基于深层神经网络的备件储备方案决策方法

doi:10.16182/j.issn1004731x.joss.19-FZ0390

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (11): 2238-2246.doi: 10.16182/j.issn1004731x.joss.19-FZ0390

基于深层神经网络的备件储备方案决策方法

张云景, 汤光明, 徐潇雨

中国人民解放军战略支援部队信息工程大学,河南郑州 450001

收稿日期:2019-05-20 修回日期:2019-07-31 出版日期:2019-11-10 发布日期:2019-12-13
作者简介:张云景(1983-),男,河南南阳,博士生,工程师,研究方向为军事信息装备保障与评估;汤光明(1963-),女,湖南常德,博士,教授,研究方向为数据挖掘、信息安全;徐潇雨(1993-),男,江苏连云港,博士生,研究方向为数据挖掘。
基金资助:
国家社科基金军事学(13GJ003-066)

Decision-making Method for Formulating Spares Reserve Scheme Based on Deep Neural Network

Zhang Yunjing, Tang Guangming, Xu Xiaoyu

Information Engineering University, PLA Strategic Support Force, Henan, Zhengzhou 450001, China

Received:2019-05-20 Revised:2019-07-31 Online:2019-11-10 Published:2019-12-13

摘要/Abstract

摘要： 备件分类对于备件储备具有重要意义,是备件决策活动的关键环节。分析了影响备件储备选择的因素,提出了基于深层神经网络的备件储备品种和数量决策方法。对备件属性进行梳理,按照属性影响因素分析,提出2种备件分类方法：(1) 将备件属性重要性展开,对备件属性重要性进行排序,使用一个结构相对简单的深层神经网络依次对各属性实施判决,“不确定储备”的品种将再通过下一属性判决;(2) 将备件的全部属性输入一个结构相对复杂的深层神经网络,深层神经网络依据备件的全属性实施判决。实验证明2种方法分别在时间效率和决策准确性上具有优势,能够为备件储备工作提供决策支撑。

关键词: 备件, 储备方案, 深层神经网络, 属性分析, 决策

Abstract: Spare parts classification is important for spare parts storage and is a key part of spare parts decision-making activities. This paper analyzes the factors affecting the reserve scheme of wartime spares. Then by analyzing the inherent attributes of wartime spares, two methods of spare parts classification are proposed to determine the variety and quantity of wartime spares based on deep neural network: (1) Ranks wartime spares according to their importance. A relatively simple deep neural network is used to analyze every attribute of the wartime spares in turn; (2) Inputs all the attributes of wartime spares into a relatively complex deep neural network to make the decision. The experimental results show the advantages of the two methods in terms of efficiency and accuracy for formulating the reserve scheme of wartime spares.

Key words: spare parts, reserve scheme, deep neural network, attribute analysis, decision making

中图分类号:

TP182

张云景, 汤光明, 徐潇雨. 基于深层神经网络的备件储备方案决策方法[J]. 系统仿真学报, 2019, 31(11): 2238-2246.

Zhang Yunjing, Tang Guangming, Xu Xiaoyu. Decision-making Method for Formulating Spares Reserve Scheme Based on Deep Neural Network[J]. Journal of System Simulation, 2019, 31(11): 2238-2246.

参考文献

[1] 程力. 装备战场抢修备件品种的优化确定模型[J]. 航空维修与工程, 2006, 14(4): 55-57.
Cheng Li.Optimization and determination model of spares variety for equipment battlefield repair[J]. Aviation Maintenance and Engineering, 2006, 14(4): 55-57.
[2] 金正, 张志华, 应新雅, 等. 舰船装备限寿备件满足率评估模型[J]. 指挥控制与仿真, 2015, 37(4): 130-133.
Jin Zheng, Zhang Zhihua, Ying Xinya, et al.Satisfaction Rate Assessment Model of Limited Life Spare Parts for Ship Equipment[J]. Command Control and Simulation, 2015, 37(4): 130-133.
[3] 闫红伟, 康建设, 赵纳新, 等. 战时装备维修备件重要度模糊综合评定方法[J]. 兵工自动化, 2007, 26(2): 16-17.
Yan Hongwei, Kang Jianshe, Zhao Naxin, et al.Fuzzy Comprehensive Evaluation Method for the Importance of Wartime Equipment Maintenance Spare Parts[J]. Ordnance Industry Automation, 2007, 26(2): 16-17.
[4] 孙强, 岳继光. 基于不确定性的故障预测方法综述[J].控制与决策, 2014, 29(5): 769-776.
Sun Qiang, Yue Jiguang.Overview of fault prediction methods based on uncertainty[J]. Control and Decision-making. 2014, 29(5): 769-776.
[5] 张柳, 聂成龙, 张伟, 等. 装备作战单元维修保障建模与仿真[M]. 北京: 国防工业出版社, 2015: 124-132.
Zhang Liu, Nie Chenglong, Zhang Wei, et al.Modeling and Simulation of maintenance support for equipment combat unit [M]. Beijing: National Defense Industry Press, 2015: 124-132.
[6] 胡丹. 平战结合下大型服务系统应急备品备件库存管理研究[D]. 重庆: 重庆大学, 2012: 20-21.
Hu Dan.Research on emergency spare parts inventory management of large-scale service system under the combination of peacetime and wartime [D]. Chongqing: Chongqing University, 2012: 20-21.
[7] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature (S0028-0836), 2015, 521(7553): 436.
[8] Krizhevsky A, Sutskever I, Hinton G E.Imagenet classification with deep convolutional neural networks[C]. Advances in Neural Information Processing Systems, 2012: 1097-1105.
[9] Girshick R.Fast R-CNN[C]. IEEE International Conference on Computer Vision. IEEE, 2015:1440-1448.
[10] Taigman Y, Yang M, Ranzato M A, et al.Deepface: Closing the gap to human-level performance in face verification[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2014: 1701-1708.
[11] Lecun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE(S0018-9219), 1998, 86(11): 2278-2324.
[12] 高学东, 丁军. 一种新的信息系统属性约简算法[J]. 系统工程理论与实践, 2007, 27(1): 131-136.
Gao Xuedong, Ding Jun.A New Attribute Reduction Algorithms for Information Systems[J]. Systems Engineering Theory and Practice, 2007, 27(1): 131-136.
[13] 张帅, 唐金国, 俞金松, 等. 基于属性的舰载机航材备件品种确定方法[J]. 火力与指挥控制, 2015, 40(7): 87-91.
Zhang Shuai, Tang Jinguo, Yu Jinsong, et al.Attribute- based method for determining the types of spare parts for shipboard aircraft[J]. Firepower and Command Control, 2015, 40(7): 87-91.
[14] 张仕念, 刘春和,刘雪峰, 等. 战储备件储备品种选择的属性分析法[J]. 系统工程理论与实践, 2010(10): 118-123.
Zhang Shinian, Liu Chunhe,Liu Xuefeng, et al.Attribute Analysis Method for Selection of Warfare Reserve Varieties[J]. Systems Engineering Theory and Practice, 2010(10): 118-123.
[15] 可荣博, 王铁宁, 宋宁波. 基于遗传BP神经网络的装甲装备器材需求预测[J]. 火力与指挥控制, 2015, 40(6): 99-102.
Ke Rongbo, Wang Tiening, Song Ningbo.Armored equipment demand forecasting based on genetic BP neural network[J]. Firepower and Command Control, 2015, 40(6): 99-102.
[16] 夏国清,陈红召,栾添添. 有限维修渠道下两级维修供应系统性能评估模型[J]. 系统工程理论与实践, 2015: 116-118.
Xia Guoqing, Chen Hongzhao, Luan Tiantian.Performance evaluation model of two-level maintenance supply system under limited maintenance channels[J]. System engineering theory and practice, 2015: 116-118.
[17] 李华, 邵松世, 张光宇, 等. 备件保障的工程实践[M]. 北京: 科学出版社, 2016: 5-11.
Li Hua, Shao Songshi, Zhang Guangyu, et al.Engineering practice of spare parts support [M]. Beijing: Science Press, 2016: 5-11.
[18] 赵建忠, 徐廷学, 尹延涛, 等. 基于改进GM(1,1)模型的导弹备件消耗预测[J]. 装备环境工程, 2012, 9(3): 48-51.
Zhao Jianzhong, Xu Tingxue, Yin Yantao, et al.Missile spare parts consumption prediction based on improved GM(1,1) model[J]. Equipment Environmental Engineering, 2012, 9(3): 48-51.
[19] Lecun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE(S0018-9219), 1998, 86(11): 2278-2324.
[20] 边肇祺. 模式识别[M]. 2版. 北京: 清华大学出版社, 2000.
Bian Zhaoqi.Pattern Recognition [M]. 2 nd Edition. Beijing: Tsinghua University Press, 2000.

基于深层神经网络的备件储备方案决策方法

Decision-making Method for Formulating Spares Reserve Scheme Based on Deep Neural Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	程鹏, 张文柱, 谢书翰, 杨子轩. 基于移动边缘计算的车联网任务卸载研究与仿真[J]. 系统仿真学报, 2022, 34(6): 1304-1311.
[2]	周思锦, 陈棣成, 涂耿, 姜大志. 基于个性化和记忆机制的多模态情感计算模型[J]. 系统仿真学报, 2022, 34(4): 745-758.
[3]	许斌, 闫文卿, 韩卓凡, 何广深, 邓涛, 赵云凯, 亓晋. 基于烟花算法的基站群协作计算卸载模型研究[J]. 系统仿真学报, 2022, 34(2): 354-365.
[4]	吴曦, 孟祥林, 杨镜宇. 下一代战略博弈推演系统研究[J]. 系统仿真学报, 2021, 33(9): 2017-2024.
[5]	贺筱媛, 郭圣明, 吴琳, 李东, 许霄, 李丽. 面向智能化兵棋的认知行为建模方法研究[J]. 系统仿真学报, 2021, 33(9): 2037-2047.
[6]	赵毓, 郭继峰, 颜鹏, 白成超. 稀疏奖励下多航天器规避决策自学习仿真[J]. 系统仿真学报, 2021, 33(8): 1766-1774.
[7]	黄星源, 李岩屹. 基于双Q学习算法的干扰资源分配策略[J]. 系统仿真学报, 2021, 33(8): 1801-1808.
[8]	邵松世, 张志华, 莫小杰. 基于分段函数的威布尔型备件需求量近似算法[J]. 系统仿真学报, 2021, 33(6): 1444-1450.
[9]	曾贲, 房霄, 孔德帅, 宋祥祥, 贾政轩, 林廷宇. 一种数据驱动的对抗博弈智能体建模方法[J]. 系统仿真学报, 2021, 33(12): 2838-2845.
[10]	蔡敏, 王艳, 纪志成. 基于多策略融合量子粒子群算法的MOFFJSP研究[J]. 系统仿真学报, 2021, 33(11): 2615-2626.
[11]	王治莹, 王伟康, 岳朝龙. 政府干预下多种舆情信息交互传播模型与仿真[J]. 系统仿真学报, 2020, 32(5): 956-966.
[12]	王剑, 司徒陈麒, 袁胜强. 基于多主体和前景理论的应急风险决策仿真研究[J]. 系统仿真学报, 2020, 32(3): 353-361.
[13]	邵松世, 阮旻智, 张志华. 基于库存状态的备件初始配置及采购优化模型[J]. 系统仿真学报, 2020, 32(3): 509-517.
[14]	张东俊, 王维平, 黎潇, 张磊, 李小波, 刘国杰. 基于判别矩阵的潜艇作战态势认知决策建模方法[J]. 系统仿真学报, 2020, 32(2): 182-190.
[15]	孙剑, 黄润涵, 李霖, 刘启远, 李宇迪. 智能汽车环境感知与规划决策一体化仿真测试平台[J]. 系统仿真学报, 2020, 32(2): 236-246.