基于时间序列挖掘的合成旅装备维修保障能力预测

doi:10.3969/j.issn.1001-506X.2020.04.19

摘要/Abstract

摘要：

针对现有的预测方法参数较多、精确度不高的问题,采用了时间序列挖掘的方法对合成旅未来一定时期内的装备维修保障能力进行预测。首先建立了指标体系,利用“装备云”平台相关数据对指标及装备维修保障能力随时间变化的序列进行计算;然后对多元时间序列进行线段化拟合、聚类、符号化表达、Apriori关联挖掘,通过差分整合移动平均自回归-支持向量回归组合模型及反向传播神经网络对合成旅装备维修保障能力进行预测,最后通过事例验证了本文所提出的方法。

关键词: 时间序列挖掘, 合成旅, 装备维修保障, Apriori算法, 差分整合移动平均自回归, 支持向量回归机, 预测

Abstract:

In view of the problem that there are too many parameters in the existing prediction method and the accuracy is not high, the time series mining method is used to predict the equipment maintenance support capability of the synthetic brigade in a certain period of time in the future. Firstly, the index system is established and the data of the "equipment cloud" platform is used to calculate the sequence of indicators and equipment maintenance support ability. Then, the segmentation fitting, clustering, symbolic expression and Apriori association mining are applied to the multivariate time series. The autoregressive integrated moving average-support vector regression (ARIMA-SVR) model and back propagation (BP) neural network are used to predict the equipment maintenance support capability of the synthetic brigade. Finally, the proposed method is verified by an example.

Key words: time series mining, synthetic brigade, equipment maintenance support, Apriori algorithm, autoregressive integrated moving average (ARIMA), support vector regression (SVR), prediction

中图分类号:

E919

宋星, 贾红丽, 王谦, 赵汝东. 基于时间序列挖掘的合成旅装备维修保障能力预测[J]. 系统工程与电子技术, 2020, 42(4): 878-886.

Xing SONG, Hongli JIA, Qian WANG, Rudong ZHAO. Prediction of equipment maintenance support capability of synthetic brigade based on time series mining[J]. Systems Engineering and Electronics, 2020, 42(4): 878-886.

图/表 25

表1

图1

图2

图3

表2

图4

表3

图5

表4

表5

图6

表6

表7

图7

图8

图9

表8

表9

表10

图10

图11

表11

表12

图12

图13

参考文献 26

1	FU T C . A review on time series data mining[J]. Engineering Applications of Artificial Intelligence, 2011, 24 (1): 164- 181. doi: 10.1016/j.engappai.2010.09.007
2	ESLING P , AGON C . Time-series data mining[J]. ACM Computing Surveys, 2012, 45 (1): 12- 15.
3	刘强, 秦泗钊. 过程工业大数据建模研究展望[J]. 自动化学报, 2016, 42 (2): 161- 171.
	LIU Q , QIN S Z . Perspectives on big data modeling of process industries[J]. Acta Automatica Sinica, 2016, 42 (2): 161- 171.
4	HIPPERT H S , PEDREIRA C E , SOUZA R C . Neural networks for short-term load forecasting: a review and evaluation[J]. Power Systems, 2001, 16 (1): 44- 55. doi: 10.1109/59.910780
5	NIU D X, KOU B E, ZHANG Y Y. Mid-long term load forecasting using hidden markov model[C]//Proc.of the 3rd International Symposium on Intelligent Information Technology Application: 481-483.
6	MORI H, URANO S. Short-term load forecasting with chaos time series analysis[C]//Proc.of the 3rd Intelligent Systems Applications to Power Systems, 1996: 133-137.
7	YAO S , SONG Y , ZHANG L , et al. Wavelet transform and neural networks for short-term electrical load forecasting[J]. Energy Conversion and Management, 2000, 41 (18): 1975- 1988. doi: 10.1016/S0196-8904(00)00035-2
8	MULLER K R, SMOLA A J, RATSCH G, et al. Predicting time series with support vector machines[C]//Proc.of the Lecture Notes in Computer Science, 1997, 20(2): 999-1004.
9	PAPADAKIS S , THEOCHARIS J , KIARTZIS S , et al. A novel approach to short-term load forecasting using fuzzy neural networks[J]. Power Systems, 1998, 13 (2): 480- 492. doi: 10.1109/59.667372
10	PARK D C , EL-SHARK M , MARKS R , et al. Electric load forecasting using an artificial neural network[J]. Power Systems, 1991, 6 (2): 442- 449. doi: 10.1109/59.76685
11	CHEN B J , CHANG M W , LIN C J . Load forecasting using support vector machines: a study on reunite competition 2001[J]. Power System, 2004, 19 (4): 1821- 1830.
12	范剑锋.时间序列数据特征选择和预测方法研究[D].南京:南京大学, 2016.
	FAN J F. Study of time series feature selection and prediction[D]. Nanjing: Nanjing University, 2016.
13	熊腾飞.基于滑动窗口的多元时间序列数据动态关联规则挖掘[D].哈尔滨:哈尔滨工业大学, 2015.
	XIONG T F. Mining dynamic association rules from multiple time-series data based on sliding window[D]. Harbin: Harbin Institute of Technology, 2015.
14	徐昭邦.多元时间序列关联挖掘算法研究与应用[D].成都:电子科技大学, 2016.
	XU Z B. Research and application of multivariate time series association mining algorithm[D]. Chengdu: University of Electronic Science and Technology, 2016.
15	王振武, 徐慧. 数据挖掘算法原理与实现[M]. 北京: 清华大学出版社, 2015.
	WANG Z W , XU H . Data mining algorithm principle and implementation[M]. Beijing: Tsinghua University Press, 2015.
16	李正欣, 郭建胜, 毛红保, 等. 多元时间序列相似性度量方法[J]. 控制与决策, 2017, 32 (2): 368- 372.
	LI Z X , GUO J S , MAO H B , et al. Similarity measure for multivariate time series[J]. Control and Decision, 2017, 32 (2): 368- 372.
17	MARCO C , ARITZ P , JOSE A L . An efficient approximation to the K-means clustering for massive data[J]. Knowledge-Based Systems, 2016, 117 (6): 56- 69.
18	TIBSHIRANI R , WALTHER G , HASTIE T . Estimating the number of clusters in a data set via the gap statistic[J]. Journal of the Royal Statistical Society, 2000, 63 (2): 411- 423.
19	王枭, 刘雅奇, 齐锋. 基于Apriori算法的作战仿真探索实验控制[J]. 系统工程与电子技术, 2017, 39 (4): 917- 923.
	WANG X , LIU Y Q , QI F . Control method of Apriori based exploratory warfare simulation experiment[J]. Systems Engineering and Electronics, 2017, 39 (4): 917- 923.
20	郑邦祺.基于时间序列的频繁模式挖掘研究与应用[D].成都:电子科技大学, 2016.
	ZHENG B Q. A research and application of mining frequent patterns based on time series[D]. Chengdu: University of Electronic Science and Technology, 2016.
21	EIAD Y , BHATTACHARYYA D K , GHOSH A . Incremental association rule mining: a survey[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2013, 3 (3): 157- 169.
22	RAMAKRISHNAN S , RAKESH A . Mining generalized association rules[J]. Future Generation Computer Systems, 1997, 13 (2): 161- 180.
23	HAN J, KAMBER M.数据挖掘概念与技术[M].范明,孟小峰,译.北京:机械工业出版社, 2012: 245-254.
	HAN J, KAMBER M. Data mining: concepts and techniques[M]. FAN M, MENG X F, trans. Beijing: Machinery Industry Press, 2012: 245-254.
24	AYODELE A A, ADEREMI A, CHARLES A. Stock price prediction using the ARIMA model[C]//Proc.of the 16th International Conference on Computer Modelling and Simulation, 2014: 106-111.
25	FAN G F , PENG L L , HONG W C , et al. Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression[J]. Neurocomputing, 2016, 173 (3): 958- 965.
26	REN T , LIU S , YAN G C , et al. Temperature prediction of the molten salt collector tube using BP neural network[J]. IET Renewable Power Generation, 2016, 10 (2): 212- 214. doi: 10.1049/iet-rpg.2015.0065

一级指标	二级指标	三级指标
装备品质α₁	可用性α₁₁	固有可用度α₁₁₁ 使用可用度α₁₁₂
	维修性α₁₂	维修诊断性α₁₂₁ 维修可达性α₁₂₂
	配套性α₁₃	诊断设备数量α₁₃₁ 维修设备数量α₁₃₂
人力资源α₂	编制结构α₂₁	维修人员在位率α₂₁₁ 指挥人员比例α₂₁₂
	训练水平α₂₂	训练时间α₂₂₁ 训练成绩α₂₂₂
	维修水平α₂₃	修复率α₂₃₁ 平均修复时间α₂₃₂ 维修响应时间α₂₃₃
维修管理α₃	经费使用α₃₁	经费到位率α₃₁₁ 经费利用率α₃₁₂
	信息资源α₃₂	信息采集率α₃₂₁ 技术资料数量α₃₂₂ 信息安全性α₃₂₃
	保障指挥α₃₃	通信能力α₃₃₁ 指挥能力α₃₃₂ 机动能力α₃₃₃
战场环境α₄	自然环境α₄₁	地理条件α₄₁₁ 气候条件α₄₁₂
	人文环境α₄₂	社会化保障力量α₄₂₁ 民社情情况α₄₂₂
	战场建设α₄₃	野外维修设施建设α₄₃₁ 远程技术支援能力α₄₃₂ 野外仓库开设情况α₄₃₃
器材保障α₅	器材平时供应α₅₁	器材配套率α₅₁₁ 器材响应时间α₅₁₂
器材保障α₅	器材战时保障α₅₂	器材储备情况α₅₂₁ 器材保障方案α₅₂₂

时间/周	1	2	3	4	…	51	52
使用可用度	0.989	0.989	0.986	0.985	…	0.997	0.997
维修人员在位率	1.000	1.000	1.000	0.980	…	0.908	0.900
					$ \ddots $		
器材响应时间	1.000	1.000	1.000	1.000	…	1.000	1.000
器材储备情况	0.995	0.995	0.995	0.995	…	0.913	0.913
器材保障方案	0.971	0.971	0.971	0.971	…	0.970	0.970
装备维修保障能力	0.896	0.901	0.906	0.908	…	0.932	0.932

线段序列	k	w
1	-0.278	0.000
2	-0.463	0.000
3	-0.500	0.167
4	-0.500	0.167
5	0.611	0.167
6	0.185	0.333
7	0.556	0.333
8	0.148	0.500
9	-0.815	0.500
10	-1.000	0.500
11	0.907	1.000
12	0.315	0.833

线段序号	聚类	距离
1	2	0.178
2	2	0.088
3	2	0.106
4	2	0.106
5	5	0.087
6	6	0.086
7	5	0.087
8	6	0.086
9	4	0.093
10	4	0.093
11	1	0.000
12	3	0.000

线段序号	符号化表述
1	a1
2	a1
3	a1
4	a1
5	b1
6	b1
7	b1
8	b1
9	a1
10	a1
11	c1
12	b1