This review paper explores how digital twin technology has evolved and its increasing applications while focusing on turbomachinery, including pumps, gas turbines, steam turbines, and wind turbines. The paper highlights the impact of digital twins on performance optimization, reducing downtime, and fault detection. Digital twins are virtual prototypes of physical systems that can simulate real-time operation, monitoring, and predictive maintenance to achieve high-value operational improvements. Advanced methodologies, like hybrid modeling, data-driven approaches, and machine learning techniques such as CNN, RNN, and LSTM models, are underlined in this paper, which ensures better performance in fault detection, performance prediction, and process optimization. Such approaches have been used to provide an accurate prognosis for gas turbines, renewable energy forecasting, and the real-time estimation of unsteady flow states in pumping stations. Most importantly, the integration of ML algorithms into digital twin frameworks gives much promise for improving turbomachinery operation in various directions: efficiency, reliability, and cost-effectiveness. Because of that, digital twin technology will be very promising toward the changing of present industrial strategies of maintenance to proactive, data-driven management of equipment in advanced engineering practices.
KritzingerWKarnerMTraarG, et al. Digital Twin in manufacturing: a categorical literature review and classification. IFAC-PapersOnLine2018; 51(11): 1016–1022.
2.
SunJYanZHanY, et al. Deep learning framework for gas turbine performance digital twin and degradation prognostics from airline operator perspective. Reliab Eng Syst Saf2023; 238: 109404.
3.
AmbaritaEEKarlsenAOsenO, et al. Towards fully autonomous floating offshore wind farm operation & maintenance. Energy Rep2023; 9: 103–108.
4.
YolcanOO. World energy outlook and state of renewable energy: 10-year evaluation. Innov Green Dev2023; 2(4): 100070.
5.
IbrahimTKMohammedMKAwadOI, et al. A comprehensive review on the exergy analysis of combined cycle power plants. Renew Sustain Energ Rev2018; 90: 835–850.
6.
MontoriFBedogniLBononiL. A collaborative internet of things architecture for smart cities and environmental monitoring. IEEE Internet Things J2018; 5(2): 592–605.
7.
SooriMArezooBDastresR. Virtual manufacturing in Industry 4.0: a review. Data Sci Manag2024; 7(1): 47–63.
8.
TahanMTsoutsanisEMuhammadM, et al. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: a review. Appl Energy2017; 198: 122–144.
9.
TaoFChengJQiQ, et al. Digital twin-driven product design, manufacturing and service with big data. Int J Adv Manuf Technol2018; 94(9–12): 3563–3576.
10.
DeSZhouYLarizgoitia AbadI, et al. Cyber–physical–social frameworks for Urban Big Data Systems: a survey. Appl Sci2017; 7(10): 1017.
11.
JavaidMHaleemASinghRP, et al. Digital economy to improve the culture of industry 4.0: a study on features, implementation and challenges. Green Technol Sustain2024; 2(2): 100083.
12.
QinJLiuYGrosvenorR. A categorical framework of manufacturing for Industry 4.0 and beyond. Procedia CIRP2016; 52: 173–178.
13.
MourtzisDVlachouEMilasN. Industrial Big Data as a result of IoT adoption in manufacturing. Procedia CIRP2016; 55: 290–295.
14.
KaurMJMishraVPMaheshwariP. The convergence of digital twin, IoT and machine learning: transforming data into action. In: FarsiMDaneshkhahAHosseinian-FarA, et al. (eds) Digital twin technologies and smart cities. Springer International Publishing, 2020, pp. 3–17.
15.
NegriEFumagalliLMacchiM. A review of the roles of digital twin in CPS-based production systems. Procedia Manuf2017; 11: 939–948.
16.
FaridFBelloAJahanN, et al. A review of the concept, applications, risks and control strategies for digital twin. In: SilhavyRSilhavyP (eds) Data analytics in system engineering. Springer Nature, 2024, pp. 264–282.
17.
TaoFZhangHLiuA, et al. Digital twin in industry: state-of-the-art. IEEE Trans Ind Inform2019; 15(4): 2405–2415.
18.
GrievesMVickersJ. Digital twin: mitigating unpredictable, undesirable emergent behavior in complex systems. In: KahlenFJFlumerfeltSlvesAA (eds) Transdisciplinary perspectives on complex systems. Springer International Publishing, 2017, pp. 85–113.
19.
BrennerBHummelV. Digital Twin as enabler for an innovative digital shopfloor management system in the ESB Logistics Learning Factory at Reutlingen - University. Procedia Manuf2017; 9: 198–205.
20.
UhlemannTHJLehmannCSteinhilperR. The digital twin: realizing the cyber-physical Production System for Industry 4.0. Procedia CIRP2017; 61: 335–340.
21.
QiQTaoFZuoY, et al. Digital Twin Service towards Smart Manufacturing. Procedia CIRP2018; 72: 237–242.
22.
SeegrünAKruschkeTMüggeJ, et al. Sustainable product lifecycle management with Digital Twins: a systematic literature review. Procedia CIRP2023; 119: 776–781.
23.
ErrandoneaIBeltránSArrizabalagaS. Digital Twin for maintenance: a literature review. Comput Ind2020; 123: 103316.
24.
RosenRvon WichertGLoG, et al. About the importance of autonomy and digital twins for the future of manufacturing. IFAC-PapersOnLine2015; 48(3): 567–572.
25.
SöderbergRWärmefjordKCarlsonJS, et al. Toward a digital twin for real-time geometry assurance in individualized production. CIRP Ann2017; 66(1): 137–140.
26.
XiaoDLinZYuA, et al. Data-driven method embedded physical knowledge for entire lifecycle degradation monitoring in aircraft engines. Reliab Eng Syst Saf2024; 247: 110100.
27.
GubbiJBuyyaRMarusicS, et al. Internet of Things (IoT): a vision, architectural elements, and future directions. Future Gener Comput Syst2013; 29(7): 1645–1660.
28.
HuMHeYLinX, et al. Digital twin model of gas turbine and its application in warning of performance fault. Chin J Aeronaut2023; 36(3): 449–470.
29.
ZhouLWangHXuS. Aero-engine gas path system health assessment based on depth digital twin. Eng Fail Anal2022; 142: 106790.
30.
WangCZhuZLuN, et al. A data-driven degradation prognostic strategy for aero-engine under various operational conditions. Neurocomputing2021; 462: 195–207.
31.
OlmedoLESchiffmannJ. Towards a real-time capable hybrid-twin for gas-bearing supported high-speed turbocompressors. Energy2023; 275: 127385.
32.
ZhangYZhangGWangJ, et al. Real-time information capturing and integration framework of the internet of manufacturing things. Int J Comput Integr Manuf2015; 28(8): 811–822.
33.
KostadinovAKolevK. Internet of things applications. In: 2021 IEEE engineering international research conference (EIRCON), 2021, pp. 1–4. Lima: IEEE.
34.
YangLYangSHPlotnickL. How the internet of things technology enhances emergency response operations. Technol Forecast Soc Change2013; 80(9): 1854–1867.
35.
MohammedA. Data driven-based model for predicting pump failures in the oil and gas industry. Eng Fail Anal2023; 145: 107019.
36.
AtzoriLIeraAMorabitoG. The Internet of Things: a survey. Comput Netw2010; 54(15): 2787–2805.
37.
ZaccariaVStenfeltMAslanidouI, et al. Fleet monitoring and diagnostics framework based on digital twin of aero-engines. In: Volume 6: ceramics; controls, diagnostics, and instrumentation; education; manufacturing materials and metallurgy, 2018, pp. V006T05A021. Oslo: American Society of Mechanical Engineers.
38.
TsoutsanisEMeskinN. Derivative-driven window-based regression method for gas turbine performance prognostics. Energy2017; 128: 302–311.
39.
GuanJWangXLvX, et al. Multidimensional analysis and performance prediction of heavy-duty gas turbine based on actual operational data. Appl Therm Eng2023; 234: 121280.
40.
LiuHXiaMWilliamsD, et al. Digital twin-driven machine condition monitoring: a literature review. J Sens2022; 2022: 1–13.
41.
YuJLiuPLiZ. Hybrid modelling and digital twin development of a steam turbine control stage for online performance monitoring. Renew Sustain Energ Rev2020; 133: 110077.
42.
WangZZhangYZengB, et al. Data-driven modeling of aero-derivative gas turbine start-up. J Therm Sci2025; 34(5): 1750–1757.
43.
Abou HouranMSalman BukhariSMZafarMH, et al. COA-CNN-LSTM: coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications. Appl Energy2023; 349: 121638.
44.
ChenYXiaoJWWangYW, et al. Regional wind-photovoltaic combined power generation forecasting based on a novel multi-task learning framework and TPA-LSTM. Energy Convers Manag2023; 297: 117715.
45.
De KooningJDMStockmanKDe MaeyerJ, et al. Digital twins for wind energy conversion systems: a literature review of potential modelling techniques focused on model fidelity and computational load. Processes2021; 9(12): 2224.
46.
GargSKrishnamurthiR. A CNN encoder decoder LSTM model for sustainable wind power predictive analytics. Sustain Comput Inform Syst2023; 38: 100869.
47.
BranlardEJonkmanJDanaS, et al. A digital twin based on OpenFAST linearizations for real-time load and fatigue estimation of land-based turbines. J Phys Conf Ser2020; 1618(2): 022030.
48.
Avendaño-ValenciaLDAbdallahIChatziE. Virtual fatigue diagnostics of wake-affected wind turbine via Gaussian process regression. Renew Energy2021; 170: 539–561.
49.
LeeWYDawesWCoullJ. The required aerodynamic simulation fidelity to usefully support a gas turbine digital twin for manufacturing. J Glob Power Propuls Soc2021; 5: 15–27.
50.
HeLWenKGongJ, et al. A multi-model ensemble digital twin solution for real-time unsteady flow state estimation of a pumping station. ISA Trans2022; 126: 242–253.
51.
SongTLiuCWuR, et al. A hierarchical scheme for remaining useful life prediction with long short-term memory networks. Neurocomputing2022; 487: 22–33.
52.
FangMZhangFYangY, et al. The influence of optimization algorithm on the signal prediction accuracy of VMD-LSTM for the pumped storage hydropower unit. J Energy Storage2024; 78: 110187.
53.
YuWZhouPMiaoZ, et al. Energy performance prediction of pump as turbine (PAT) based on PIWOA-BP neural network. Renew Energy2024; 222: 119873.
54.
ChenCLiuMLiM, et al. Digital twin modeling and operation optimization of the steam turbine system of thermal power plants. Energy2024; 290: 129969.
55.
YuJLiuPLiZ. A hybrid modelling approach to developing digital twins of an ultra-supercritical steam turbine control stage. Renew Sustain Energy Rev2020; 133: 110077.
56.
LiJWangYQiuZ, et al. Fast performance prediction and field reconstruction of gas turbine using supervised graph learning approaches. Aerosp Sci Technol2023; 140: 108425.
57.
KasatPKulkarniMGundetiK, et al. Developing a digital twin of centrifugal pump for performance evaluation. Mater Today Proc2023; 72: 1798–1802.
58.
SunLLiuTXieY, et al. Real-time power prediction approach for turbine using deep learning techniques. Energy2021; 233: 121130.
59.
TongZLiuHCaoXE, et al. Cavitation diagnosis for water distribution pumps: an early-stage approach combing vibration signal-based neural network with high-speed photography. Sustain Energy Technol Assess2023; 55: 102919.
60.
JordiZJErasmoCRafaelCA. Multi-criteria optimal design of small wind turbine blades based on deep learning methods. Energy2024; 293: 130625.
61.
CaoYTangXLiJ, et al. Flow field distribution and structural strength performance evaluation of fixed offshore wind turbine based on digital twin technology. Ocean Eng2023; 288: 116156.
62.
BadoraMBartosikPGrazianoA, et al. Using physics-informed neural networks with small datasets to predict the length of gas turbine nozzle cracks. Adv Eng Inform2023; 58: 102232.
63.
QinXChenLSunF, et al. Optimization for a steam turbine stage efficiency using a genetic algorithm. Appl Therm Eng2003; 23(18): 2307–2316.
64.
ChaibakhshAGhaffariA. Steam turbine model. Simul Model Pract Theory2008; 16(9): 1145–1162.
65.
StrušnikDMarčičMGolobM, et al. Energy efficiency analysis of steam ejector and electric vacuum pump for a turbine condenser air extraction system based on supervised machine learning modelling. Appl Energy2016; 173: 386–405.
66.
BaiMYangXLiuJ, et al. Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers. Appl Energy2021; 302: 117509.
67.
WangZZhouZXuW, et al. Physics informed neural networks for fault severity identification of axial piston pumps. J Manuf Syst2023; 71: 421–437.
68.
WangFChenGLiuK, et al. Health assessment of an electro-hydraulic servo pump control system for servomotor based on LGA deep neural network. Heliyon2024; 10(5): e26936.
69.
ZaidanMARelanRMillsAR, et al. Prognostics of gas turbine engine: an integrated approach. Expert Syst Appl2015; 42(22): 8472–8483.
70.
MarinaiLProbertDSinghR. Prospects for aero gas-turbine diagnostics: a review. Appl Energy2004; 79(1): 109–126.
71.
WangJZhangZLiuZ, et al. Digital twin aided adversarial transfer learning method for domain adaptation fault diagnosis. Reliab Eng Syst Saf2023; 234: 109152.
72.
WangZWangYWangX, et al. A Novel Digital Twin Framework for aeroengine performance diagnosis. Aerospace2023; 10(9): 789.
73.
FavaroPDolányiMValléeF, et al. Neural network informed day-ahead scheduling of pumped hydro energy storage. Energy2024; 289: 129999.
74.
LakshmananKTessiciniFGilAJ, et al. A fault prognosis strategy for an external gear pump using machine learning algorithms and synthetic data generation methods. Appl Math Model2023; 123: 348–372.
75.
RanawatNSPrakashJMiglaniA, et al. Performance evaluation of LSTM and Bi-LSTM using non-convolutional features for blockage detection in centrifugal pump. Eng Appl Artif Intell2023; 122: 106092.
76.
LiuXQuHHuangC, et al. Suction detection and suction suppression of centrifugal blood pump based on the FFT-GAPSO-LSTM model and speed modulation. Heliyon2024; 10(4): e25992.
77.
GuoJYangYLiH, et al. A parallel deep neural network for intelligent fault diagnosis of drilling pumps. Eng Appl Artif Intell2024; 133: 108071.
78.
QinSTaoJZhaoZ. Fault diagnosis of wind turbine pitch system based on LSTM with multi-channel attention mechanism. Energy Rep2023; 10: 4087–4096.
79.
AbbasHShaheenSAminM. Simple, flexible, and interoperable Scada system based on Agent Technology. Intell Control Autom2015; 06(03): 184–199.
80.
KarimMEMunirABKarimMA, et al. Energy revolution for our common future: an evaluation of the emerging international renewable energy law. Energies2018; 11(7): 1769.
81.
AdedipeTShafieeMZioE. Bayesian network modelling for the Wind Energy Industry: an overview. Reliab Eng Syst Saf2020; 202: 107053.
82.
ZhangZLiuTZhangD, et al. Water droplet erosion life prediction method for steam turbine blade materials based on image recognition and machine learning. J Eng Gas Turbine Power2021; 143(3): 031009.
83.
JorgensenJHodkiewiczMCrippsE, et al. Requirements for the application of the digital twin paradigm to offshore wind turbine structures for uncertain fatigue analysis. Comput Ind2023; 145: 103806.
84.
TianZXuLYuanJ, et al. Online performance monitoring platform based on the whole process models of subcritical coal-fired power plants. Appl Therm Eng2017; 124: 1368–1381.
85.
WangNLZhangYZhuLF, et al. Operation optimization approaches of thermal power units with big data-driven hybrid modeling. Appl Mech Mater2014; 631-632: 362–366.
86.
ZierathJRosenowSELutheJ, et al. A structural fatigue monitoring concept for wind turbines by means of digital twins. In: MaoZ. (ed) Model validation and uncertainty quantification. Vol. 3. Conference proceedings of the society for experimental mechanics series. Springer, 2020, pp. 139–142.
87.
Almeida CostaEde Menezes RebelloCViena SantanaV, et al. An uncertainty approach for electric submersible pump modeling through Deep Neural Network. Heliyon2024; 10(2): e24047.
88.
GlaessgenEStargelD. The digital twin paradigm for future NASA and U.S. Air Force vehicles. In: Proceedings of the 53rd AIAA/ASME/ASCE/AHS/ASC structures, structural dynamics and materials conference; 20th AIAA/ASME/AHS adaptive structures conference; 14th AIAA conference on composite materials, 2012. Honolulu: American Institute of Aeronautics and Astronautics.
89.
GasparisGLioWHMengF. Surrogate models for wind turbine electrical power and fatigue loads in wind farm. Energies2020; 13(23): 6360.
90.
TveitTMFogelholmCJ. Multi-period steam turbine network optimisation. Part I: simulation based regression models and an evolutionary algorithm for finding D-optimal designs. Appl Therm Eng2006; 26(10): 993–1000.
91.
WoodDA. Combined cycle gas turbine power output prediction and data mining with optimized data matching algorithm. SN Appl Sci2020; 2(3): 441.
92.
JorgensenJHodkiewiczMCrippsE, et al. Probabilistic assessment of the effect of bolt pre-load loss over time in offshore wind turbine bolted ring-flanges using a Gaussian process surrogate model. In: Proceedings of the ASME 2022 41st international conference on ocean, offshore and arctic engineering – volume 8: ocean renewable energy, 2022, p.V008T09A033. Hamburg: American Society of Mechanical Engineers.
93.
WagnerRSchleichBHaefnerB, et al. Challenges and potentials of Digital Twins and Industry 4.0 in product design and production for high performance products. Procedia CIRP2019; 84: 88–93.
94.
VolponiAJ. Gas turbine engine health management: past, present, and future trends. J Eng Gas Turbine Power2014; 136(5): 051201.
95.
HuWZhangTDengX, et al. Digital twin: a state-of-the-art review of its enabling technologies, applications and challenges. J Intell Manuf Spec Equip2021; 2(1): 1–34.
96.
ChacarteguiRSánchezDMuñozA, et al. Real time simulation of medium size gas turbines. Energy Convers Manag2011; 52(1): 713–724.
97.
LoCKChenCHZhongRY. A review of digital twin in product design and development. Adv Eng Inform2021; 48: 101297.
98.
SchroederGNSteinmetzCPereiraCE, et al. Digital Twin Data Modeling with AutomationML and a communication methodology for Data Exchange. IFAC-PapersOnLine2016; 49(30): 12–17.
99.
XiangSQinYLuoJ, et al. Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction. Reliab Eng Syst Saf2021; 216: 107927.
100.
ZayedSMAttiyaGMEl-SayedA, et al. A review study on digital twins with artificial intelligence and internet of things: concepts, opportunities, challenges, tools and future scope. Multimed Tools Appl2023; 82(30): 47081–47107.
101.
AliIAboelmagedMGovindanK, et al. Understanding the key determinants of IoT adoption for the digital transformation of the food and beverage industry. Ind Manag Data Syst2023; 123(7): 1887–1910.
102.
AggarwalPNarwalBMohapatraAK, et al. Digital twin in the aviation industry and the role of machine learning: a review. In: FongSDeyNJoshiA (eds) ICT analysis and applications. Springer Nature, 2023, pp. 445–455.
103.
BisantiGMMainettiLMontanaroT, et al. Digital twins for aircraft maintenance and operation: a systematic literature review and an iot-enabled modular architecture. Internet Things2023; 24: 100991.
104.
Durán-PolancoLSillerM. A taxonomy for decision making in IoT systems. Internet Things2023; 24: 100904.
105.
ErisODruryJLErcoliniD. A collaboration-centric taxonomy of the Internet of Things: implications for awareness support. Internet Things2021; 15: 100403.
106.
TsoutsanisEMeskinNBenammarM, et al. A component map tuning method for performance prediction and diagnostics of gas turbine compressors. Appl Energy2014; 135: 572–585.
107.
PourrahmaniHYavarinasabAZahediR, et al. The applications of Internet of Things in the automotive industry: a review of the batteries, fuel cells, and engines. Internet Things2022; 19: 100579.
108.
GochGKnappWHärtigF. Precision engineering for wind energy systems. CIRP Ann2012; 61(2): 611–634.
