基于选择性维修的装备群动态健康管理决策

doi:10.12305/j.issn.1001-506X.2024.08.23

摘要/Abstract

摘要：

针对现有故障预测与健康管理(prognostics and health management, PHM)系统难以给出实时、动态健康管理决策结果的问题，综合考虑不完善维修、多资源约束(人力、时间、成本等)、备件订购、任务规划等因素，基于选择性维修理论，建立了动态健康管理决策模型，得到了最优方案，包括部件最优维修对策、维修任务分配、备件订购数量、最优任务规划等。最后，结合算例，分析了维修人员数量、备件数量、任务规划等因素对动态健康管理决策结果的影响，验证了所提模型的有效性，对于指导装备健康管理实践、提升保障质效具有重要的意义。

关键词: 故障预测与健康管理, 健康管理决策, 选择性维修, 装备群, 动态决策, 剩余寿命预测

Abstract:

Prognostics and health management (PHM), as an advanced predictive maintenance method, has become a hot research topic of equipment support. To solve the problem that the existed PHM systems cannot yield dynamic and timely results of health management decision-making, a novel selective maintenance (SM) based model was developed to obtain the optimal decisions, including the optimal maintenance strategies, maintenance task assignment, quantity of spare part ordered, optimal equipment task scheduling, etc. In this model, the imperfect maintenance options, multiple resource constraints, such as personnel, time, cost, etc., spare part ordering and task scheduling, were considered simultaneously. Based on the theory of selective maintenance, a dynamic health management decision-making model was established, and an optimal scheme, which includes optimal maintenance strategies, maintenance task scheduling, number of spare spart ordering, and optimal task planning, is obtained. Finally, an illustrative example was presented to verify the effectiveness of the proposed model, and the effect of the maintenance personnel number, spare part number and mission scheduling on decisions were analyzed. The results showed that the proposed model was of great significance for supporting equipment health management practice and improving the maintenance quality and effectiveness.

Key words: prognostics and health management (PHM), health management decision-making, selective maintenance, fleet, dynamic decision-making, remaining useful life prediction

中图分类号:

曹文斌, 马维宁, 贾希胜. 基于选择性维修的装备群动态健康管理决策[J]. 系统工程与电子技术, 2024, 46(8): 2760-2769.

Wenbin CAO, Weining MA, Xisheng JIA. Dynamic health management decision-making for fleet based on selective maintenance[J]. Systems Engineering and Electronics, 2024, 46(8): 2760-2769.

图/表 11

图1

图2

图3

表1

图4

表2

图5

图6

图7

表3

图8

参考文献 30

1	HAMADACHE M , JUNG J H , PARK J , et al. A comprehensive review of artificial intelligence-based approaches for rolling element bearing PHM: shallow and deep learning[J]. JMST Advances, 2019, 1 (3): 125- 151.
2	MENG H X , LI Y F . A review on prognostics and health management (PHM) methods of lithiumion batteries[J]. Renewable and Sustainable Energy Reviews, 2019, 116, 109405. doi: 10.1016/j.rser.2019.109405
3	XIA T B , DONG Y F , XIAO L , et al. Recent advances in prognostics and health management for advanced manufacturing paradigms[J]. Reliability Engineering and System Safety, 2018, 178, 255- 268. doi: 10.1016/j.ress.2018.06.021
4	HU Y , MIAO X W , SI Y , et al. Prognostics and health management: a review from the perspectives of design, development and decision[J]. Reliability Engineering and System Safety, 2022, 217, 108063. doi: 10.1016/j.ress.2021.108063
5	CAMCI F , MEDJAHERB K , ATAMURADOV V . Integrated maintenance and mission planning using remaining useful life information[J]. Engineering Optimization, 2019, 51 (10): 1794- 1809. doi: 10.1080/0305215X.2018.1552951
6	ZHEN L I , ZHONG S , LIN L N . An aero-engine life-cycle maintenance policy optimization algorithm: the reinforcement learning approach[J]. Chinese Journal of Aeronautics, 2019, 32 (9): 2133- 2150. doi: 10.1016/j.cja.2019.07.003
7	HU Y , MIAO X W , ZHANG J , et al. Reinforcement learning-driven maintenance strategy: a novel solution for long-term aircraft maintenance decision optimization[J]. Computers and Industrial Engineering, 2021, 153, 107056. doi: 10.1016/j.cie.2020.107056
8	曹文斌, 贾希胜, 胡起伟. 共因失效条件下多状态系统选择性维修优化[J]. 航空学报, 2018, 39 (2): 164- 178.
	CAO W B , JIA X S , HU Q W . Selective maintenance optimization for multi-state systems subject to common cause failures[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39 (2): 164- 178.
9	RICE W F, CASSADY C R, NACHLAS J A. Optimal maintenance plans under limited maintenance time[C]//Proc. of the 7th Industrial Engineering Research Conference, 1988.
10	DAO C D , ZUO M J . Selective maintenance for multistate series systems with s-dependent components[J]. IEEE Trans.on Reliability, 2016, 65 (2): 525- 539. doi: 10.1109/TR.2015.2494689
11	DAO C D , ZUO M J . Selective maintenance of multi-state systems with structural dependence[J]. Reliability Engineering and System Safety, 2017, 159, 184- 195. doi: 10.1016/j.ress.2016.11.013
12	DAO C D , ZUO M J , PANDEY M . Selective maintenance for multi-state series-parallel systems under economic dependence[J]. Reliability Engineering and System Safety, 2014, 121, 240- 249. doi: 10.1016/j.ress.2013.09.003
13	LIU Y , HUANG H Z . Optimal selective maintenance strategy for multi-state systems under imperfect maintenance[J]. IEEE Trans.on Reliability, 2010, 59 (2): 356- 367. doi: 10.1109/TR.2010.2046798
14	PANDEY M , ZUO M J , MOGHADDASS R . Selective maintenance modeling for a multistate system with multistate components under imperfect maintenance[J]. ⅡE Trans., 2013, 45 (11): 1221- 1234.
15	CAO W B , JIA X S , LIU Y , et al. Selective maintenance optimization for fuzzy multi-state systems[J]. Journal of Intelligent and Fuzzy Systems, 2018, 34 (1): 105- 121. doi: 10.3233/JIFS-17031
16	PANDEY M , ZUO M J , MOGHADDASS R , et al. Selective maintenance for binary systems under imperfect repair[J]. Reliability Engineering and System Safety, 2013, 113, 42- 51. doi: 10.1016/j.ress.2012.12.009
17	ZHU H P , LIU F M , SHAO X Y , et al. A cost-based selective maintenance decision-making method for machining line[J]. Quality and Reliability Engineering International, 2010, 27 (2): 191- 201.
18	CAO W B , JIA X S , LIU Y , et al. Selective maintenance optimisation considering random common cause failures and imperfect maintenance[J]. Proc.of the Institution of Mechanical Engineers Part O: Journal of Risk and Reliability, 2019, 233 (3): 427- 443. doi: 10.1177/1748006X18799907
19	GAO S , ZHOU F , TU J Q , et al. Selective maintenance strategy for a finite planning horizon considering imperfect maintenance[J]. Mathematical Problems in Engineering, 2023, 2023 (1): 5431739.
20	CHEN Q , WANG P , YANG L , et al. Mission and reliability driven fleet-level selective maintenance planning and scheduling two-stage method[J]. Applied Sciences, 2023, 13 (15): 8600. doi: 10.3390/app13158600
21	MA W N , ZHANG Q , XIAHOU T F , et al. Integrated selective maintenance and task assignment optimization for multi-state systems executing multiple missions[J]. Reliability Engineering & System Safety, 2023, 237, 109330.
22	JIANG T , LIU Y . Selective maintenance strategy for systems executing multiple consecutive missions with uncertainty[J]. Reliability Engineering and System Safety, 2020, 193, 106632. doi: 10.1016/j.ress.2019.106632
23	JIA X S , CAO W B , HU Q W . Selective maintenance optimization for random phased-mission systems subject to random common cause failures[J]. Proc.of the Institution of Mechanical Engineers Part O: Journal of Risk and Reliability, 2019, 233 (3): 329- 400.
24	LIU Y L , QIAN X B . Selective maintenance optimization with stochastic break duration based on reinforcement learning[J]. Eksploatacja i Niezawodno s ' c ', 2022, 24 (4): 771- 784. doi: 10.17531/ein.2022.4.17
25	曹文斌, 贾希胜, 胡起伟, 等. 基于选择性维修的装备战场抢修决策建模[J]. 系统工程与电子技术, 2018, 40 (1): 98- 105. doi: 10.3969/j.issn.1001-506X.2018.01.15
	CAO W B , JIA X S , HU Q W , et al. Equipment battlefield damage assessment and repair decision-making modeling based on selective maintenance[J]. Systems Engineering and Electronics, 2018, 40 (1): 98- 105. doi: 10.3969/j.issn.1001-506X.2018.01.15
26	马维宁, 胡起伟, 曹文斌, 等. 考虑维修任务分配的装备选择性维修决策优化[J]. 系统工程与电子技术, 2023, 45 (6): 1902- 1910. doi: 10.12305/j.issn.1001-506X.2023.06.35
	MA W N , HU Q W , CAO W B , et al. Equipment selective maintenance decision optimization considering maintenance task assignment[J]. Systems Engineering and Electronics, 2023, 45 (6): 1902- 1910. doi: 10.12305/j.issn.1001-506X.2023.06.35
27	LIU Y , CHEN Y M , JIANG T . Dynamic selective maintenance optimization for multi-state systems over a finite horizon: a deep reinforcement learning approach[J]. European Journal of Operational Research, 2020, 283 (1): 166- 181. doi: 10.1016/j.ejor.2019.10.049
28	CAO W B , JIA X S , HU Q W . A literature review on selective maintenance for multi-unit systems[J]. Quality and Reliability Engineering International, 2018, 34 (5): 824- 845. doi: 10.1002/qre.2293
29	JABOURI H A , SAIF A , KHATAB A , et al. Selective maintenance optimization: a condensed critical review and future research directions[J]. IFAC-Papers OnLine, 2022, 55 (10): 1213- 1218. doi: 10.1016/j.ifacol.2022.09.555
30	HESADI H , NOURELFAH M , HAIJI A . A deep learning predictive model for selective maintenance optimization[J]. Reliability Engineering and System Safety, 2022, 219, 108191. doi: 10.1016/j.ress.2021.108191

装备j	部件i	维修方式l_{j, i}	任务成功概率	维修费用/元	维修时间/天	备件订购交付时间/天
1	1	1	0.90	0	0	-
	1	2	0.99	1 300	0.5	2
	1	3	0.94	500	1.2	-
	2	1	0.95	0	0	-
	2	2	0.99	1 500	1	1.5
	2	3	0.98	700	1.3	-
2	1	1	0.80	0	0	-
	1	2	0.99	1 300	0.5	2
	1	3	0.84	500	1.2	-
	2	1	0.85	0	0	-
	2	2	0.99	1 500	1	1.5
	2	3	0.90	700	1.3	-
3	1	1	0.75	0	0	-
	1	2	0.99	1 300	0.5	2
	1	3	0.80	500	1.2	-
	2	1	0.70	0	0	-
	2	2	0.99	1 500	1	1.5
	2	3	0.75	700	1.3	-
4	1	1	0.60	0	0	-
	1	2	0.99	1 300	0.5	2
	1	3	0.68	500	1.2	-
	2	1	0.70	0	0	-
	2	2	0.99	1 500	1	1.5
	2	3	0.75	700	1.3	-

装备j	部件i	维修方式l_{j, i}	备件订购数量O_{j, 1}	备件需求量	维修费用/元	维修时间/天	维修任务分配h_{q, (j, I)}	任务规划Ta_j	运转费用c_j^o/元
1	1	3	0	0	500	1.2	(1, 0)	1	1 200
1	2	1	0	0	0	0	-	1	1 200
2	1	1	0	0	0	0	-	1	1 200
2	2	1	0	0	0	0	-	1	1 200
3	1	2	0	1	1 300	0.5	(0, 1)	1	1 200
3	2	2	0	1	1 500	1	(0, 1)	1	1 200
4	1	1	0	0	0	0	-	0	0
4	2	1	0	0	0	0	-	0	0
任务成功概率		0.959		总费用/元		6 900	总维修时间/天		1.5

装备j	部件i	维修方式l_{j, i}	备件订购数量O_{j, 1}	备件需求量	维修费用/元	维修时间/天	维修任务分配h_{q, (j, I)}	任务规划Ta_j	运转费用c_j^o/元
1	1	2	1	1	1 300	2.5	(1, 0)	1	1 200
1	2	3	0	0	700	1.3	(1, 0)	1	1 200
2	1	2	0	1	1 300	0.5	(1, 0)	1	1 200
2	2	2	0	1	1 500	1	(0, 1)	1	1 200
3	1	1	0	0	0	0	-	0	0
3	2	1	0	0	0	0	-	0	0
4	1	1	0	0	0	0	-	0	0
4	2	1	0	0	0	0	-	0	0
任务成功概率		0.951		总费用/元		7 200	总维修时间/天		2.5

[1]	吴嘉俊, 苏春, 张玉茹. 基于双重自注意力机制和长短时记忆网络的剩余寿命预测[J]. 系统工程与电子技术, 2024, 46(6): 1986-1994.
[2]	马维宁, 胡起伟, 曹文斌, 贾希胜. 考虑维修任务分配的装备选择性维修决策优化[J]. 系统工程与电子技术, 2023, 45(6): 1902-1910.
[3]	闫啸家, 梁伟阁, 张钢, 佘博, 田福庆. 基于RCNN-ABiLSTM的机械设备剩余寿命预测方法[J]. 系统工程与电子技术, 2023, 45(3): 931-940.
[4]	蔺瑞管, 王华伟, 车畅畅, 倪晓梅, 熊明兰. 基于LSTM分类器的航空发动机预测性维护模型[J]. 系统工程与电子技术, 2022, 44(3): 1052-1059.
[5]	孙世岩, 张钢, 梁伟阁, 佘博, 田福庆. 基于时间序列数据扩增和BLSTM的滚动轴承剩余寿命预测方法[J]. 系统工程与电子技术, 2022, 44(3): 1060-1068.
[6]	陈云翔, 饶益, 蔡忠义, 王泽洲. 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[J]. 系统工程与电子技术, 2021, 43(9): 2688-2696.
[7]	王泽洲, 陈云翔, 蔡忠义, 项华春, 王莉莉. 基于比例关系加速退化建模的设备剩余寿命在线预测[J]. 系统工程与电子技术, 2021, 43(2): 584-592.
[8]	李京峰, 陈云翔, 项华春, 蔡忠义. 基于LSTM-DBN的航空发动机剩余寿命预测[J]. 系统工程与电子技术, 2020, 42(7): 1637-1644.
[9]	蔡忠义, 王泽洲, 张晓丰, 李岩. 隐含非线性退化设备的剩余寿命在线预测方法[J]. 系统工程与电子技术, 2020, 42(6): 1410-1416.
[10]	王双川, 贾希胜, 胡起伟, 曹文斌, 郭驰名. 考虑随机共因失效的战时装备群任务成功概率仿真评估[J]. 系统工程与电子技术, 2020, 42(11): 2529-2537.
[11]	蔡忠义, 陈云翔, 郭建胜, 王泽洲, 邓林. 考虑测量误差和随机效应的设备剩余寿命预测#br#[J]. 系统工程与电子技术, 2019, 41(7): 1658-1664.
[12]	王泽洲, 陈云翔, 蔡忠义, 项华春, 罗承昆. 考虑随机失效阈值的设备剩余寿命在线预测[J]. 系统工程与电子技术, 2019, 41(5): 1162-1168.
[13]	冯晓, 郭霖瀚, 宋常浩, 孔丹丹. 基于CTMC族的多部件装备群稳态可用度建模方法[J]. 系统工程与电子技术, 2018, 40(6): 1405-1410.
[14]	蔡忠义, 郭建胜, 陈云翔, 董骁雄, 项华春. 基于步进加速退化建模的剩余寿命在线预测[J]. 系统工程与电子技术, 2018, 40(11): 2605-.
[15]	王少华, 张仕新, 李勇, 刘宏祥. 有限任务间隔时间内的装备选择性维修决策研究[J]. 系统工程与电子技术, 2018, 40(11): 2611-.