Abstract
As a technology for the interaction and integration of products and simulation models, the digital twin can achieve accurate prediction and evaluation of product performance. However, the accurate model base is computationally complex, has a long iteration time, and is unable to perceive changes in the operating state in time. This leads to poor adaptability of the model and low efficiency of performance evaluation. The surrogate model can simplify the above model and improve computational efficiency. Based on this, this paper proposes a digital twin modelling and updating approach. The surrogate model is applied to the digital twin modelling process, which can accurately describe the physical mechanism and achieve interaction with the physical world. Then, this paper defines the consistency metric function, which achieves the rapid perception of the operation state and follows the physical world. Meanwhile, an improved LHS-Adam model update algorithm is used to adaptively update the model structure, improving the efficiency of the model parameters adjustment. Finally, experiments are conducted on the bogie suspension system to verify the feasibility and effectiveness of the update method in practical applications. The experimental results show that the established digital twin model has good updating performance and more efficient performance evaluation capability.
Similar content being viewed by others
Abbreviations
- N :
-
The number of units in the input layer
- p :
-
The number of units in the hidden layer
- \(\left\| {x - c_{p} } \right\|\) :
-
The input of the pth unit
- \(\sigma_{p}\) :
-
The flatness of the pth Gaussian function
- w :
-
Weighting coefficient
- \(d_{i}\) :
-
Status input parameters
- \(\lambda_{i}\) :
-
Range of values of \(d_{i}\)
- \(U_{r}\) :
-
Physical space
- \(U_{si}\) :
-
Simulation model
- \(\max C( \, \cdot { ,} \cdot \, )\) :
-
The current local search output parameter
- \((x_{i\_new} ,y_{i\_new} )\) :
-
Sample set after resampling for \(U_{si}\)
- \(m_{t}\) :
-
Weight update of the first-order moment estimation
- β 1, β 2 :
-
The decay rate of the hyperparameter control shift mean
- \(\overset{\lower0.5em\hbox{$\smash{\scriptscriptstyle\frown}$}}{v}_{t}\) :
-
The update of the corrected second-order moment estimation weights
- t :
-
The number of iterations
- ε:
-
Smooth term of RBF
- θ:
-
The threshold of RBF
- \(T_{k}\) :
-
The consistency metric function
- \(y_{k}\) :
-
Surrogate model predictions at moment k
- p k :
-
Physical space actuals at moment k
- \(H_{k}\) :
-
Predefined thresholds of \(T_{k}\)
- \({\text{LHS}}(n,m)\) :
-
Latin cubic matrix
- \(A_{i}\) :
-
Global search results of \({\text{LHS}}(n,m)\)
- \(A_{i}^{(\max )}\) :
-
Optimal Output Parameters of \({\text{LHS}}(n,m)\)
- \(B_{i - 1}^{(i)} ,B_{i + 1}^{(i)}\) :
-
Greedy Algorithm Solving of \(T_{k}\)
- Z :
-
parameter solving set
- \(y_{i}\) :
-
Twin model output predictions
- \(v_{t}\) :
-
Weight update of the second-order moment estimation
- \(\overset{\lower0.5em\hbox{$\smash{\scriptscriptstyle\frown}$}}{m}_{t}\) :
-
The update of the corrected first-order moment estimation weights
- α:
-
Learning rate
- \(\mu\) :
-
The equivalent taper
References
Yu J, Song Y, Tang D, Dai J (2021) A digital twin approach based on nonparametric bayesian network for complex system health monitoring. J Manuf Syst 58:293–304
Zhang W, Wang S, Hou L, Jiao RJ (2021) Operating data-driven inverse design optimization for product usage personalization with an application to wheel loaders. J Ind Inf Integr 23:100212
Lützenberger J, Klein P, Hribernik K, Thoben K (2016) Improving product-service systems by exploiting information from the usage phase. A case study. Procedia Cirp 47:376–381
Xin Y, Chen Y, Li W, Li X, Wu F (2022) Refined simulation method for computer-aided process planning based on digital twin technology. Micromachines (Basel) 13:620
Napoleone A, Macchi M, Pozzetti A (2020) A review on the characteristics of cyber-physical systems for the future smart factories. J Manuf Syst 54:305–335
Negri E, Berardi S, Fumagalli L, Macchi M (2020) Mes-integrated digital twin frameworks. J Manuf Syst 56:58–71
Segovia M, Garcia-Alfaro J (2022) Design, modeling and implementation of digital twins. Sensors (Basel) 22:5396
Magargle R, Johnson L, Mandloi P, Davoudabadi P, Kesarkar O, Krishnaswamy S, Batteh J, Pitchaikani A (2017) A simulation-based digital twin for model-driven health monitoring and predictive maintenance of an automotive braking system. Modelica, pp 132–133
Zhu D, Li Z, Hu N (2022) Multi-body dynamics modeling and analysis of planetary gearbox combination failure based on digital twin. Applied Sciences 12:12290
Alam KM, El Saddik A (2017) C2ps: a digital twin architecture reference model for the cloud-based cyber-physical systems. Ieee Access 5:2050–2062
Mack Y, Goel T, Shyy W, Haftka R (2007) Surrogate model-based optimization framework: a case study in aerospace design. Evolutionary computation in dynamic and uncertain environments (Springer) 51:323–342
Grieves M (2014) Digital twin: manufacturing excellence through virtual factory replication. White Paper 1:1–7
Glaessgen E, Stargel D (2012) The digital twin paradigm for future nasa and us air force vehicles. 53rd AIAA/ASME/ASCE/AHS/ASC structures, structural dynamics and materials Conference, 20th AIAA/ASME/AHS adaptive structures conference 14th AIAA, pp 1818. https://doi.org/10.2514/6.2012-1818
Agnusdei GP, Elia V, Gnoni MG (2021) A classification proposal of digital twin applications in the safety domain. Comput Ind Eng 154:107137
Voropai NI, Stennikov VA, Barakhtenko EA (2018) Methodological principles of constructing the integrated energy supply systems and their technological architecture. Journal of Physics: Conference Series. IOP Publishing, pp 12001. https://iopscience.iop.org/article/10.1088/1742-6596/1111/1/012001/meta
Liu S, Bao J, Lu Y, Li J, Lu S, Sun X (2021) Digital twin modeling method based on biomimicry for machining aerospace components. J Manuf Syst 58:180–195
Coelho F, Relvas S, Barbosa-Póvoa AP (2021) Simulation-based decision support tool for in-house logistics: the basis for a digital twin. Comput Ind Eng 153:107094
Qin C, Tao J, Liu C (2019) A novel stability prediction method for milling operations using the holistic-interpolation scheme. Proc Inst Mech Eng Part C: J Mech Eng Sci 233:4463–4475
Lu Y, Liu C, Kevin I, Wang K, Huang H, Xu X (2020) Digital twin-driven smart manufacturing: connotation, reference model, applications and research issues. Robot Comput Integr Manuf 61:101837
Shevlyugin MV, Korolev AA, Golitsyna AE, Pletnev DS (2019) Electric stock digital twin in a subway traction power system. Russ Electr Eng 90:647–652
Meng Z, Tang T, Wei G, Yuan L (2020) Digital twin based comfort scenario modeling of ato controlled train. Journal of Physics: Conference Series. IOP Publishing, pp 12071. https://iopscience.iop.org/article/10.1088/1742-6596/1654/1/012071/meta
Liu L, Zhang X, Wan X, Zhou S, Gao Z (2022) Digital twin-driven surface roughness prediction and process parameter adaptive optimization. Adv Eng Inform 51:101470
Sisson W, Karve P, Mahadevan S (2022) Digital twin approach for component health-informed rotorcraft flight parameter optimization. Aiaa J 60:1923–1936
Wang M, Wang C, Hnydiuk-Stefan A, Feng S, Atilla I, Li Z (2021) Recent progress on reliability analysis of offshore wind turbine support structures considering digital twin solutions. Ocean Eng 232:109168
Angione C, Silverman E, Yaneske E (2022) Using machine learning as a surrogate model for agent-based simulations. Plos One 17:e263150
Li Y, Zhang W, Xiong Q, Lu T, Mei G (2016) A novel fault diagnosis model for bearing of railway vehicles using vibration signals based on symmetric alpha-stable distribution feature extraction. Shock Vib. https://doi.org/10.1155/2016/5714195
Kreuzer M, Schmidt A, Kellermann W (2021) Novel features for the detection of bearing faults in railway vehicles. INTER-NOISE and NOISE-CON Congress and Conference Proceedings. Institute of Noise Control Engineering 263(3):3833–3844
Hesser DF, Altun K, Markert B (2022) Monitoring and tracking of a suspension railway based on data-driven methods applied to inertial measurements. Mech Syst Signal Process 164:108298
Jesussek M, Ellermann K (2014) Fault detection and isolation for a full-scale railway vehicle suspension with multiple kalman filters. Veh Syst Dyn 52:1695–1715
Zhao Y, Liang B, Iwnicki S (2014) Friction coefficient estimation using an unscented kalman filter. Veh Syst Dyn 52:220–234
Bernal E, Spiryagin M, Vollebregt E, Oldknow K, Stichel S, Shrestha S, Ahmad S, Wu Q, Sun Y, Cole C (2022) Prediction of rail surface damage in locomotive traction operations using laboratory-field measured and calibrated data. Eng Fail Anal 135:106165
Karttunen K, Kabo E, Ekberg A (2014) Numerical assessment of the influence of worn wheel tread geometry on rail and wheel deterioration. Wear 317:77–91
Wang J, Ren Z, Chen J, Chen L (2017) Study on rail profile optimization based on the nonlinear relationship between profile and wear rate. Math Probl Eng. https://doi.org/10.1155/2017/6956514
Ye Y, Sun Y, Dongfang S, Shi D, Hecht M (2021) Optimizing wheel profiles and suspensions for railway vehicles operating on specific lines to reduce wheel wear: a case study. Multibody Syst Dyn 51:91–122
Tsunashima H (2019) Condition monitoring of railway tracks from car-body vibration using a machine learning technique. Appl Sci 9:2734
Li C, He Q, Wang P (2022) Estimation of railway track longitudinal irregularity using vehicle response with information compression and bayesian deep learning. Comput-Aided Civil Infrastruct Eng 37:1260–1276
Yao Y, Li G, Wu G, Zhang Z, Tang J (2020) Suspension parameters optimum of high-speed train bogie for hunting stability robustness. Int J Rail Transp 8:195–214
Zhang Z (2018) Improved adam optimizer for deep neural networks. 2018 IEEE/ACM 26th international symposium on quality of service (IWQoS). Ieee, pp 1–2. https://ieeexplore.ieee.org/abstract/document/8624183
Bosso N, Magelli M, Trinchero R, Zampieri N (2023) Application of machine learning techniques to build digital twins for long train dynamics simulations. Veh Syst Dyn:1–20. https://doi.org/10.1080/00423114.2023.2174885
Attivissimo F, Danese A, Giaquinto N, Sforza P (2007) A railway measurement system to evaluate the wheel–rail interaction quality. Ieee Trans Instrum Meas 56:1583–1589
Funding
The authors gratefully acknowledge the financial support of the National Key Research and Development Program of China (Grant number 2020YFB1708003), Shandong Natural Science Foundation (Grant number ZR2020QE295), and the Taishan Scholars Program of Shandong Province (ts20190914).
Author information
Authors and Affiliations
Contributions
All authors contributed to this study, including original ideas, technical articulation, validation, and writing.
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, X., Han, X., Wang, H. et al. A modelling and updating approach of digital twin based on surrogate model to rapidly evaluate product performance. Int J Adv Manuf Technol 129, 5059–5074 (2023). https://doi.org/10.1007/s00170-023-12646-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-023-12646-w