Hostname: page-component-5b777bbd6c-f9nfp Total loading time: 0 Render date: 2025-06-18T13:36:40.365Z Has data issue: false hasContentIssue false
  • English
  • Français

System’s resilience through a data-learning-guided maintenance planner

Published online by Cambridge University Press:  13 June 2025

José N. M. Filho Open the ORCID record for José N. M. Filho [Opens in a new window] ,
Antonio C. P. Mesquita Open the ORCID record for Antonio C. P. Mesquita [Opens in a new window]  and
Fernando T. M. Abrahão Open the ORCID record for Fernando T. M. Abrahão [Opens in a new window]
José N. M. Filho
Affiliation:
AeroLogLab – Logistics Engineering Laboratory, Instituto Tecnológico de Aeronáutica, São José dos Campos, Brazil
Antonio C. P. Mesquita*
Affiliation:
AeroLogLab – Logistics Engineering Laboratory, Instituto Tecnológico de Aeronáutica, São José dos Campos, Brazil
Fernando T. M. Abrahão
Affiliation:
AeroLogLab – Logistics Engineering Laboratory, Instituto Tecnológico de Aeronáutica, São José dos Campos, Brazil
*
Corresponding author: Antonio C. P. Mesquita; Email: celio@ita.br
Get access Rights & Permissions [Opens in a new window]

Abstract

Maintaining high-complexity aircraft requires resilient and data-driven maintenance planning. This article presents the efficient task allocation and packing problem solver (ETTAPS), a novel framework that integrates predictive analytics and optimisation models to generate adaptive maintenance schedules. ETTAPS employs a trial-and-error approach to optimise maintenance intervals, leveraging a branch-and-cut solver combined with first-fit decreasing (FFD) task grouping to minimise costs and enhance aircraft availability. Additionally, a random forest model, retrained using a rolling 24-month data window, continuously refines predictions, leading to progressive cost reductions and improved system reliability over multiple maintenance cycles. Our results demonstrate that ETTAPS significantly reduces maintenance costs and increases aircraft availability by efficiently grouping tasks and incorporating real-world constraints, such as mechanic skill levels, task dependencies and resource limitations. The framework addresses key gaps in MSG-3 and certification analysis, improving task scheduling efficiency and ensuring long-term operational resilience. Furthermore, ETTAPS lays the groundwork for integration with digital twins, real-time anomaly detection and flight planning systems, supporting a more intelligent and proactive approach to aircraft maintenance. This research advances resilience and sustainable aviation maintenance planning by optimising costs, reducing downtime and proactively adapting to operational demands. By aligning with Industry 4.0 and aviation sustainability goals for 2050, ETTAPS contributes to the next generation of intelligent maintenance systems.

Keywords

predictive analyticsoptimizationcost efficiencysystem availabilityaircraft maintenance planning
Type
Research Article
Information
The Aeronautical Journal , First View , pp. 1 - 24
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Song, Z. and Liu, C. Energy efficient design and implementation of electric machines in air transport propulsion system, Appl. Energy, 2022, 322, pp 119–472.10.1016/j.apenergy.2022.119472CrossRefGoogle Scholar
Yusaf, T., Fernandes, L., Talib, A.R.A., Altarazi, Y.S.M., Alrefae, W., Kadirgama, K., Ramasamy, D., Jayasuriya, A., Brown, G., Mamat, R., Dhahad, H.A., Benedict, F. and Laimon, M. Sustainable aviation – hydrogen is the future, Sustainability, 2022, 14, p 548.10.3390/su14010548CrossRefGoogle Scholar
Russel, S.H. Supply chain management: more than integrated logistics, Air Force J. Logist., 2007, pp 56–64.Google Scholar
Salonen, A. and Gopalakrishnan, M. Practices of preventive maintenance planning in discrete manufacturing industry, J. Qual. Maint. Eng., 2020.10.1108/JQME-04-2019-0041CrossRefGoogle Scholar
Lei, Y., Li, N., Guo, L., Li, N. and Yan, T. Machinery health prognostics: a systematic review from data acquisition to RUL prediction, Mech. Syst. Signal Process., 2018, 104, pp 799–834.10.1016/j.ymssp.2017.11.016CrossRefGoogle Scholar
Gunda, T., Hackett, S., Kraus, L., Downs, C., Jones, R., McNalley, C., Bolen, M. and Walker, A. A machine learning evaluation of maintenance records for common failure modes in PV inverters, IEEE Access, 2020, 8, pp 211610–211620.10.1109/ACCESS.2020.3039182CrossRefGoogle Scholar
Tsang, A.H.C., Jardine, A.K.S. and Kolodny, H. The state of IOT in predictive maintenance: challenges and opportunities, J. Maint. Sci. Technol., 2018, 12, pp 321–340.Google Scholar
Li, X., Zhang, W. and Shi, Y. Dynamic predictive maintenance using machine learning, Int. J. Prod. Res., 2020, 58, pp 2567–2582.Google Scholar
Wen, L., Chen, X. and Li, X.. A comprehensive review of machine learning applications in predictive maintenance, IEEE Trans. Ind. Inf., 2022, 18, pp 2746–2759.Google Scholar
Tao, F., Qi, Q., Liu, A. and Kusiak, A. Data-driven smart manufacturing, J. Manuf. Syst., 2019, 48, pp 157–169.10.1016/j.jmsy.2018.01.006CrossRefGoogle Scholar
Duan, C., Deng, C., Gong, Q. and Wang, Y. Optimal failure mode-based preventive maintenance scheduling for a complex mechanical device, Int. J. Adv. Manuf. Technol., 2018, 95, pp 2717–2728.10.1007/s00170-017-1419-2CrossRefGoogle Scholar
Kheder, M., Trigui, M. and Aifaoui, N. Optimization of disassembly sequence planning for preventive maintenance, Int. J. Adv. Manuf. Technol., 2017, 90, (5–8), pp 1337–1349.10.1007/s00170-016-9434-2CrossRefGoogle Scholar
Gonçalves, P., Sobral, J. and Ferreira, L. Establishment of an initial maintenance program for UAVs based on reliability principles, Aircr. Eng. Aerosp. Technol., 2017, 89, (1), pp 66–75.10.1108/AEAT-09-2014-0146CrossRefGoogle Scholar
Gill, A. and Szrama, S. Aircraft operators maintenance decisions supporting method, Arch. Transport, 2021, 59, (3), pp 93–111.10.5604/01.3001.0015.0466CrossRefGoogle Scholar
FAA, F.A.A. FAA AC 121-22: maintenance review boards, maintenance type boards, and OEM/TCH recommended maintenance procedures, 2012. https://www.faa.gov/documentLibrary/media/Advisory\_Circular/AC121-22C.pdf. citationKey:federal_aviation_administration_faa_2012 Google Scholar
Ahmadi, A., Söderholm, P. and Kumar, U. On aircraft scheduled maintenance program development, J. Qual. Maint. Eng., 2010, 16, pp 229–255.10.1108/13552511011072899CrossRefGoogle Scholar
Cardoso, D. and Ferreira, L. Application of predictive maintenance concepts using artificial intelligence tools, Appl. Sci., 2020, 11, p 18.10.3390/app11010018CrossRefGoogle Scholar
Plastropoulos, A., Avdelidis, N., Angus, J., Maggiore, J. and Atkinson, H. The hangar of the future for sustainable aviation, Aeronaut. J., 2024, 2024, pp 2430–2450. doi: 10.1017/aer.2024.79.Google Scholar
FAA. eCFR: 14 CFR 121.367 – maintenance, preventive maintenance, and alterations programs, 2022. https://www.ecfr.gov/current/title-14/chapter-I/subchapter-G/part121/subpart-L/section-121.367 Google Scholar
FAA. FAA AC 121-22d: maintenance review boards, maintenance type boards, and original equipment manufacturer/type certificate holder recommended maintenance procedures, Advisory Circular, 2024. https://www.faa.gov/regulations_policies/advisory_circulars/index.cfm/go/document.information/documentID/1042771 Google Scholar
Mlynarski, S., Pilch, R., Smolnik, M., Szybka, J. and Wiqzania, G. A model of an adaptive strategy of preventive maintenance of complex technical objects, Eksploatacja i Niezawodnosc – Maint. Reliab., 2019, 22, pp 35–41.10.17531/ein.2020.1.5CrossRefGoogle Scholar
Kabashkin, I. Digital twin framework for aircraft lifecycle management based on data-driven models, Mathematics, 2024, 12. https://doi.org/10.3390/math12192979 CrossRefGoogle Scholar
Giacotto, A., Mesquita, A.C.P., Marques, H.C. and Martinetti, A. Holistic and scalable smart optimization framework for prescriptive maintenance, in 34th Congress of the International Council of the Aeronautical Sciences, 2024.Google Scholar
FAA. DOT/FAA/AR-03/70 – Continuing Analysis and Surveillance System (CASS) Description and Models, 2003. https://www.tc.faa.gov/its/worldpac/techrpt/ar03-70.pdf Google Scholar
Rebaiaia, M.L. and Ait-kadi, D. Maintenance policies with minimal repair and replacement on failures: analysis and comparison, Int. J. Prod. Res., 2021, 59, (23), pp 6995–7017.10.1080/00207543.2020.1832275CrossRefGoogle Scholar
O’Connor, P.D.T. and Kleyner, A. Practical Reliability Engineering, 5th ed. New York: Wiley, 2012.Google Scholar
Usuga-Cadavid, J.P., Lamouri, S., Grabot, B. and Fortin, A. Using deep learning to value free-form text data for predictive maintenance, Int. J. Prod. Res., 2021, 60, (14).Google Scholar
Blanchard, B. and Blyler, J. Introduction to system engineering, in System Engineering Management, 2016, pp 1–52.Google Scholar
Johnson, D.S. Near-optimal bin packing algorithms. PhD thesis, Massachusetts Institute of Technology, Department of Mathematics, 1973.Google Scholar
de Jonge, B. and Scarf, P.A. A review on maintenance optimization, Eur. J. Oper. Res., 2020, 285, pp 805–824.10.1016/j.ejor.2019.09.047CrossRefGoogle Scholar
Hu, Y., Miao, X., Si, Y., Pan, E. and Zio, E. Prognostics and health management: a review from the perspectives of design, development and decision, Reliab. Eng. Syst. Saf., 2022, 217, p 108063.10.1016/j.ress.2021.108063CrossRefGoogle Scholar
Cao, K., Zhang, Y. and Feng, J. Failure rate analysis and maintenance plan optimization method for civil aircraft parts based on data fusion, Chin. J. Aeronaut., 2025, 38, p 103219.10.1016/j.cja.2024.08.050CrossRefGoogle Scholar
Goerger, S.R., Madni, A.M. and Eslinger, O.J. Engineered resilient systems: a DOD perspective, Proc. Comput. Sci., 2014, 28, pp 865–872.10.1016/j.procs.2014.03.103CrossRefGoogle Scholar
Forrest, J., et al. CoIN–OR CBC version 2.10.5, 2020. doi: 10.5281/zenodo.2720283.CrossRefGoogle Scholar
Harris, C., Millman, K. and van der Walt, S. Array programming with NumPy, 2020. doi: 10.1038/s41586-020-2649-2.CrossRefGoogle Scholar
McKinney, W., et al. Data structures for statistical computing in Python, in Data Structures for Statistical Computing in Python, 2010, pp 51–56.10.25080/Majora-92bf1922-00aCrossRefGoogle Scholar
Pedregosa, F., et al. Scikit-learn: machine learning in python, J. Mach. Learn. Res., 2011, 12, pp 2825–2830.Google Scholar
Dori, D. Object-process analysis: maintaining the balance between system structure and behavior, J. Logic Comput., 1995, pp 227–249.10.1093/logcom/5.2.227CrossRefGoogle Scholar
Smith, A.M. and Hinchcliffe, G.R. RCM – Gateway to World Class Maintenance. Elsevier, 2003.Google Scholar
Wieser, F. (Ed.) Über den Ursprung und die Hauptgesetze des wirtschaftlichenWerthes (On the Origin and Main Laws of Economic Value). Viena: Alfred Hölder, 1984.Google Scholar
Almgren, T., Andréasson, N., Patriksson, M., Strömberg, A.B., Wojciechowski, A. and Önnheim, M. The opportunistic replacement problem: theoretical analyses and numerical tests, Math. Methods Oper. Res. (Heidelberg, Germany), 2012, 76, pp 289–319.10.1007/s00186-012-0400-yCrossRefGoogle Scholar
Ackert, S.P. Basics of aircraft maintenance programs for financiers, 2010. https://www.icf.com Google Scholar
Deng, Q., Santos, B.F. and Verhagen, W.J. A novel decision support system for optimizing aircraft maintenance check schedule and task allocation, Decis. Support Syst., 2021, 146, p 113545.10.1016/j.dss.2021.113545CrossRefGoogle Scholar
Li, J., Mourelatos, Z. and Singh, A. Optimal preventive maintenance schedule based on lifecycle cost and time-dependent reliability, SAE Int. J. Mater. Manuf., 2012, 5, pp 87–95. https://www.sae.org/publications/technical-papers/content/2012-01-0070/ 10.4271/2012-01-0070CrossRefGoogle Scholar
Senturk, C. and Ozkol, I. The effects of the use of single task-oriented maintenance concept and more accurate letter check alternatives on the reduction of scheduled maintenance downtime of aircraft, Int. J. Mech. Eng. Robot. Res., 2018, 7, pp 189–196.Google Scholar
Goyal, D. and Purohit, H. To predict or not to predict: applications of predictive analytics in maintenance, J. Reliab. Eng., 2020, 45, pp 123–135.Google ScholarPubMed
IMRBPB. IMPS: International MRB/MTB process standard, 2022. https://www.easa.europa.eu/en/domains/aircraft-products/international-maintenancereview-board-policy-board-IMRBPB Google Scholar