兵器装备工程学报,2016,37(6):97-101.
Qi Haochun, Huang Dapeng,Wei Jiunan,et al. Demand analyses of ammunition consumption in cold mountain areas based on BP neural network[J]. Journal of Ordnance Equipment Engineering,2016,37(6):97-101.
[13]李松,刘力军,翟曼. 改进粒子群算法优化 BP 神经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 Song,Liu Lijun,Zhai Man. Prediction for short-term traffic flow based on modified PSO optimized BP neural network[J]. Systems Engineering—Theory & Practice,2012,32(9):2045-2049.
[14]宫晓莉,庄新田. 基于改进 PSO 算法的调和稳定跳跃下随机波动模型期权定价与套期保值[J]. 系统工程理论与实践,2017,37(11):2765-2776.
Gong Xiaoli,Zhuang Xintian. Option pricing and hedging for tempered stable jumps driven stochastic volatility models based on improved PSO algorithm[J]. Systems Engineering—Theory & Practice,2017,37(11):2765-2776.

备注/Memo

备注/Memo:
收稿日期:2018-09-07 修回日期:2018-09-14
基金项目:国家自然科学基金(71371051)
作者简介:田德红(1979-),男,博士生,主要研究方向:航空弹药供应保障及其决策支持系统,E-mail:tiandehongseu@126.com; 通讯作者:何建敏(1956-),男,教授,博士生导师,主要研究方向:应急管理与应急系统,E-mail:hejianminseu138@126.com。
引文格式:田德红,何建敏. 基于变异粒子群优化与深度神经网络的航空弹药消耗预测模型[J]. 南京理工大学学报,2018,42(6):716-721.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2018-12-30