面向阶段任务的携行器材品种确定方法

doi:10.12305/j.issn.1001-506X.2024.06.23

系统工程与电子技术 ›› 2024, Vol. 46 ›› Issue (6): 2054-2064.doi: 10.12305/j.issn.1001-506X.2024.06.23

• 系统工程 • 上一篇

面向阶段任务的携行器材品种确定方法

吴巍屹, 贾云献, 姜相争, 史宪铭, 刘洁, 刘彬, 董恩志, 朱曦

陆军工程大学石家庄校区装备指挥与管理系, 河北石家庄 050003

收稿日期:2022-12-06 出版日期:2024-05-25 发布日期:2024-06-04
通讯作者: 史宪铭
作者简介:吴巍屹(1982—), 女, 副教授, 博士, 主要研究方向为维修保障资源优化配置、装备保障指挥
贾云献(1963—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为维修保障资源优化配置、维修决策建模
姜相争(1984—), 男, 工程师, 博士, 主要研究方向为军事装备学
史宪铭(1975—), 男, 副教授, 硕士研究生导师, 博士, 主要研究方向为装备保障理论与应用
刘洁(1981—), 女, 讲师, 博士, 主要研究方向为军事装备学、装备保障指挥
刘彬(1984—), 男, 讲师, 博士, 主要研究方向为维修工程、军事装备学
董恩志(1997—), 男, 博士研究生, 主要研究方向为维修工程
朱曦(1997—), 男, 博士研究生, 主要研究方向为维修工程、基于性能的保障
基金资助:
国家自然科学基金(71871220)

Method for determining for carrying material varieties of stage task

Weiyi WU, Yunxian JIA, Xiangzheng JIANG, Xianming SHI, Jie LIU, Bin LIU, Enzhi DONG, Xi ZHU

Department of Equipment Command and Management, Army Engineering University Shijiazhuang Campus, Shijiazhuang 050003, China

Received:2022-12-06 Online:2024-05-25 Published:2024-06-04
Contact: Xianming SHI

摘要/Abstract

摘要：

维修器材是有效实施维修保障的物质基础, 携行器材品种确定是开展维修器材携行决策的关键。针对执行阶段任务武器装备维修器材品种多、影响因素复杂且关联关系不明确造成的携行器材品种确定困难的现实问题, 提出了一种将改进稀疏核主成分分析(sparse kernel principal component analysis, SKPCA)算法与长短时记忆(long short-term memory, LSTM)神经网络模型相结合的阶段任务携行器材品种确定方法。在分析与任务阶段时序相关的携行器材影响因素及特征指标的基础上, 运用基于弹性惩罚的SKPCA降维算法, 对器材特征进行降维分析并得到低维稀疏特征向量, 通过缩减数据容量增强特征指标的可解释性; 运用混沌序列改进花授粉算法(flower pollination algorithm, FPA)优化LSTM超参数, 构建混沌FPA-LSTM预测模型, 精准进行携行器材品种确定。通过对演习携行器材品种确定算例分析验证了所提方法的科学性和可行性。

关键词: 携行器材, 阶段任务, 稀疏核主成分分析, 影响因素分析, 花授粉算法, 长短时记忆神经网络

Abstract:

Maintenance material is the basis for effective implementation of maintenance support. It is the key to make decision of carrying material variety. In order to solve the problem which is difficult to determine the carrying material varieties due to various types of material in the stage task, the complex influencing factors and unclear association relationchip, a method for determining carrying material varieties of stage task combined with the improved sparse kernel principal component analysis (SKPCA) and long short-term memory (LSTM) neural network model is proposed. On the basis of analyzing the influencing factors and characteristic indicators of stage task carrying material, an improved SKPCA dimension reduction method based on elastic penalty is proposed which can reduce the material features dimensionality and obtain low-dimensional sparse feature vectors to enhance the data interpretability. The chaotic sequence is used to improve the flower pollination algorithm (FPA) which optimizing the LSTM hyperparameters and the chaotic FPA-LSTM prediction model is constructed. Through the example analysis by the exercise, the scientificity and feasibility of the proposed method are verified.

Key words: carrying material, stage task, sparse kernel principal component analysis (SKPCA), influencing factor analysis, flower pollination algorithm (FPA), long short-term memory (LSTM) neural network

中图分类号:

吴巍屹, 贾云献, 姜相争, 史宪铭, 刘洁, 刘彬, 董恩志, 朱曦. 面向阶段任务的携行器材品种确定方法[J]. 系统工程与电子技术, 2024, 46(6): 2054-2064.

Weiyi WU, Yunxian JIA, Xiangzheng JIANG, Xianming SHI, Jie LIU, Bin LIU, Enzhi DONG, Xi ZHU. Method for determining for carrying material varieties of stage task[J]. Systems Engineering and Electronics, 2024, 46(6): 2054-2064.

图/表 17

图1

表1

图2

图3

图4

表2

表3

图5

表4

图6

表5

图7

图8

表6

表7

图9

表8

参考文献 31

1	阮旻智, 傅健, 周亮, 等. 面向任务的作战单元携行备件配置优化方法研究[J]. 兵工学报, 2017, 38 (6): 1178- 1185. doi: 10.3969/j.issn.1000-1093.2017.06.018
	RUAN M Z , FU J , ZHOU L , et al. Configuration and opimization method of carrying spares of mission-oriented combat unit[J]. Acta Armamentarii, 2017, 38 (6): 1178- 1185. doi: 10.3969/j.issn.1000-1093.2017.06.018
2	FRANDSEN C S , NIELSEN M M , CHAUDHURI A , et al. In search for classification and selection of spare parts suitable for additive manufacturing: a literature review[J]. International Journal of Production Research, 2020, 58 (4): 970- 996. doi: 10.1080/00207543.2019.1605226
3	吕金建, 贾长治, 杨建春. 基于模糊综合评判法的装备备件应急制造性评价[J]. 火炮发射与控制学报, 2018, (1): 82-86, 91.
	LYU J J , JIA C Z , YANG J C . Emergency manufacturing evaluation of equipment spare parts based on fuzzy comprehensive evaluation method[J]. Journal of Gun Launch & Control, 2018, (1): 82-86, 91.
4	苏小波. 陆军合成旅战时装备维修保障筹划建研究[D]. 石家庄: 陆军工程大学, 2021.
	SU X B. Research on the planning and establishment of wartime equipment maintenance support for the army's composite brigade[D]. Shijiazhuang: Army Engineering University Shijiazhuang Campus, 2021.
5	PRACHUABSUPAKIJ W. ABC classification in spare parts for inventory management using ensemble techniques[C]//Proc. of the IEEE Asia Pacific Conference on Circuits and Systems, 2019: 333-336.
6	肖丽丽, 靳峰雷, 谷继品. 控制棒驱动机构备件数量优化方法[J]. 原子能科学技术, 2020, 54 (7): 1273- 1278.
	XIAO L L , JIN F L , GU J P . Opitimization method for spare part quantity of control rod drive mechanism[J]. Atomic Energy Science and Technology, 2020, 54 (7): 1273- 1278.
7	SHEIKH-ZADEH A , SCOTT M A , ENAYATY-AHANGAR F . The role of prescriptive data and non-linear dimension-reduction methods in spare part classification[J]. Computers & Industrial Engineering, 2023, 175 (8): 1089- 1102.
8	ZHANG X L , TAN Y J , YANG Z W . Resource allocation optimization of equipment development task based on MOPSO algorithm[J]. Journal of Systems Engineering and Electronics, 2019, 30 (6): 1132- 1143. doi: 10.21629/JSEE.2019.06.09
9	季嘉伟, 孙国文, 罗佳伟. 基于模糊综合评判的电源车战场抢修备件品种研究[J]. 装备制造技术, 2017, (7): 214- 216. doi: 10.3969/j.issn.1672-545X.2017.07.072
	JI J W , SUN G W , LUO J W . Fuzzy comprehensive evaluation of BDAR spare parts varieties of aircraft power vehicle[J]. Equipment Manufacturing Technology, 2017, (7): 214- 216. doi: 10.3969/j.issn.1672-545X.2017.07.072
10	杨超, 侯兴明, 陈小卫, 等. 新型小规模装备备件品种确定的犹豫模糊粗糙集决策方法[J]. 国防科技大学学报, 2022, 44 (3): 201- 210.
	YAHG C , HOU X M , CHEN X W , et al. Hesitant fuzzy rough set decision-making method for determining spare parts variety of nem small-scale equipment[J]. Journal of National University of Defense, 2022, 44 (3): 201- 210.
11	赵力, 史贤俊, 张志龙. 基于AHP和灰色局势决策模型的装备测试资源选择和优化配置[J]. 导航定位与授时, 2022, (3): 92- 99.
	ZHAO L , SHI X J , ZAHNG Z L . Method of resourse selection and optimal allocetion based on AHP and Grey situation decision model[J]. Navigation Positioning & Timing, 2022, (3): 92- 99.
12	杨超, 侯兴明, 秦海峰, 等. 基于限制优势关系的航天装备备件品种确定[J]. 系统工程与电子技术, 2022, 44 (2): 584- 591.
	YANG C , HOU X M , QIN H F , et al. Variety determination of spare parts for space equipmeng based on the relationship of limitied advantages[J]. Systems Engineering and Electronics, 2022, 44 (2): 584- 591.
13	于晓琳, 张磊, 杨奕飞, 等. 基于改进优劣解距离法和价值工程的舰船备件配置[J]. 科学技术与工程, 2021, 21 (30): 13170- 13176. doi: 10.3969/j.issn.1671-1815.2021.30.051
	YU X L , ZHANG L , YANG Y F , et al. Warship spare parts allocation based on improved technique for order preference by similarity to ideal solution and value engineering[J]. Science Technology and Engineering, 2021, 21 (30): 13170- 13176. doi: 10.3969/j.issn.1671-1815.2021.30.051
14	杨帆, 王生凤, 王铁宁, 等. 基于全过程的备件需求预测综述[J]. 装甲兵工程学院学报, 2018, 32 (3): 25- 29. doi: 10.3969/j.issn.1672-1497.2018.03.005
	YANG F , WANG S F , WANG T N , et al. Review on spare parts forecasting based on whole process management[J]. Journal of Armored Forces, 2018, 32 (3): 25- 29. doi: 10.3969/j.issn.1672-1497.2018.03.005
15	林琳, 陈湘芝, 钟诗胜. 基于特征合成的周期性备件需求预测方法[J]. 哈尔滨工业大学学报, 2016, 48 (7): 27- 32.
	LIN L , CHEN X Z , ZHONG S S . Demand forecasting method for periodic spare parts based on feature synthesis[J]. Journal of Harbin Institute of Technology, 2016, 48 (7): 27- 32.
16	CAO W B , SONG W Y , HAN Y C , et al. Spare parts demand forecasting: a review[J]. Journal of Donghua University (English Edition), 2016, 33 (2): 340- 344.
17	PINCE C , TURRINI L , MEISSNER J . Intermittent demand forecasting for spare parts: a critical review[J]. Omega, 2021, 105 (7): 102513- 102535.
18	RATNAYAKE R M C. Consequence classification based spare parts evaluation and control in the petroleum industry[C]//Proc. of the IEEE International Conference on Industrial Engineering and Engineering Management, 2019: 1204-1210.
19	CAO L J , CHUA K S , CHONG W K , et al. A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine[J]. Neurocomputing, 2003, 55 (1/2): 321- 336.
20	张明蓝, 孙林夫, 邹益胜. 基于深度网络的汽车配件两级备件决策[J]. 计算机集成制造系统, 2019, 11 (31): 2238- 2246.
	ZHANG M L , SUN L F , ZOU Y S . Two-level spare parts decision for auto parts based on deep network[J]. Computer Integrated Manufacturing Systems, 2019, 11 (31): 2238- 2246.
21	MEMARZADEH G , KEYNIA F . Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm[J]. Electric Power Systems Research, 2021, 192 (10): 106995- 107016.
22	王雷. 装备战场抢修时间计划研究[D]. 长沙: 国防科学技术大学, 2010.
	WANG L. Equipment battlefield emergency repair time planning study[D]. Changsha: National University of Defense Technology, 2010.
23	STOLL J , KOPF R , SCHNEIDER J , et al. Criticality analysis of spare parts management: a multi-criteria classification regarding a cross-plant central warehouse strategy[J]. Production Engineering, 2015, 9 (2): 225- 235. doi: 10.1007/s11740-015-0602-2
24	SUN Y , WEI Q , ZHUANG Z L , et al. An adaptive fault detection and root-cause analysis scheme for complex industrial processes using moving window KPCA and information geometric causal inference[J]. Journal of Intelligent Manufacturing, 2021, 32 (7): 2007- 2021. doi: 10.1007/s10845-021-01752-9
25	杜春, 孙即祥, 周石琳, 等. 基于稀疏表示和非参数判别分析的降维算法[J]. 国防科技大学学报, 2013, 35 (2): 143- 147.
	DU C , SUN J X , ZHOU S L , et al. Dimensionality reduction based on sparse representation and nonparametric discriminant analysis[J]. Journal of Nonal University of Defense Technology, 2013, 35 (2): 143- 147.
26	TIPPING M E. Sparse kernel principal component analysis[C]//Proc. of the Advances in Neural Information Processing Systems 13, Papers from Neural Information Processing Systems, 2000.
27	王双川, 贾希胜, 胡起伟, 等. 合成部队多阶段作战任务成功概率仿真评估[J]. 系统工程与电子技术, 2021, 43 (3): 763- 772.
	WANG S C , JIA X S , HU Q W , et al. Success probability simulation evaluation of phased combat mission of the synthetic force[J]. Systems Engineering and Electronics, 2021, 43 (3): 763- 772.
28	YANG X S. Flower pollination algorithm for global optimization[C]//Proc. of the International Conference on Unconventional Computing and Natural Computation, 2012.
29	肖辉辉, 万常选. 基于多策略的改进花授粉算法[J]. 软件学报, 2021, 32 (10): 3152- 3175.
	XIAO H H , WANG C X . Improved flower pollination algorithm based on muilti-strategy[J]. Journal of Software, 2021, 32 (10): 3152- 3175.
30	HUANG Y , LI J P , WANG P . Unusual phenomenon of optimizing the Griewank function with the increase of dimension[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20 (10): 45- 62.
31	王强, 贾希胜, 程中华, 等. 基于改进的局部保持投影的战时备件分类[J]. 系统工程与电子技术, 2020, 42 (1): 133- 140.
	WANG Q , JIA X S , CHENG Z H , et al. Classification of spare parts based on improved local preserving projection in wartime[J]. Systems Engineering and Electronics, 2020, 42 (1): 133- 140.

任务	阶段时序	阶段任务	部件类型
综合行动	1	战斗准备	部件1部件2部件3
综合行动	2	机动	部件1部件2部件3
火力打击	3	火力压制	部件1部件2部件3部件4部件5
火力打击	4	火力支援	-
侦察	5	武装侦察	-
侦察	6	-	-
$\vdots$	7	$\vdots$	$\vdots$

器材品种	可靠性/h	关键性	维修复杂性	可获取性	单价/元	使用时间/h	供应周转时间/h	体积/m³	质量/kg	单装用数	维修时间/min	使用环境要求	携行结果
器材1	91	1	1	0	500	50	4	2.4	6.3	5	25	1	1
器材2	144	1	1	0	450	120	3	1.5	3.6	4	20	1	1
器材3	888	2	1	0	900	250	2	3.23	2.2	1	45	3	0
器材4	274	3	1	1	800	75	1	1.21	1.33	3	40	4	0
器材5	750	1	1	1	727	100	2	2.97	0.91	1	45	2	0
$\vdots$

向量	PCA			KPCA			改进SKPCA
向量	PCA1	PCA2	PCA3	PCA1	PCA2	PCA3	PCA1	PCA2	PCA3
X1	-0.40	0.22	-0.21	-0.39	0.48	-0.07	-0.12	0.00	-0.04
X2	-0.41	0.19	-0.24	-0.39	0.47	0.13	-0.04	-0.07	0.00
X3	0.12	0.54	0.14	0.02	0.35	0.30	-0.03	0.00	-0.19
X4	-0.17	0.46	0.35	-0.02	-0.21	0.40	0.00	0.16	0.00
X5	-0.06	-0.17	0.48	0.12	-0.34	0.09	-0.11	0.09	0.00
X6	-0.28	-0.01	0.48	-0.38	0.08	0.34	-0.02	0.03	-0.15
X7	-0.40	-0.19	0.25	-0.47	-0.50	0.51	0.24	0.00	0.19
X8	-0.29	-0.19	-0.24	0.27	0.31	-0.33	-0.11	0.00	-0.41
X9	-0.36	0.02	-0.21	-0.37	0.30	-0.38	0.31	-0.15	0.00
X10	-0.38	-0.25	-0.12	-0.43	-0.52	-0.47	0.00	0.00	0.09
方差/%	32.40	18.30	14.40	40.80	19.20	15.30	52.76	23.78	10.72
累计方差/%	32.40	50.70	65.10	40.80	50.00	75.30	52.76	76.54	87.26

主成分	PCA1	PCA2	PCA3	PCA4	PCA5
X1	-0.12	0.00	-0.04	0.00	0.23
X2	-0.04	-0.07	0.00	-0.06	0.00
X3	-0.03	0.00	-0.19	0.04	0.00
X4	0.00	0.16	0.00	0.16	-0.35
X5	-0.11	0.09	0.00	0.00	0.18
X6	-0.02	0.03	-0.15	0.00	0.00
X7	0.24	0.00	0.19	0.37	0.00
X8	-0.11	0.00	-0.41	0.18	0.00
X9	0.31	-0.15	0.00	0.00	0.01
X10	0.00	0.00	0.09	0.15	-0.28
方差/%	52.76	23.78	10.72	6.86	0.90
累计方差/%	52.76	76.54	87.26	94.12	95.02

模型	降维维数	决策准确率	MAE	RMSE	算法时间/s
PCA-LSTM	9	0.78	0.136	0.382	30.27
KPCA-LSTM	6	0.81	0.131	0.374	27.61
改进SKPCA-LSTM	5	0.88	0.126	0.355	28.79

面向阶段任务的携行器材品种确定方法

Method for determining for carrying material varieties of stage task

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 31

相关文章 7

编辑推荐

Metrics

本文评价

测试集(器材品种)	器材1	器材2	…	器材7	…	器材50
预测结果	0	1	$\vdots$	0	$\vdots$	1
实际结果	0	1	$\vdots$	1	$\vdots$	0
MAE			0.14
RMSE			0.374
决策准确率			0.87

模型算法	隐含层数	隐含层神经元数	学习率	MAE	RMSE
GA-LSTM	2	64/103	0.013 3	0.156	0.395
FPA-LSTM	2	42/88	0.026 1	0.134	0.366
混沌FPA-LSTM	2	68/80	0.017 5	0.126	0.355

分类算法	决策准确率	算法计算时间/s
DT	0.74	18.33
KDE-LPP-SVM	0.92	103.76
混沌FPA-LSTM	0.87	23.59

[1]	李翔宇, 黄洪钟, 熊晓燕. 考虑冲击与阶段备份的多阶段任务系统可靠性建模[J]. 系统工程与电子技术, 2023, 45(7): 2280-2286.
[2]	王鹏, 孙紫荆, 张帆, 肖国松. 考虑概率型共因失效的多阶段任务系统可靠性分析模型[J]. 系统工程与电子技术, 2022, 44(12): 3887-3898.
[3]	李孝鹏, 黄洪钟, 李福秋. 基于PRA的复杂航天多阶段任务系统可靠性分析[J]. 系统工程与电子技术, 2019, 41(9): 2141-2147.
[4]	闫华, 汪贻生, 王锐淇, 刘波, 郭立卿, 肖骅. 基于GPU的大规模多阶段任务系统可靠性并行计算方法[J]. 系统工程与电子技术, 2019, 41(1): 215-222.
[5]	郭小威, 李保刚, 滕克难. 面向多阶段任务可用度的装备群维修决策模型[J]. 系统工程与电子技术, 2016, 38(3): 582-587.
[6]	钟季龙, 郭基联, 王卓健, 邵帅. 装备体系多阶段任务可靠性高效解析算法[J]. 系统工程与电子技术, 2016, 38(1): 232-238.
[7]	许双伟，武小悦. 航天测控任务可靠性的混合分析方法[J]. Journal of Systems Engineering and Electronics, 2013, 35(3): 667-671.