A Comparative Study of Optimization Models for Condition-Based Maintenance Scheduling of an Aircraft Fleet

被引:4
|
作者
Tseremoglou, Iordanis [1 ]
van Kessel, Paul J. [2 ]
Santos, Bruno F. [1 ]
机构
[1] Delft Univ Technol, Fac Aerosp Engn, Air Transport & Operat, NL-2629 HS Delft, Netherlands
[2] KLM Royal Dutch Airlines, NL-1117 ZL Schiphol, Netherlands
基金
欧盟地平线“2020”;
关键词
condition-based maintenance (CBM); partially observable markov decision process (POMDP); partially observable Monte Carlo planning (POMCP); deep reinforcement learning (DRL); mixed integer linear programming (MILP); planning under uncertainty; ELECTIVE PATIENTS;
D O I
10.3390/aerospace10020120
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
Condition-based maintenance (CBM) scheduling of an aircraft fleet in a disruptive environment while considering health prognostics for a set of systems is a very complex combinatorial problem, which is becoming more challenging in light of the uncertainty included in health prognostics. This type of problem falls under the broad category of resource-constrained scheduling problems under uncertainty and is often solved using a mixed integer linear programming (MILP) formulation. While a MILP framework is very promising, the problem size can scale exponentially with the number of considered aircraft and considered tasks, leading to significantly high computational costs. The most recent advances in artificial intelligence have demonstrated the capability of deep reinforcement learning (DRL) algorithms to alleviate this curse of dimensionality, as once the DRL agent is trained, it can achieve real-time optimization of the maintenance schedule. However, there is no guarantee of optimality. These comparative merits of a MILP and a DRL formulation for the aircraft fleet maintenance scheduling problem have not been discussed in the literature. This study is a response to this research gap. We conduct a comparison of a MILP and a DRL scheduling model, which are used to derive the optimal maintenance schedule for various maintenance scenarios for aircraft fleets of different sizes in a disruptive environment, while considering health prognostics and the available resources for the execution of each task. The quality of solutions is evaluated on the basis of four planning objectives, defined according to real airline practice. The results show that the DRL approach achieves better results with respect to scheduling of prognostics-driven tasks and requires less computational time, whereas the MILP model produces more stable maintenance schedules and induces less maintenance ground time. Overall, the comparison provides valuable insights for the integration of health prognostics in airline maintenance practice.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] A NEW ALGORITHM FOR SCHEDULING CONDITION-BASED MAINTENANCE OF GAS TURBINES
    Yilmaz, Yavuz
    Kurz, Rainer
    Ozmen, Ayse
    Weber, Gerhard-Wilhelm
    PROCEEDINGS OF THE ASME TURBO EXPO: TURBINE TECHNICAL CONFERENCE AND EXPOSITION, 2015, VOL 9, 2015,
  • [32] CONDITION-BASED MAINTENANCE
    BALDIN, AE
    CHEMICAL ENGINEERING, 1981, 88 (16) : 89 - 95
  • [33] Condition-based maintenance
    Rudd, Kevin
    Wesley, Ian
    World Cement, 2003, 34 (06): : 43 - 45
  • [34] Joint optimization of condition-based maintenance and condition-based production of a single equipment considering random yield and maintenance delay
    Zhang, Nan
    Cai, Kaiquan
    Deng, Yingjun
    Zhang, Jun
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2024, 241
  • [35] Optimization of condition-based maintenance using soft computing
    Goyal, Deepam
    Pabla, B. S.
    Dhami, S. S.
    Lachhwani, Kailash
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 : S829 - S844
  • [36] Discounted cost model for condition-based maintenance optimization
    van der Weide, J. A. M.
    Pandey, M. D.
    van Noortwijk, J. M.
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2010, 95 (03) : 236 - 246
  • [37] Optimization of condition-based maintenance using soft computing
    Deepam Goyal
    B. S. Pabla
    S. S. Dhami
    Kailash Lachhwani
    Neural Computing and Applications, 2017, 28 : 829 - 844
  • [38] Joint Optimization of Lot-streaming Scheduling and Condition-based Maintenance Based on a Consideration of Quality Degradation
    Lu Z.
    Mou X.
    1600, Science Press (49): : 535 - 543
  • [39] Optimization of condition-based maintenance considering partial opportunities
    Huy Truong-Ba
    Borghesani, Pietro
    Cholette, Michael E.
    Ma, Lin
    QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2020, 36 (02) : 529 - 546
  • [40] MACHINE INTEGRATED HEALTH MODELS FOR CONDITION-BASED MAINTENANCE
    Lu, Chen
    Tao, Xiaochuang
    Zhang, Wenjin
    Wang, Zili
    TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2014, 21 (06): : 1377 - 1383