基于改进相似性的装备部件剩余寿命预测及经济性储备策略

doi:10.12305/j.issn.1001-506X.2021.09.40

Abstract

Abstract:

Aiming at the problem of the traditional similarity-based remaining useful lifetime (RUL) prediction method does not consider the difference of operating conditions, which affects the accuracy of prediction and the scientific of components reserve strategy, an improved similarity-based RUL prediction and economic reserve strategy of equipment components is proposed. Based on the proposed improved similarity method, distinguishing the operating condition categories of equipment components, the RUL of the service components is predicted by the performance state similarity between the service components and the reference components in each category. Based on RUL prediction results, the economic reserve strategy decision model is established by taking the lowest total cost of equipment components maintenance and reserve as the objective and the resource utilization as the constraint. The differential evolution algorithm is used to optimize the model to obtain the optimal equipment components reserve strategy. The results of numerical example analysis show that the proposed method can effectively improve the accuracy of the RUL prediction and the scientific of components reserve strategy, which has engineering application value.

Key words: remaining useful lifetime (RUL) prediction, reserve strategy, improved similarity, GA-BP (genetice algorithm-back propagation), differential evolution algorithm

CLC Number:

TP311

Yunxiang CHEN, Yi RAO, Zhongyi CAI, Zezhou WANG. Remaining useful lifetime prediction and economic reserve strategy of equipment components based on improved similarity[J]. Systems Engineering and Electronics, 2021, 43(9): 2688-2696.

Figures/Tables 14

Fig.1

Fig.2

Table 1

Table 2

Table 3

Fig.3

Fig.4

Table 4

Table 5

Table 6

Fig.5

Table 7

Table 8

Fig.6

References 19

1	孙博, 康锐, 谢劲松. 故障预测与健康管理系统研究和应用现状综述[J]. 系统工程与电子技术, 2007, 29 (10): 1762- 1767. doi: 10.3321/j.issn:1001-506x.2007.10.042
	SUN B , KANG R , XIE J S . Research and application of the prognostic and health management system[J]. Systems Engineering and Electronics, 2007, 29 (10): 1762- 1767. doi: 10.3321/j.issn:1001-506x.2007.10.042
2	TANG D , MAKIS V , JAFAR I L , et al. Optimal maintenance policy and residual life estimation for a slowly degrading system subject to condition monitoring[J]. Reliability Engineering & System Safety, 2015, 134, 198- 207.
3	PANG Z N , HU C H , SI X S , et al. Nonlinear step-stress accelerated degradation modeling and remaining useful life estimation considering multiple sources of variability[J]. IEEE Access, 2019, 7, 124558- 124575. doi: 10.1109/ACCESS.2019.2933854
4	石慧, 曾建潮. 基于寿命预测的预防性维护维修策略[J]. 计算机集成制造系统, 2014, 20 (5): 1133- 1140.
	SHI H , ZENG J C . Preventive maintenance strategy based on life prediction[J]. Computer Integrated Manufacturing Systems, 2014, 20 (5): 1133- 1140.
5	蒋云鹏, 郭天序, 周东华. 基于剩余使用寿命预测的替换时间和备件订购时间联合决策[J]. 化工学报, 2015, 66 (1): 284- 290.
	JIANG Y P , GUO T X , ZHOU D H . Joint decision on replacement time and spare ordering time based on remaining useful life prediction[J]. CIESC Journal, 2015, 66 (1): 284- 290.
6	张新辉, 王雷震, 赵斐. 基于剩余寿命预测的维修与备件订购联合策略优化[J]. 工业工程, 2020, 23 (4): 106- 113. doi: 10.3969/j.issn.1007-7375.2020.04.014
	ZHANG X H , WANG L Z , ZHAO F . Optimization of a joint maintenance and spare ordering policy based on remaining useful life prediction[J]. Industrial Engineering Journal, 2020, 23 (4): 106- 113. doi: 10.3969/j.issn.1007-7375.2020.04.014
7	刘珍翔. 基于改进GA-SVR的机械关键部件寿命预测及维修策略研究[D]. 重庆: 重庆大学, 2016.
	LIU Z X. Mechanical key component life prediction and main-tenance strategy research based on the improved GA-SVR[D]. Chongqing: Chongqing University, 2016.
8	WANG W B , WANG Z Q , HU C H , et al. An integrated decision model for critical component spare parts ordering and condition-based replacement with prognostic information[J]. Chemical Engineering, 2013, 33, 1063- 1068.
9	YOU M Y , MENG G . A generalized similarity measure for simi-larity-based residual life prediction[J]. Proceedings of the Institution of Mechanical Engineers Part E: Journal of Process Mechanical Engineering, 2011, 225 (3): 151- 160. doi: 10.1177/0954408911399832
10	WANG T Y. Trajectory similarity based prediction for remaining useful life estimation[D]. Cincinnati: University of Cincinnati, 2010: 39-56.
11	宋辰亮. 电子系统可靠性与剩余寿命的实时预测算法设计与实现[D]. 成都: 电子科技大学, 2014.
	SONG C L. The algorithm's design and implementation of relia- bility and remaining life real-time prediction for electronic systems[D]. Chendu: University of Electronic Science and Technology of China, 2014.
12	曹惠玲, 崔科璐, 梁佳旺. 基于多参数融合相似的民航发动机寿命预测[J]. 中国机械工程, 2020, 31 (7): 781- 787. doi: 10.3969/j.issn.1004-132X.2020.07.003
	CAO H L , CUI K L , LIANG J W . Multi-parameter fusion similarity-based method for remaining useful life prediction of civil aviation engines[J]. China Mechanical Engineering, 2020, 31 (7): 781- 787. doi: 10.3969/j.issn.1004-132X.2020.07.003
13	刘畅, 孟晨, 王成, 等. 基于相似性的装备剩余寿命预测研究[J]. 军械工程学院学报, 2014, 26 (5): 13- 17. doi: 10.3969/j.issn.1008-2956.2014.05.004
	LIU C , MENG C , WANG C , et al. Research on similarity-based remaining useful life prediction of equipment[J]. Journal of Ordnance Engineering College, 2014, 26 (5): 13- 17. doi: 10.3969/j.issn.1008-2956.2014.05.004
14	谷梦瑶, 陈友玲, 罗凯. 多退化变量下基于灰色生成率序列的相似性寿命预测方法[J]. 计算机集成制造系统, 2017, 23 (3): 525- 533.
	GU M Y , CHEN Y L , LUO K . Multi-index modeling for similarity-based residual life estimation based on grey generation rate sequence[J]. Computer Integrated Manufacturing Systems, 2017, 23 (3): 525- 533.
15	刘帅君. 基于性能退化数据的航空发动机剩余寿命预测[D]. 成都: 电子科技大学, 2015.
	LIU S J. Remaining useful life prediction of aero-engine based on performance degradation data[D]. Chendu: University of Electronic Science and Technology of China, 2015.
16	WANG T, YU J, SIEGEL D, et al. A similarity-based prognostics approach far remaining useful life estimation of engineered systems[C]//Proc. of the International Conference on Prognostics Health Management, 2008.
17	STORN R , PRICE K . Differential evolution: a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11 (4): 341- 359. doi: 10.1023/A:1008202821328
18	OPARA K R , ARABAS J . Differential evolution: a survey of theoretical analyses[J]. Swarm and Evolutionary Computation, 2019, 44, 546- 558. doi: 10.1016/j.swevo.2018.06.010
19	SHETH P, UMBARKAR D A. Constrained optimization problems solving using evolutionary algorithms: a review[C]//Proc. of the International Conferece on Computational Intelligence and Communication Networks, 2015.

部件	检测序数
部件	0	1	2	…	93	94	…	130	…
1#	0.2	0.189 23	0.201 20	…	0.321 69	0.277 06	…	0.521 29	…
2#	0.2	0.174 08	0.165 88	…	0.205 01	0.223 03	…	0.475 93	…
⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋱	⋮	⋱
239#	0.2	0.243 89	0.235 70	…	0.232 47	0.202 15	…	0.693 71	…
240#	0.2	0.190 77	0.265 59	…	0.214 22	0.201 15	…	0.679 84	…

部件	检测序数
部件	0	1	2	…	93	94	…	104	…
1#	0.2	0.227 03	0.301 49	…	0.267 23	0.278 80	…	0.284 54	…
2#	0.2	0.257 93	0.272 02	…	0.249 36	0.263 80	…	0.306 16	…
⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋱	⋮	⋱
19#	0.2	0.189 81	0.197 84	…	0.361 58	0.374 52	…	0.343 55	…
20#	0.2	0.232 72	0.262 74	…	0.371 94	0.349 39	…	0.437 57	…

更换费用万元/个	订货费用万元/次	缺件损失费用万元/(个·天)	存储费用万元/(个·天)	订货周转期/天	订货周期/天
300	50	5	0.5	60	180

类别	装备关键部件
第1类	3# 7# 20#
第2类	2# 13# 15# 17#
第3类	1# 5# 6# 10# 11# 12# 16#
第4类	4# 8# 9# 14# 18# 19#

部件寿命信息	部件
部件寿命信息	1#	2#	3#	4#	5#	6#	7#	8#	9#	10#
当前运行时间	1 905	1 770	1 635	2 070	2 055	2 190	1 785	1 680	1 755	1 800
全寿命	2 159.860 1	2 183.408 8	1 976.007 5	2 159.975 5	2 191.479 4	2 249.321 1	2 002.891 9	1 840.361 3	1 851.722 3	2 125.121 5
剩余寿命	254.860 1	413.408 8	341.007 5	89.975 5	136.479 4	59.321 1	217.891 9	160.361 3	96.722 3	325.121 5

部件寿命信息	部件
部件寿命信息	11#	12#	13#	14#	15#	16#	17#	18#	19#	20#
当前运行时间	2 040	1 800	1 830	1 800	1 665	1 800	1 665	1 740	1 965	1 725
全寿命	2 187.036 5	2 126.700 5	2 200.093 8	1 897.022 2	2 174.122 4	2 131.968 2	2 175.487 5	1 848.639 4	2 159.980 9	1 985.665 6
剩余寿命	147.036 5	326.700 5	370.093 8	97.022 2	509.122 4	331.968 2	510.487 5	108.639 4	194.980 9	260.665 6

Remaining useful lifetime prediction and economic reserve strategy of equipment components based on improved similarity

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 19

Related Articles 10

Recommended Articles

Metrics

Comments

部件	实际全寿命	M1寿命预测值	M1寿命误差	M1相对误差	M0类别	M0寿命预测值	M0寿命误差	M0相对误差
X1#	2 085	2 198.729 0	113.729 0	5.454 6%	3	2 146.282 1	61.282 1	2.939 2%
X2#	2 145	2 217.297 5	72.297 5	3.370 5%	3	2 072.578 3	-72.421 7	3.376 3%
X3#	2 235	2 334.231 6	99.231 6	4.439 9%	3	2 279.880 5	44.880 5	2.008 1%
X4#	2 175	2 078.030 1	-96.969 9	4.458 4%	2	2 171.868 8	-3.131 2	0.144 0%
X5#	2 160	2 222.457 2	62.457 2	2.891 5%	3	2 235.324 6	75.324 6	3.487 3%
X6#	2 085	2 177.338 5	92.338 5	4.428 7%	1	1 998.018 2	-86.981 8	4.171 8%
X7#	2 055	1 963.261 9	-91.738 1	4.464 1%	2	1 975.448 4	-79.551 6	3.871 1%
X8#	2 190	2 302.372 3	112.372 3	5.131 2%	2	2 275.685 9	85.685 9	3.912 6%
X9#	2 310	2 268.519 1	-41.480 9	1.795 7%	2	2 273.068 5	-36.931 5	1.598 8%
X10#	2 250	2 145.030 0	-104.970 0	4.665 3%	3	2 212.546 5	-37.453 5	1.664 6%
X11#	2 250	2 185.156 9	-64.843 1	2.881 9%	2	2 180.042 0	-69.958 0	3.109 2%
X12#	2 280	2 169.120 0	-110.880 0	4.863 2%	3	2 233.079 4	-46.920 6	2.057 9%
X13#	1 965	2 022.954 3	57.954 3	2.949 3%	1	2 003.813 1	38.813 1	1.975 2%
X14#	2 130	2 114.131 9	-15.868 1	0.745 0%	3	2 143.087 0	13.087 0	0.614 4%
X15#	2 115	2 091.269 2	-23.730 8	1.122 0%	2	2 090.115 9	-24.884 2	1.176 6%
X16#	2 235	2 164.676 1	-70.323 9	3.146 5%	2	2 169.334 9	-65.665 1	2.938 0%
X17#	2 250	2 326.366 5	76.366 5	3.394 1%	2	2 319.636 5	69.636 5	3.095 0%
X18#	2 265	2 184.933 7	-80.066 3	3.534 9%	2	2 193.945 7	-71.054 3	3.137 1%
X19#	2 220	2 327.409 6	107.409 6	4.838 3%	2	2 286.819 9	66.819 9	3.009 9%
X20#	2 175	2 313.083 8	138.083 8	6.348 7%	4	2 233.416 3	58.416 28	2.685 8%

储备策略	订货时间/周期
储备策略	1	2	3	4	5	6	7	8
订货量/个	10	7	3	0	0	0	0	0

储备策略	订货时间/周期
储备策略	9	10	11	12	13	14	15	—
订货量/个	0	0	4	0	8	4	4	—

[1]	Mulai TAN, Dali DING, Lei XIE, Wei DING, Chenghui LYU. UCAV escape maneuvering decision based on fuzzy expert system and IDE algorithm [J]. Systems Engineering and Electronics, 2022, 44(6): 1984-1993.
[2]	Wenhai WU, Xiaofeng GUO, Siyu ZHOU, Li GAO. Self-adaptive differential evolution algorithm with random neighborhood-based strategy and generalized opposition-based learning [J]. Systems Engineering and Electronics, 2021, 43(7): 1928-1942.
[3]	Wenhai WU, Xiaofeng GUO, Siyu ZHOU, Li GAO. Improved differential evolution algorithm for solving weapon-targetassignment problem [J]. Systems Engineering and Electronics, 2021, 43(4): 1012-1021.
[4]	Jun LUO, Jianqiang LIU, Yanan PANG. Multi-threshold image segmentation of 2D Otsu based on neighborhood search JADE [J]. Systems Engineering and Electronics, 2020, 42(10): 2164-2171.
[5]	LI Shihao, DING Yong, GAO Zhenlong. UAV air combat maneuvering decision based on intuitionistic fuzzy game theory [J]. Systems Engineering and Electronics, 2019, 41(5): 1063-1070.
[6]	LIU Han, YIN Cheng-you, LIU Wei. Optimization and design of wideband antenna with adaptive differential evolution algorithm based on hybrid coding method [J]. Systems Engineering and Electronics, 2016, 38(4): 773-777.
[7]	HAN Wei, SU Xi-chao, CHEN Jun-feng. Integrated maintenance support scheduling method of multi carrier aircrafts [J]. Systems Engineering and Electronics, 2015, 37(4): 809-816.
[8]	ZHANG Rui, GAO Hui, ZHANG Tao. Hybird optimization algorithm based on quantum and differential evolution for continuous space optimization [J]. Journal of Systems Engineering and Electronics, 2012, 34(6): 1288-1292.
[9]	LIN Lian-lei, YAN Fang, YANG Jing-li. Use of nested differential evolution algorithm to select microburst model’s parameters [J]. Journal of Systems Engineering and Electronics, 2012, 34(11): 2379-2383.
[10]	BAO Zi-yang, CHEN Ke-song, HE Zi-shu, HAN Chun-lin. Sparse circular arrays method based on modified DE algorithm [J]. Journal of Systems Engineering and Electronics, 2009, 31(3): 497-499.