基于改进的局部保持投影的战时备件分类

doi:10.3969/j.issn.1001-506X.2020.01.18

Abstract

Abstract:

In order to improve the support efficiency of combined army spare parts in wartime, it is necessary to classify them effectively in order to carry out the pre-storage and pre-configuration of spare parts. Aiming at the practical problems of many kinds of spare parts, strong timeliness and complex factors affecting the classification, a method of spare parts classification based on improved local preservation projection is proposed. Firstly, according to the influencing factors of the classified reserve of wartime spare parts, it is taken as the characteristic index of the spare parts classification. Secondly, the dimension reduction method of improved local preserving projection is used to reduce the dimension of the original feature data of spare parts, and low-dimensional feature vectors are obtained. Then the classifier of the support vector machine (SVM) is used to classify the low dimensional data. The kernel function parameters of the SVM are optimized by quantum particle swarm optimization to improve the accuracy of spare parts classification. The dimension reduction and classifier parameters are obtained when the spare parts classification accuracy is optimized. Finally, the feasibility and rationality of the model are verified by an example of the classification of spare parts of military manoeuvre equipment. By comparing and analyzing other classification methods, it shows that the method can better solve the problem of spare parts classification in wartime.

Key words: local preserving projection algorithm, quantum particle swarm optimization-support vector machines (QSPO-SVM), wartime, spare parts classification

CLC Number:

Qiang WANG, Xisheng JIA, Zhonghua CHENG, Shuangchuan WANG, Yunfei MA. Classification of spare parts based on improved local preserving projection in wartime[J]. Systems Engineering and Electronics, 2020, 42(1): 133-140.

Figures/Tables 8

Table 1

Fig.1

Table 2

Fig.2

Table 3

Fig.3

Table 4

Table 5

References 23

1	周一鸣, 王茜, 荣鹏辉, 等. 基于灰色局势决策的航空弹药保障装备备件品种确定方法[J]. 舰船电子对抗, 2017, 40 (5): 56- 60.
	ZHOU Y M , WANG Q , RONG P H , et al. Determination method of spare part varieties for air ammunition support equipment based on grey situation decision-making[J]. Shipboard Electronic Countermeasure, 2017, 40 (5): 56- 60.
2	卜新旺, 张杨, 杨一凡. 基于综合模糊评价法的修复性维修备件确定优化研究[J]. 价值工程, 2016, 35 (30): 125- 128.
	BU X W , ZHANG Y , YANG Y F . Research on the variety and quantity optimization of repair maintenance spare parts based on comprehensive fuzzy evaluation method[J]. Value Engineering, 2016, 35 (30): 125- 128.
3	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, 45 (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, 45 (7): 214- 216. doi: 10.3969/j.issn.1672-545X.2017.07.072
4	李艳, 徐文隆, 陈胜远, 等. 基于ABC分类法的气象装备备件分类研究[J]. 价值工程, 2018, 37 (2): 8- 10.
	LI Y , XU W L , CHEN S Y , et al. Research on classification of parts and accessories of meteorological equipment based on ABC classification[J]. Value Engineering, 2018, 37 (2): 8- 10.
5	刘琦, 冯向前, 张华荣. 基于相似度的犹豫模糊语言多属性决策方法[J]. 统计与决策, 2017, 33 (19): 42- 46.
	LIU Q , FENG X Q , ZHANG H R . Multiattribute decision-making method of hesitant fuzzy language based on similarity[J]. Statistics and Decision, 2017, 33 (19): 42- 46.
6	MAJDAR R S , GHASSEMIAN H . A probabilistic SVM approach for hyperspectral image classification using spectral and texture features[J]. International Journal of Remote Sensing, 2017, 38 (15): 4265- 4284. doi: 10.1080/01431161.2017.1317941
7	ZHANG W , ZHAO D , ZHI C , et al. Deep learning and SVM-based emotion recognition from Chinese speech for smart affective services[J]. Software-Practice & Experience, 2017, 47 (8): 1127- 1138.
8	ZHANG B . Distributed SVM face recognition based on Hadoop[J]. Cluster Computing, 2017, (4): 1- 8.
9	WU J , YANG H . Linear regression-based efficient SVM learning for large-scale classification[J]. IEEE Trans.on Neural Networks & Learning Systems, 2017, 26 (10): 2357- 2369.
10	JIAN L , SHEN S , LI J , et al. Budget online learning algorithm for least squares SVM[J]. IEEE Trans.on Neural Networks & Learning Systems, 2017, 28 (9): 2076- 2087.
11	ZIMING M A , ZHONG H , XIE L , et al. Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model:an ERCOT case study[J]. Journal of Modern Power Systems & Clean Energy, 2018, 6 (2): 281- 291.
12	HU Q , CHAKHAR S , SIRAJ S , et al. Spare parts classification in industrial manufacturing using the dominance-based rough set approach[J]. European Journal of Operational Research, 2017, 262 (3): 1136- 1163. doi: 10.1016/j.ejor.2017.04.040
13	PRUSTY M R , JAYANTHI T , CHAKRABORTY J , et al. Feasibility of ANFIS towards multiclass event classification in PFBR considering dimensionality reduction using PCA[J]. Annals of Nuclear Energy, 2017, 99, 311- 320. doi: 10.1016/j.anucene.2016.09.015
14	LI X , ZHAO X D , PU W . Battle damage-oriented spare parts forecasting method based on wartime influencing factors analysis and ε-support vector regression[J]. International Journal of Production Research, 2019, 6, 1- 21.
15	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
16	ZHAI Y , ZHANG L , WANG N , et al. A modified locality-preserving projection approach for hyperspectral image classification[J]. IEEE Geoscience & Remote Sensing Letters, 2017, 13 (8): 1059- 1063.
17	XU Y , ZHONG A , YANG J , et al. LPP solution schemes for use with face recognition[J]. Pattern Recognition, 2010, 43 (12): 4165- 4176. doi: 10.1016/j.patcog.2010.06.016
18	TANG X , XU A . Multi-class classification using Kernel density estimation on K-nearest neighbours[J]. Electronics Letters, 2016, 52 (8): 600- 602. doi: 10.1049/el.2015.4437
19	ABUELLA H , OZDEMIR M K . Automatic modulation classification based on Kernel density estimation[J]. Canadian Journal of Electrical & Computer Engineering, 2016, 39 (3): 203- 209.
20	杨望灿, 张培林, 张云强. 基于邻域自适应局部保持投影的轴承故障诊断模型[J]. 振动与冲击, 2014, 33 (4): 39- 44.
	YANG W C , ZHANG P L , ZHANG Y Q . Bearing fault diagnosis model based on neighborhood adaptive locality preserving projections[J]. Journal of Vibration and Shock, 2014, 33 (4): 39- 44.
21	JING C , HOU J . SVM and PCA based fault classification approaches for complicated industrial process[J]. Neurocomputing, 2015, 167 (C): 636- 642.
22	GUO X , PENG C , ZHANG S , et al. A novel feature extraction approach using window function capturing and QPSO-SVM for enhancing electronic nose performance[J]. Sensors, 2015, 15 (7): 15198- 15217. doi: 10.3390/s150715198
23	CHEN H L , YANG B , WANG S J , et al. Towards an optimal support vector machine classifier using a parallel particle swarm optimization strategy[J]. Applied Mathematics & Computation, 2014, 239 (8): 180- 197.

备件分类类别	库存策略
不储备备件	——
基于状态的储备备件	(S-1, S)
部件级储备备件	经济订货批量 (economic order quantity, EOQ)
系统级储备备件	综合装备可用度要求进行库存补充

序号	备件分类指标	偏好	数据类型	备注
1	备件故障模式严酷程度	Gain	Ordinal	通过装备的损伤模式及影响(damage mode and effect analysis，DMEA)分析,可根据单元损伤模式得出的严酷程度进行确定,由高到低分为:1-4级
2	备件满足率	Gain	Continuous	根据战时装备保障任务的要求,得到备件供应量与需求量的比值
3	备件可替换性	Gain	Ordinal	指备件是否能替代使用,不能用“0”进行标记,能用“1”进行标记
4	仓库数量	Cost	Continuous	指后方仓库中,备件储备的仓库数量
5	备件周转时间/h	Gain	Continuous	指备件由后方仓库运输到装备使用分队的平均时间
6	备件消耗数量/个	Gain	Continuous	预测一次战役中,备件消耗的数量
7	备件的体积/m³	Cost	Continuous	备件的体积
8	备件储备环境要求	Cost	Ordinal	指备件在仓库储备时的环境要求,如温度、湿度等,根据要求等级由高到低为:1-4级
9	限时可更换性	Gain	Ordinal	指备件是否能在本级限定的小修时间内,完成更换维修任务,能进行更换用“1”进行标记,否则记为“0”
10	备件储备费用/元	Cost	Continuous	指备件在仓库储备的总费用,包括购置、管理、储存等费用之和
11	备件维修能力	Gain	Ordinal	指备件是否能在本级进行维修,能在本级维修单元进行维修,用“1”标记,否则用“0”标记
12	易损伤程度	Gain	Ordinal	指战时备件损伤的难易程度,根据装备使用分队演习等历史数据确定其难易程度,由高到低分为1-4级

序号	指标1	指标2	指标3	指标4	指标5	指标6	指标7	指标8	指标9	指标10	指标11	指标12	种类
1	1	0.95	0	1	38	2	2.3	1	1	5 000	1	1	C
2	1	0.92	0	1	30	5	1.5	1	1	18 000	1	1	C
3	2	0.68	0	7	26	136	0.9	4	1	600	0	3	B
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮

序号	降维方法	降维的维数	分类准确率	算法计算时间/s
1	PCA	4	0.82	348.442
2	LPP	8	0.88	421.533
3	KDE-LPP	6	0.92	458.288

序号	分类方法	备件分类查全率(P)				备件分类查准率(R)				备件分类准确率
序号	分类方法	N	C	B	X	N	C	B	X	备件分类准确率
1	DT	0.902 6	0.923 3	0.693 6	0.714 3	0.889 6	0.723 6	0.583 9	0.630 2	0.783 6
2	KNN	0.925 3	0.875 6	0.816 2	0.793 5	0.835 6	0.902 3	0.756 2	0.864 3	0.837 4
3	SVM	0.965 3	0.935 6	0.834 6	0.812 7	0.957 8	0.899 6	0.838 8	0.809 3	0.895 9
4	QPSO-SVM	0.954 1	0.965 7	0.884 8	0.892 6	0.964 3	0.895 1	0.895 9	0.905 6	0.920 2

Classification of spare parts based on improved local preserving projection in wartime

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 23

Related Articles 1

Recommended Articles

Metrics

Comments