Abstract
In recent years, the trend toward greater integration and complexity of mechanical systems has brought challenges to the formulation of preventive maintenance plans. It is very difficult to realize the traditional condition-based maintenance method that relies on calculating the optimal maintenance threshold to achieve optimal maintenance. However, in solving highly complex and challenging control and decision-making problems, the deep reinforcement learning (DRL) method shows its powerful ability and provides a new idea for the maintenance planning of complex systems. Numerical results show that DRL-based maintenance model can obtain optimization strategies through continuous exploration and realize the trade-off between component maintenance cost and the loss caused by system failure, whether in simple or complex multi-component systems. The policy minimizes the overall cost of the system by choosing actions that minimize the total long-term cost. The comparison with other maintenance strategies shows that the proposed model is superior to various baseline policies and reduces the system lifecycle cost.
Similar content being viewed by others
Data availability
We declare that the data generated and analyzed in this study can be obtained from the article.
References
Gong Y, Zha M, Lv Z (2022) Fractional-order optimal control model for the equipment management optimization problem with preventive maintenance. Neural Comput Appl 34:4693–4714
Goyal D, Pabla BS, Dhami SS et al (2017) Optimization of condition-based maintenance using soft computing. Neural Comput Appl 28(1):829–844
Zheng R, Chen B, Gu L (2020) Condition-based maintenance with dynamic thresholds for a system using the proportional hazards model. Reliab Eng Syst Saf 204:107123
Chen N, Ye ZS, Xiang Y et al (2015) Condition-based maintenance using the inverse Gaussian degradation model. Eur J Oper Res 243(1):190–199
Ahmad R, Kamaruddin S (2012) An overview of time-based and condition-based maintenance in industrial application. Comput Ind Eng 63(1):135–149
Nan C, Yong C, Li Z et al (2011) Optimal variability sensitive condition-based maintenance over time-based maintenance with a Cox PH model. Int J Prod Res 49(6–8):2083–2100
Hong PEI, Chang-Hua HU, Xiao-Sheng SI, Zheng-Xin Z, Dang-Bo DU (2018) Remaining life prediction information-based maintenance decision model for equipment under imperfect maintenance. Acta Autom Sin 44(4):719–729
Grall A, Bérenguer C, Dieulle L (2002) A condition-based maintenance policy for stochastically deteriorating systems. Reliab Eng Syst Saf 76(2):167–180
Du DB, Pei H, Zhang JX, et al (2020) A new condition-based maintenance decision model for degraded equipment subjected to random shocks. In: 2020 Chinese Control Decision Conference (CCDC)
Jonge BD, Teunter R, Tinga T (2017) The influence of practical factors on the benefits of condition-based maintenance over time-based maintenance. Reliab Eng Syst Saf 158:21–30
Liu B, Wu S, Xie M et al (2017) A condition-based maintenance policy for degrading systems with age- and state-dependent operating cost. Eur J Oper Res 263(3):879–887
Shahraki AF, Yadav OP, Vogiatzis C (2020) Selective maintenance optimization for multi-state systems considering stochastically dependent components and stochastic imperfect maintenance actions. Reliab Eng Syst Saf 196:106738
Tian Z, Liao H (2011) Condition based maintenance optimization for multi-component systems using proportional hazards model. Reliab Eng Syst Saf 96(5):581–589
Xu J, Liang Z, Li YF et al (2021) Generalized condition-based maintenance optimization for multi-component systems considering stochastic dependency and imperfect maintenance. Reliab Eng Syst Saf 211:107592
Hai CV, Phuc D, Anne B (2016) A stationary grouping maintenance strategy using mean residual life and the birnbaum importance measure for complex structures. IEEE Trans Reliab 65(1):217–234
Rasmekomen N, Parlikad AK (2016) Condition-based maintenance of multi-component systems with degradation state-rate interactions. Reliab Eng Syst Saf 148:1–10
Fan D, Zhang A, Feng Q et al (2021) Group maintenance optimization of subsea Xmas trees with stochastic dependency. Reliab Eng Syst Saf 209(7):107450
Mengkai Xu, Jin X, Kamarthi S et al (2018) A failure-dependency modeling and state discretization approach for condition-based maintenance optimization of multi-component systems. J Manuf Syst 47:141–152
Broek MAJUH, Teunter RH, Jonge BD et al (2021) Joint condition-based maintenance and load-sharing optimization for two-unit systems with economic dependency. Eur J Oper Res
Mokhtar EHA, Chateauneuf A, Laggoune R (2018) Condition based opportunistic preventive maintenance policy for utility systems with both economic and structural dependencies. Appl Gas Supply Netw 165:214–223
Guo QC, Bing HZ, Ling L (2017) Joint optimization of lot sizing and condition-based maintenance for multi-component production systems. Comput Ind Eng 110:538–549
Zhang N, Si W (2020) Deep reinforcement learning for condition-based maintenance planning of multi-component systems under dependent competing risks. Reliab Eng Syst Saf 203:107094
Andrzejczak K (2015) Stochastic modelling of the repairable system. J Konbin 35(1):5–14
Andriotisa CP, Papakonstantinou KG (2021) Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints. Reliab Eng Syst Saf 212:107551
Hsieh MH, Jeng SL (2007) Accelerated discrete degradation models for leakage current of ultra-thin gate oxides. IEEE Trans Reliab 56(3):369–380
Huang J, Chang Q, Arinez J (2020) Deep reinforcement learning based preventive maintenance policy for serial production lines. Expert Syst Appl 160:113701
Han X, Liu H, Sun F et al (2019) Active object detection with multi-step action prediction using deep Q-network. IEEE Trans Industr Inf 15(6):3723–3731
Hasselt HV, Guez A, Silver D (2015) Deep reinforcement learning with double Q-learning. In: Thirtieth AAAI conference on artificial intelligence
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no conflicts of interest associated with this publication. There was no funding for conducting this study. This manuscript is submitted only in this journal, and there is no case of multiple submissions of one manuscript. We confirm that we have taken full consideration of the intellectual property protection related to this work. There are no impediments to publication.
Ethical approval
Our research belongs to the improvement and application innovation of intelligent algorithms, so it does not involve ethical issues.
Informed consent
We confirm that the article has been read and approved to submit by all authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, J., Wang, Y. A deep reinforcement learning approach for maintenance planning of multi-component systems with complex structure. Neural Comput & Applic 35, 15549–15562 (2023). https://doi.org/10.1007/s00521-023-08542-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08542-9