In the last years, there has been a growing interest in the emerging concept of digital twin (DT) as it represents a promising paradigm to continuously monitor cyber–physical systems, as well as to test and validate predictability, safety, and reliability aspects. At the same time, artificial intelligence (AI) is exponentially affirming as an extremely powerful tool when it comes to modeling the behavior of physical assets allowing, de facto, the possibility of making predictions on their potential evolution. However, despite the fact that DTs and AI (and their combination) can act as game-changing technologies in different domains (including the railways), several challenges have to be faced to ensure their effectiveness, especially when dealing with safety-critical systems. This paper provides a narrative review of the scientific literature on DTs for railway maintenance applications, with a special focus on their relationship with AI. The aim is to discuss the opportunities the integration of these two technologies could open in railway maintenance applications (and beyond), while highlighting the main challenges that should be overcome for its effective implementation.
FlamminiF. Digital twins as run-time predictive models for the resilience of cyber-physical systems: a conceptual framework. Philos Trans Royal Soc A Math Phys Eng Sci, 2021; 379: 1–10.
2.
LaamartiFBadawiHFDingY, et al. An ISO/IEEE 11073 standardized digital twin framework for health and well-being in smart cities. IEEE Access2020; 8: 105950–105961.
3.
SemeraroCLezocheMPanettoH, et al. Digital twin paradigm: a systematic literature review. Comp Indus2021; 130: 103469.
4.
PernoMHvamLHaugA. Implementation of digital twins in the process industry: a systematic literature review of enablers and barriers. Comp Indus2022; 134: 103558.
5.
BaoLWangQJiangY. Review of digital twin for intelligent transportation system. In: International conference on information control, electrical engineering and rail transit (ICEERT), Lanzhou, China, 30 October–1 November 2021, pp. 309–315. New York: IEEE.
6.
KaewunruenSSresakoolchaiJLinYh. Digital twins for managing railway maintenance and resilience. Open Res Eur2021; 1: 91.
7.
VieiraJPoças MartinsJMarques de AlmeidaN, et al. Towards resilient and sustainable rail and road networks: a systematic literature review on digital twins. Sustainability2022; 14: 7060.
8.
De DonatoLFlamminiFMarroneS, et al. A survey on audio-video based defect detection through deep learning in railway maintenance. IEEE Access2022; 10: 65376–65400.
9.
TangRDe DonatoLBešinovićN, et al. A literature review of artificial intelligence applications in railway systems. Transp Res C: Emerg Technol2022; 140: 103679.
10.
BešinovićNDe DonatoLFlamminiF, et al. Artificial intelligence in railway transport: taxonomy, regulations and applications. IEEE Trans Intell Transp Syst2022; 23: 14011–14024.
11.
FlamminiFDe DonatoLFantechiA, et al. A vision of intelligent train control. In: Collart-DutilleulSHaxthausenAELecomteT (eds) Reliability, safety, and security of railway systems. Modelling, analysis, verification, and certification. Cham: Springer International Publishing, pp. 192–208.
12.
LiuMFangSDongH, et al. Review of digital twin about concepts, technologies, and industrial applications. J Manuf Syst2021; 58: 346–361.
13.
BhattiGMohanHRaja SinghR. Towards the future of smart electric vehicles: digital twin technology. Renew Sustain Energ Rev2021; 141: 110801.
14.
LuJZhengXSchweigerL, et al. A cognitive approach to manage the complexity of digital twin systems. In WestSMeierhoferJGanzC (eds) Smart services summit. Cham: Springer, 2021, pp. 105–115.
15.
ZhengXLuJKiritsisD. The emergence of cognitive digital twin: vision, challenges and opportunities. Int J Prod Res2022; 60: 7610–7632.
16.
ErrandoneaIBeltránSArrizabalagaS. Digital twin for maintenance: a literature review. Comp Indust2020; 123: 103316.
17.
De DonatoLMarroneSFlamminiF, et al. Intelligent detection of warning bells at level crossings through deep transfer learning for smarter railway maintenance. Eng Appl Artif Intell2023; 123: 106405.
18.
OriveDIriondoNBurgosA, et al. Fault injection in digital twin as a means to test the response to process faults at virtual commissioning. In: 2019 24th IEEE international conference on emerging technologies and factory automation (ETFA), Zaragoza, 10–13 September, pp. 1230–1234. New York: IEEE.
19.
AlexopoulosKNikolakisNChryssolourisG. Digital twin-driven supervised machine learning for the development of artificial intelligence applications in manufacturing. Int J Comp Integr Manuf2020; 33: 429–439.
20.
De DonatoLDirnfeldRSommaA, et al. Towards AI-assisted digital twins for smart railways: preliminary guideline and reference architecture. J Rel Intell Environ2023: 1–15.
21.
RasheedASanOKvamsdalT. Digital twin: values, challenges and enablers from a modeling perspective. IEEE Access2020; 8: 21980–22012.
22.
ZhangHLiuQChenX, et al. A digital twin-based approach for designing and multi-objective optimization of hollow glass production line. IEEE Access2017; 5: 26901–26911.
23.
YaqoobISalahKUddinM, et al. Blockchain for digital twins: recent advances and future research challenges. IEEE Network2020; 34: 290–298.
24.
KitchenhamB. Procedures for Performing Systematic Reviews. Technical Report TR/SE-0401, Department of Computer Science, Keele University, UK, 2004.
25.
LiuZJinCJinW, et al. Industrial AI enabled prognostics for high-speed railway systems. In: 2018 IEEE international conference on prognostics and health management (ICPHM), Seattle, WA, 11–13 June, pp. 1–8. New York: IEEE.
26.
GanTHKanfoudJNedunuriH, et al. Industry 4.0: why machine learning matters? In: GelmanLMartinNMalcolmAA, et al. (eds) Advances in condition monitoring and structural health monitoring. Singapore: Springer Singapore, pp. 397–404.
27.
BoscagliaLBogliettiANateghS, et al. Numerically based reduced-order thermal modeling of traction motors. IEEE Trans Indus Appl2021; 57: 4118–4129.
28.
ZhangTDuWZhangG, et al. PHM of rail vehicle based on digital twin. In: 2021 global reliability and prognostics and health management (PHM-Nanjing), Nanjing, China, 15–17 October, pp. 1–5. New York: IEEE.
29.
ConsilvioASolís-HernándezJJiménez-RedondoN, et al. On applying machine learning and simulative approaches to railway asset management: the earthworks and track circuits case studies. Sustainability2020; 12: 2544.
30.
IkedaM. Recent research and development activities in maintenance technologies for electric railway power supply systems. Quarter Rep RTRI2020; 61: 6–10.
31.
SahalRAlsamhiSHBrownKN, et al. Blockchain-empowered digital twins collaboration: smart transportation use case. Machines2021; 9: 193.
32.
MilosevicM. Towards model-based condition monitoring of railway swithces and crossings. PhD Thesis, Department of Mechanics and Maritime Sciences, Chalmers University of Technology, 2021.
33.
YangJSunYCaoY, et al. Predictive maintenance for switch machine based on digital twins. Information2021; 12: 485.
34.
WangXSongHZhaW, et al. Digital twin based validation platform for smart metro scenarios. In: 2021 IEEE 1st international conference on digital twins and parallel intelligence (DTPI), Beijing, China, 15 July–15 August, pp. 386–389. New York: IEEE.
35.
ZhouMHouZLiuJ, et al. Digital twin-based automatic train regulation for integration of dispatching and control. In: 2021 IEEE 1st international conference on digital twins and parallel intelligence (DTPI), Beijing, China, 15 July–15 August, pp. 461–464. New York: IEEE.
36.
Lumban-GaolYAChenZSmitM, et al. A comparative study of point clouds semantic segmentation using three different neural networks on the railway station dataset. Int Archiv Photogr Rem Sens Spat Inf Sci2021; XLIII-B3-2021: 223–228.
37.
ZhangSDongHMaschekU, et al. A digital-twin-assisted fault diagnosis of railway point machine. In: 2021 IEEE 1st international conference on digital twins and parallel intelligence (DTPI), Beijing, China, 15 July–15 August, pp. 430–433. New York: IEEE.
38.
DimitrovaETomovS. Digital twins: an advanced technology for railways maintenance transformation. In: 2021 13th electrical engineering faculty conference (BulEF), Varna, 8–11 September, pp. 1–5. New York: IEEE.
39.
ChenSWuXZhouM, et al. Digital twin based train delay prediction system: design and realization. In: 2022 41st Chinese control conference (CCC), Hefei, China, 25–27 July, pp. 305–310. New York: IEEE.
40.
WuXLianWZhouM, et al. A digital twin based fault diagnosis framework for bogies of high-speed trains. IEEE J Radio Freq Identif2022; 7: 203–207.
41.
AriyachandraMBrilakisI. Detection of railway masts in airborne LiDAR data. J Constr Eng Manage2020; 146: 04020105.
42.
FebriantoEButlerLGirolamiM, et al. Digital twinning of self-sensing structures using the statistical finite element method. Data-Centr Eng2022; 3: e31.
43.
PengFZhengL. Fuzzy rule-based neural network for high-speed train manufacturing system scheduling problem. Neur Comp Appl2023; 35: 2077–2088.
44.
PatwardhanAThaduriAKarimR, et al. Federated learning for enablement of digital twin. IFAC-PapersOnLine2022; 55: 114–119.
45.
FlamminiFDe DonatoLFantechiA, et al. A vision of intelligent train control. In: Collart-DutilleulSHaxthausenAELecomteT (eds) Reliability, safety, and security of railway systems. Modelling, analysis, verification, and certification. Cham: Springer International Publishing, pp. 192–208.
46.
YangCFerdousiREl SaddikA, et al. Lifetime learning-enabled modelling framework for digital twin. In: 2022 IEEE 18th international conference on automation science and engineering (CASE), Mexico City, Mexico, 20–24 August, pp. 1761–1766. New York: IEEE.
47.
ZhangTRenGMingH, et al. Application exploration of digital twin in rail transit health management. In: 2022 global reliability and prognostics and health management (PHM-Yantai), Yantai, China, 13–16 October, pp. 1–5. New York: IEEE.
48.
TorzoniMManzoniAMarianiS. Structural health monitoring of civil structures: a diagnostic framework powered by deep metric learning. Comp Struct2022; 271: 106858.
49.
FerdousiRLaamartiFYangC, et al. Railtwin: a digital twin framework for railway. In: 2022 IEEE 18th international conference on automation science and engineering (CASE), Mexico City, Mexico, 20–24 August, pp. 1767–1772. New York: IEEE.
50.
ErrandoneaIGoyaJAlvaradoU, et al. IoT approach for intelligent data acquisition for enabling digital twins in the railway sector. In: 2021 international symposium on computer science and intelligent controls (ISCSIC), Rome, 12–14 November, pp. 164–168. New York: IEEE.
51.
JiangRWangWXieY, et al. Research and design of infrastructure monitoring platform of intelligent high speed railway. In: 2022 IEEE 6th information technology and mechatronics engineering conference (ITOEC), Chongqing, China, 4–6 March, vol. 6, pp. 2096–2099. New York: IEEE.
52.
BustosARubioHSoriano-HerasE, et al. Methodology for the integration of a high-speed train in Maintenance 4.0. J Comput Des Eng2021; 8: 1605–1621.
53.
ZhouSDumssSNowakR, et al. A conceptual model-based digital twin platform for holistic large-scale railway infrastructure systems. Procedia CIRP2022; 109: 362–367.
54.
Gürdür BrooDBravo-HaroMSchoolingJ. Design and implementation of a smart infrastructure digital twin. Autom Construct2022; 136: 104171.
55.
MalekNGTayefehMBenderD, et al. Live digital twin for smart maintenance in structural systems. IFAC-PapersOnLine2021; 54: 1047–1052.
56.
DuWZhangTZhangG, et al. A digital twin framework and an implementation method for urban rail transit. In: 2021 global reliability and prognostics and health management (PHM-Nanjing), Nanjing, China, 15–17 October, pp. 1–4. New York: IEEE.
57.
AmbraTMacharisC. Agent-based digital twins (ABM-DT) in synchromodal transport and logistics: the fusion of virtual and pysical spaces. In: 2020 Winter simulation conference (WSC), Orlando, FL, 14–18 December, pp. 159–169. New York: IEEE.
58.
AvizzanoCAScivolettoGTripicchioP. Robust image stitching and reconstruction of rolling stocks using a novel Kalman filter with a multiple-hypothesis measurement model. IEEE Access2021; 9: 154011–154021.
59.
FutaiMMBittencourtTNCarvalhoH, et al. Challenges in the application of digital transformation to inspection and maintenance of bridges. Struct Inf Eng2022; 18: 1581–1600.
60.
RicondoIPortoAUgarteM. A digital twin framework for the simulation and optimization of production systems. Procedia CIRP2021; 104: 762–767.
61.
MagnaniniMTolioT. A model-based digital twin to support responsive manufacturing systems. CIRP Ann2021; 70: 353356.
62.
BoockmeyerAFriedenbergerDPirlL, et al. From CCS-planning to testautomation: the digital testfield of Deutsche Bahn in Scheibenberg—a case study. In: 2021 IEEE international conference on cloud engineering (IC2E), San Francisco, CA, 4–8 October, pp. 258–263. New York: IEEE.
63.
KaewunruenSPengSPhil-EbosieO. Digital twin aided sustainability and vulnerability audit for subway stations. Sustainability2020; 12: 7973.
64.
KaewunruenSXuN. Digital twin for sustainability evaluation of railway station buildings. Front Built Environ2018; 4: 77.
65.
YeCButlerLJCalkaB, et al. A digital twin of bridges for structural health monitoring. In: Proceedings of 12th International Workshop on Structural Health Monitoring, Standford, California, USA, 10-12 September 2019.
66.
AhmadiMKaleybarHBrennaM, et al. Adapting digital twin technology in electric railway power systems. In: 2021 12th power electronics, drive systems, and technologies conference (PEDSTC), Tabriz, Iran, 2–4 February, pp. 1–6. New York: IEEE.
67.
JeschkeSGrassmannR. Development of a generic implementation strategy of digital twins in logistics systems under consideration of the German rail transport. Appl Sci2021; 11: 10289.
68.
GengQWenYZhangD, et al. Analysis of electromagnetic coupling characteristics of balise transmission system based on digital twin. Appl Sci-Basel2021; 11: 6002.
69.
RamatloDLongCLovedayP, et al. A modelling framework for simulation of ultrasonic guided wave-based inspection of welded rail tracks. Ultrasonics2020; 108: 106215.
70.
GaoYQianSLiZ, et al. Digital twin and its application in transportation infrastructure. In: 2021 IEEE 1st international conference on digital twins and parallel intelligence (DTPI), Beijing, China, 15 July–15 August, pp. 298–301. New York: IEEE.
71.
SpiryaginMWuQPolachO, et al. Problems, assumptions and solutions in locomotive design, traction and operational studies. Rail Eng Sci2022; 30: 265–288.
72.
KaewunruenSLianQ. Digital twin aided sustainability-based lifecycle management for railway turnout systems. J Clean Prod2019; 228: 1537–1551.
73.
PreeceJSamraMThomasR, et al. A video game-inspired approach for a pedestrian guidance system within a railway station. In: 2021 IEEE international conference on big data (big data), Orlando, FL, 15–18 December, pp. 2919–2924. New York: IEEE.
74.
AksenovVSemochkinABendikA, et al. Utilizing digital twin for maintaining safe working environment among railway track tamping brigade. Transp Res Proc2022; 61: 600–608.
75.
PoceMCasielloGFerrariL, et al. Creation of a digital twin model, redesign of plant structure and new fuzzy logic controller for the cooling system of a railway locomotive. In: SaponaraSDe GloriaA (eds) Applications in electronics pervading industry, environment and society. Cham: Springer, pp. 125–135.
76.
ZhengXXuBZhaoW, et al. Modeling method and application of metro power supply system based on digital twin. In: 2021 IEEE 2nd China international youth conference on electrical engineering (CIYCEE), Chengdu, China, 15–17 December, pp. 1–7. New York: IEEE.
77.
BernalESpiryaginMVollebregtE, et al. Prediction of rail surface damage in locomotive traction operations using laboratory-field measured and calibrated data. Eng Fail Anal2022; 135: 106165.
78.
MishkurovPRakhmangulovAKornilovS, et al. Rail yard digital twin implementation into an industrial information system. AIP Conf Proc2022; 2456: 030026.
79.
YuBChenCTangJ, et al. Autonomous vehicles digital twin: a practical paradigm for autonomous driving system development. Computer2022; 55: 26–34.
80.
ThielingJMatharMRoßmannJ. Automated generation of virtual road scenarios for efficient tests of driver assistance systems. In: 2017 IEEE AUTOTESTCON, Schaumburg, IL, 9–15 September, pp. 1–9. New York: IEEE.
81.
PattinsonJAChenHBasuS. Legal issues in automated vehicles: critically considering the potential role of consent and interactive digital interfaces. Human Soc Sci Commun2020; 7: 153.
82.
PickeringJWhitakerJGlazerB, et al. An investigation into the closer running of autonomous trains. In: XLVII symposium on operational research, Kraljevo, Serbia, 20-23 September 2020, pp. 1–6.
83.
WangZGuptaRHanK, et al. Mobility digital twin: concept, architecture, case study, and future challenges. IEEE Internet Things J2022; 9: 17452–17467.
84.
HuiYMaXSuZ, et al. Collaboration as a service: digital-twin-enabled collaborative and distributed autonomous driving. IEEE Internet Things J2022; 9: 1860718619.
85.
DahmenUOsterlohTRoßmannJ. Generation of virtual test scenarios for training and validation of AI-based systems. In: 2021 IEEE international conference on progress in informatics and computing (PIC), Shanghai, China, 17–19 December, pp. 64–71. New York: IEEE.
86.
LiuYWangZHanK, et al. Sensor fusion of camera and cloud digital twin information for intelligent vehicles. In: 2020 IEEE intelligent vehicles symposium (IV), Las Vegas, NV, 19 October–13 November, pp. 182–187. New York: IEEE.
87.
HouZLiuHZhangY. Attributes based Bayesian unknown hazards assessment for digital twin empowered autonomous driving. In: 2021 IEEE 23rd international conf on high performance computing & communications; 7th international conf on data science & systems; 19th international conf on smart city; 7th international conference on dependability in sensor, cloud & big data systems & application (HPCC/DSS/SmartCity/DependSys), Haikou, China, 20–22 December, pp. 853–860. New York: IEEE.
88.
DrechslerMFPeintnerJRewayF, et al. Mire, a mixed reality environment for testing of automated driving functions. IEEE Trans Veh Technol2022; 71: 34433456.
89.
SzalaiMVargaBTettamantiT, et al. Mixed reality test environment for autonomous cars using unity 3D and SUMO. In: 2020 IEEE 18th world symposium on applied machine intelligence and informatics (SAMI), Herlany, 23–25 January, pp. 73–78. New York: IEEE.
90.
ChenFLuYCaiB, et al. Multi-drone collaborative trajectory optimization for large-scale aerial 3D scanning. In: 2021 IEEE international symposium on mixed and augmented reality adjunct (ISMAR-adjunct), Bari, 4–8 October, pp. 121–126. New York: IEEE.
91.
XueFLuWChenZ, et al. From LiDAR point cloud towards digital twin city: clustering city objects based on gestalt principles. ISPRS J Photogr Rem Sens2020; 167: 418431.
92.
GuoMZhouYZhaoJ, et al. Urban geospatial information acquisition mobile mapping system based on close-range photogrammetry and IGS site calibration. Geo-Spatial Information Science2021; 24: 558–579.
93.
StoccoAPulferBTonellaP. Mind the gap! A study on the transferability of virtual vs physical-world testing of autonomous driving systems. IEEE Trans Softw Eng2023; 49: 1928–1940.
94.
ThielingJElspasPRoßmannJ. Neural networks for end-to-end refinement of simulated sensor data for automotive applications. In: 2019 IEEE international systems conference (SysCon), Orlando, FL, 8–11 April, pp. 1–8. New York: IEEE.
95.
GrandioJRiveiroBSoilánM, et al. Point cloud semantic segmentation of complex railway environments using deep learning. Autom Construct2022; 141: 104425.
96.
SahebdivaniSArefiHMaboudiM. Rail track detection and projection-based 3D modeling from UAV point cloud. Sensors2020; 20: 5220.
