Bike-sharing systems are becoming increasingly important for sustainable urban mobility, but they need much maintenance, making them less efficient. Although predictive maintenance has been examined using technical and usage data, there has been insufficient focus on user-centric information as an indicator of bicycle reliability. This study examines the incorporation of user ratings into predictive maintenance models for the Lisbon GIRA bike-sharing system. We used linear mixed models and generalized additive models to examine a 1-month dataset with travel records, user feedback, and maintenance logs. Four formulations of Remaining Useful Life were developed, with riding time exhibiting the most reliable prediction capability. The findings show that user ratings are favorably related to Remaining Useful Life, and both models had an R2 of about 0.50. Residual analysis often undervalues severe results, which successfully indicate the need for maintenance sooner. Kernel density estimations and bathtub curve analysis further demonstrated the degradation effects linked to cumulative usage. The results suggest that putting the user at the heart of information enhances predictive maintenance strategies, making operations more dependable and scheduling maintenance easier in large-scale bike-sharing system operations.
LiWKamargianniM. Providing quantified evidence to policy makers for promoting bike-sharing in heavily air-polluted cities: a mode choice model and policy simulation for Taiyuan-China. Transp Res Part A: Policy Pract2018; 111: 277–291.
2.
DellRMMoseleyPTRandDAJ. The evolution of unsustainable road transport. In: DellRMMoseleyPTRandDAJ (eds) Towards sustainable road transport. Elsevier, 2014, pp. 1–64.
3.
U.S. EPA. United States Environmental Protection Agency fiscal year 2025 justification of appropriation estimates for the committee on appropriations. 2024. www.epa.gov/cj
4.
QiuLYHeLY. Bike sharing and the economy, the environment, and health-related externalities. Sustainability2018; 10: 1145. https://doi.org/10.3.390/su10041145
5.
MaXYuanYVan OortN, et al. Bike-sharing systems’ impact on modal shift: a case study in Delft, the Netherlands. J Clean Prod2020; 259: 120846. https://doi.org/10.1016/j.jclepro.2020.120846
6.
FishmanE. Bikeshare: a review of recent literature. Transp Rev2016; 36: 92–113.
7.
DeMaioPMeddinR. The bike-sharing world map. New York: MetroBike LLC, 2022.
8.
United Nations Statistical Commission. Report of the inter-agency and expert group on sustainable development goal indicators. 47th session, United Nations, 2016.
9.
CitaristiI. United nations human settlements programme—UN-habitat. In: The Europa directory of international organizations. Routledge, 28July2022, pp. 240–243.
10.
NaugesC. Greening household behaviour and water. Paris: OECD Publishing, 2017.
11.
TeixeiraJFSilvaCMoura e SáF. Empirical evidence on the impacts of bikesharing: a literature review. Transp Rev2021; 41: 329–351.
12.
ZhengLLiY. The development, characteristics and impact of bike-sharing systems: a literature review. Int Rev Spat Plan Sustain Dev2020; 8: 37–52.
13.
LiuJLiQQuM, et al. Station site optimization in bike sharing systems. In: Proceedings of the IEEE international conference on data mining, ICDM, 2016, pp. 883–888. Institute of Electrical and Electronics Engineers Inc.
14.
Duran-RodasDVilleneuveDPereiraFC, et al. How fair is the allocation of bike-sharing infrastructure? Framework for a qualitative and quantitative spatial fairness assessment. Transp Res Part A: Policy Pract2020; 140: 299–319.
15.
Médard de ChardonCCarusoGThomasI. Bike-share rebalancing strategies, patterns, and purpose. J Transp Geogr2016; 55: 22–39.
16.
KonFFerreiraÉCde SouzaHA, et al. Abstracting mobility flows from bike-sharing systems. Public Transp2022; 14: 545–581.
17.
Talavera-GarciaRRomanillosGArias-MolinaresD. Examining spatio-temporal mobility patterns of bike-sharing systems: the case of BiciMAD (Madrid). J Maps2021; 17: 7–13.
18.
ShaheenSGuzmanSZhangH. Bikesharing in Europe, the Americas, and Asia. Transp Res Rec2010; 2143(1): 159–167.
19.
O'BrienODeMaioPRabelloR, et al. The Meddin Bike-sharing World Map Report. 2022.
20.
ChoDIParlarM. A survey of maintenance models for multi-unit systems. Eur J Oper Res1991; 51(1): 1–23.
21.
ReinertsenR. Residual life of technical systems: diagnosis, prediction and life extension. Reliab Eng Syst Safety1996; 54(1): 23–34.
22.
ZhuTRanYZhouX, et al. A survey of predictive maintenance: systems, purposes and approaches. arXiv preprint arXiv:1912.07383, 2019.
23.
WangJZhangLDuanL, et al. A new paradigm of cloud-based predictive maintenance for intelligent manufacturing. J Intell Manuf2017; 28: 1125–1137.
24.
YangZKanniainenJKrogerusT, et al. Prognostic modeling of predictive maintenance with survival analysis for mobile work equipment. Sci Rep2022; 12: 8529. https://doi.org/10.1038/s41598-022-12572-z
25.
LuLZhaoSHeQC, et al. Task assignment in predictive maintenance for free-float bicycle sharing systems. Comput Ind Eng2022; 169: 108214. https://doi.org/10.1016/j.cie.2022.108214
26.
KaspiMRavivTTzurM. Detection of unusable bicycles in bike-sharing systems. Omega2016; 65: 10–16.
27.
ZhouYZhengRKouG. Detection approach for unusable shared bikes enabled by reinforcement learning and PageRank algorithm. J Saf Sci Resil2023; 4: 220–227.
28.
ZhouYKouGGuoZZ, et al. Availability analysis of shared bikes using abnormal trip data. Reliab Eng Syst Saf2023; 229: 108844.
29.
MatkovicVWaltereitMWeisT. Towards predictive safety maintenance for IoT equipped bikes. In: 2021 IEEE international conference on pervasive computing and communications workshops and other affiliated events, PerCom workshops 2021, 2021, pp. 320–323. Institute of Electrical and Electronics Engineers Inc.
30.
LuHZhangMSuS, et al. Broken bike recycling planning for sharing bikes system. IEEE Access2019; 7: 177354–177361.
31.
ChenYZengDDeveciM, et al. Life cycle analysis of bike sharing systems: a case study of Washington D.C. Environ Impact Assess Rev2024; 106: 107455. https://doi.org/10.1016/j.eiar.2024.107455
32.
ChengBLiJSuH, et al. Life cycle assessment of greenhouse gas emission reduction through bike-sharing for sustainable cities. Sustain Energy Technol Assess2022; 53: 102789. https://doi.org/10.1016/j.seta.2022.102789
33.
Al-DahidiSRashedMAbu-ShamsM, et al. A novel approach for remaining useful life prediction of high-reliability equipment based on long short-term memory and multi-head self-attention mechanism. Qual Reliab Eng Int2024; 40: 948–969.
34.
WangBSunJChenD, et al. A cumulative exposure model for remaining useful life prediction of pitot tube based on dynamic operating data. Qual Reliab Eng Int2023; 39: 1518–1531.
35.
YanBWangHMaX. Correlation-driven multivariate degradation modeling and RUL prediction based on Wiener process model. Qual Reliab Eng Int2023; 39: 3203–3229.
36.
Grau-EscolanoJBassolasAVicensJ. Cycling into the workshop: e-bike and m-bike mobility patterns for predictive maintenance in Barcelona’s bike-sharing system. EPJ Data Sci2024; 13(1): 48.
37.
MonteiroLDB. Predictive maintenance of bike sharing systems using neural networks. Master's Thesis, University of Lisbon, 2020.
BinattiGBatalhaYde CastroJ, et al. Latin American bike sharing ecosystem overview: from data collection to implementation model portraits. Urbe2022; 14: 1–15.
40.
NevesGRibeiroGGriloM, et al. Human reliability and organizational factors—how do human factors contribute to signals passed at danger?Saf Sci2024; 171: 106395. https://doi.org/10.1016/j.ssci.2023.106395
GalatoulasNFGenikomsakisKNIoakimidisCS. Spatio-temporal trends of e-bike sharing system deployment: a review in Europe, North America and Asia. Sustainability2020; 12: 4611. https://doi.org/10.3390/su12114611
43.
TurońK. Sustainable urban mobility transitions—from policy uncertainty to the CalmMobility paradigm. Smart Cities2025; 8: 164.
44.
PunzoGPanarelloDCastellanoR. Sustainable urban mobility: evidence from three developed European countries. Qual Quant2022; 56(5): 3135–3157.
45.
SiXSWangWHuCH, et al. Remaining useful life estimation – a review on the statistical data driven approaches. Eur J Oper Res2011; 213(1): 1–14.
46.
GałeckiABurzykowskiT (eds). Linear mixed-effects model. In: Linear mixed-effects models using R: a step-by-step approach. New York, NY: Springer New York, 28June2012, p. 245–273.
47.
HastieTJ. Generalized additive models. In: ChambersJMHastieTJ (eds) Statistical Models in S. Boca Raton: Chapman and Hall/CRC, 2017, pp. 249–307.
SimpsonG. Using random effects in GAMs with MGCV. From the bottom of the heap, 2021.
50.
BrossF. Using mixed effect models to analyze acceptability rating data in linguistics. University of Stuttgart, 2019.
51.
AndradeARStowJ. Statistical modelling of wear and damage trajectories of railway wheelsets. Qual Reliab Eng Int2016; 32: 2909–2923.
52.
RavindraKRattanPMorS, et al. Generalized additive models: building evidence of air pollution, climate change and human health. Environ Int2019; 132: 104987. https://doi.org/10.1016/j.envint.2019.104987
53.
KumarA. AIC & BIC for selecting regression models: formula, examples. Medium/Towards Data Science, 2023.
54.
NakagawaSSchielzethH. A general and simple method for obtaining R2 from generalized linear mixed-effects models. Methods Ecol Evol2013; 4: 133–142.
55.
JohnsonPC. Extension of Nakagawa & Schielzeth’s R2GLMM to random slopes models. Methods Ecol Evol2014; 5: 944–946.
56.
BhadouriaASMishraRPJalanAK, et al. Advances in railway condition monitoring and fault diagnosis: transition from industry 4.0 automation to industry 5.0 human-centric maintenance. Proc Inst Mech Eng F: J Rail Rapid Transit2025: 09544097261417814.
