Skip to main content
Erschienen in:

04.04.2024 | Original Article

A rapidly trained DNN model for real-time flexible multibody dynamics simulations with a fixed-time increment

verfasst von: Myeong-Seok Go, Young-Bae Kim, Jeong-Hoon Park, Jae Hyuk Lim, Jin-Gyun Kim

Erschienen in: Engineering with Computers | Ausgabe 5/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This study presents an efficient fixed-time increment-based approach for a data-driven analysis of flexible multibody dynamics (FMBD) problems, combining deep neural network (DNN) modeling and principal component analysis (PCA). To construct a DNN-based surrogate model, we eliminated the time instant in the input features while applying PCA to reduce the dimensionality of the output results, which encompassed transient dynamics such as displacement, stress, and strain. This restructuring allowed us to maintain the temporal information in the output data set while still formatting it in a fixed-time increment format, streamlining the process of training an efficient DNN model. Despite using fewer samples, this approach significantly reduces training costs compared to DNN model without PCA. Benchmark problems, including a double compound pendulum, piston-cylinder system, and deployable parabolic antenna, demonstrate that the proposed scheme drastically reduces training time while maintaining accuracy and quick prediction time.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Wehage KT, Wehage RA, Ravani B (2015) Generalized coordinate partitioning for complex mechanisms based on kinematic substructuring. Mech Mach Theory 92:464–483 Wehage KT, Wehage RA, Ravani B (2015) Generalized coordinate partitioning for complex mechanisms based on kinematic substructuring. Mech Mach Theory 92:464–483
2.
Zurück zum Zitat Wehage RA, Haug EJ (1982) Generalized coordinate partitioning for dimension reduction in analysis of constrained dynamic systems. J Mech Des 104(1):247–255 Wehage RA, Haug EJ (1982) Generalized coordinate partitioning for dimension reduction in analysis of constrained dynamic systems. J Mech Des 104(1):247–255
3.
Zurück zum Zitat Shabana AA (2003) Dynamics of multibody systems. Cambridge University Press, Cambridge Shabana AA (2003) Dynamics of multibody systems. Cambridge University Press, Cambridge
4.
Zurück zum Zitat Masoudi R, Uchida T, McPhee J (2015) Reduction of multibody dynamic models in automotive systems using the proper orthogonal decomposition. J Comput Nonlinear Dyn 10:1 Masoudi R, Uchida T, McPhee J (2015) Reduction of multibody dynamic models in automotive systems using the proper orthogonal decomposition. J Comput Nonlinear Dyn 10:1
5.
Zurück zum Zitat Brüls O, Duysinx P, Golinval J-C (2006) A model reduction method for the control of rigid mechanisms. Multibody SysDyn 15:213–227MathSciNet Brüls O, Duysinx P, Golinval J-C (2006) A model reduction method for the control of rigid mechanisms. Multibody SysDyn 15:213–227MathSciNet
6.
Zurück zum Zitat Yoo WS, Haug EJ (1986) Dynamics of flexible mechanical systems using vibration and static correction modes. J Mech Transm ASME 108:315–322 Yoo WS, Haug EJ (1986) Dynamics of flexible mechanical systems using vibration and static correction modes. J Mech Transm ASME 108:315–322
7.
Zurück zum Zitat Kim JG, Han JB, Lee H, Kim SS (2018) Flexible multibody dynamics using coordinate reduction improved by dynamic correction. Multibody SysDyn 42:411–429MathSciNet Kim JG, Han JB, Lee H, Kim SS (2018) Flexible multibody dynamics using coordinate reduction improved by dynamic correction. Multibody SysDyn 42:411–429MathSciNet
8.
Zurück zum Zitat Han JB, Kim JG, Kim SS (2019) An efficient formulation for flexible multibody dynamics using a condensation of deformation coordinates. Multibody SysDyn 47:293–316MathSciNet Han JB, Kim JG, Kim SS (2019) An efficient formulation for flexible multibody dynamics using a condensation of deformation coordinates. Multibody SysDyn 47:293–316MathSciNet
9.
Zurück zum Zitat Cammarata A (2021) Global modes for the reduction of flexible multibody systems methodology and complexity. Multibody SysDyn 53:59–83MathSciNet Cammarata A (2021) Global modes for the reduction of flexible multibody systems methodology and complexity. Multibody SysDyn 53:59–83MathSciNet
10.
Zurück zum Zitat Cammarata A (2020) Global flexible modes for the model reduction of planar mechanisms using the finite-element floating frame of reference formulation. J Sound Vib 489:115668 Cammarata A (2020) Global flexible modes for the model reduction of planar mechanisms using the finite-element floating frame of reference formulation. J Sound Vib 489:115668
11.
Zurück zum Zitat Lehner M, Eberhard P (2007) A two-step approach for model reduction in flexible multibody dynamics. Multibody SysDyn 17:157–176MathSciNet Lehner M, Eberhard P (2007) A two-step approach for model reduction in flexible multibody dynamics. Multibody SysDyn 17:157–176MathSciNet
12.
Zurück zum Zitat Fehr J, Eberhard P (2011) Simulation process of flexible multibody systems with non-modal model order reduction techniques. Multibody SysDyn 25:313–334 Fehr J, Eberhard P (2011) Simulation process of flexible multibody systems with non-modal model order reduction techniques. Multibody SysDyn 25:313–334
13.
Zurück zum Zitat Rutzmoser JB, Rixen DJ (2017) A lean and efficient snapshot generation technique for the hyper-reduction of nonlinear structural dynamics. Comput Methods Appl Mech Eng 325:330–349MathSciNet Rutzmoser JB, Rixen DJ (2017) A lean and efficient snapshot generation technique for the hyper-reduction of nonlinear structural dynamics. Comput Methods Appl Mech Eng 325:330–349MathSciNet
14.
Zurück zum Zitat Brüls O, Duysinx P, Golinval JC (2007) The global modal parameterization for non-linear model-order reduction in flexible multibody dynamics. Int J Numer Meth Eng 69:948–977MathSciNet Brüls O, Duysinx P, Golinval JC (2007) The global modal parameterization for non-linear model-order reduction in flexible multibody dynamics. Int J Numer Meth Eng 69:948–977MathSciNet
15.
Zurück zum Zitat Heirman GHK, Naets F, Desmet W (2011) Forward dynamical analysis of flexible multibody systems using system-level model reduction. Multibody SysDyn 25:97–113MathSciNet Heirman GHK, Naets F, Desmet W (2011) Forward dynamical analysis of flexible multibody systems using system-level model reduction. Multibody SysDyn 25:97–113MathSciNet
16.
Zurück zum Zitat Naets F, Tamarozzi T, Heirman GHK, Desmet W (2012) Real-time flexible multibody simulation with Global Modal Parameterization. Multibody SysDyn 27:267–284MathSciNet Naets F, Tamarozzi T, Heirman GHK, Desmet W (2012) Real-time flexible multibody simulation with Global Modal Parameterization. Multibody SysDyn 27:267–284MathSciNet
17.
Zurück zum Zitat Craig RR Jr, Bampton MC (1968) Coupling of substructures for dynamic analyses. Aiaa J 6:1313–1319 Craig RR Jr, Bampton MC (1968) Coupling of substructures for dynamic analyses. Aiaa J 6:1313–1319
18.
Zurück zum Zitat Kim JG, Lee PS (2015) An enhanced Craig–Bampton method. Int J Numer Methods Eng 103:79–93MathSciNet Kim JG, Lee PS (2015) An enhanced Craig–Bampton method. Int J Numer Methods Eng 103:79–93MathSciNet
19.
Zurück zum Zitat Wu L, Tiso P (2016) Nonlinear model order reduction for flexible multibody dynamics: a modal derivatives approach. Multibody SysDyn 36:405–425MathSciNet Wu L, Tiso P (2016) Nonlinear model order reduction for flexible multibody dynamics: a modal derivatives approach. Multibody SysDyn 36:405–425MathSciNet
20.
Zurück zum Zitat Mahdiabadi MK, Tiso P, Brandt A, Rixen DJ (2021) A non-intrusive model-order reduction of geometrically nonlinear structural dynamics using modal derivatives. Mech Syst Signal Process 147:107126 Mahdiabadi MK, Tiso P, Brandt A, Rixen DJ (2021) A non-intrusive model-order reduction of geometrically nonlinear structural dynamics using modal derivatives. Mech Syst Signal Process 147:107126
21.
Zurück zum Zitat Luo K, Hu HY, Liu C, Tian Q (2017) Model order reduction for dynamic simulation of a flexible multibody system via absolute nodal coordinate formulation. Comput Methods Appl Mech Eng 324:573–594MathSciNet Luo K, Hu HY, Liu C, Tian Q (2017) Model order reduction for dynamic simulation of a flexible multibody system via absolute nodal coordinate formulation. Comput Methods Appl Mech Eng 324:573–594MathSciNet
22.
Zurück zum Zitat Baumann M, Eberhard P (2017) Interpolation-based parametric model order reduction for material removal in elastic multibody systems. Multibody SysDyn 39:21–36MathSciNet Baumann M, Eberhard P (2017) Interpolation-based parametric model order reduction for material removal in elastic multibody systems. Multibody SysDyn 39:21–36MathSciNet
23.
Zurück zum Zitat Kim E, Kim H, Cho M (2017) Model order reduction of multibody system dynamics based on stiffness evaluation in the absolute nodal coordinate formulation. Nonlinear Dyn 87:1901–1915 Kim E, Kim H, Cho M (2017) Model order reduction of multibody system dynamics based on stiffness evaluation in the absolute nodal coordinate formulation. Nonlinear Dyn 87:1901–1915
24.
Zurück zum Zitat Peng H, Song N, Kan Z (2022) Data-driven model order reduction with proper symplectic decomposition for flexible multibody system. Nonlinear Dyn 107:173–203 Peng H, Song N, Kan Z (2022) Data-driven model order reduction with proper symplectic decomposition for flexible multibody system. Nonlinear Dyn 107:173–203
25.
Zurück zum Zitat Song N, Peng H, Kan Z (2022) A hybrid data-driven model order reduction strategy for flexible multibody systems considering impact and friction. Mech Mach Theory 169:104649 Song N, Peng H, Kan Z (2022) A hybrid data-driven model order reduction strategy for flexible multibody systems considering impact and friction. Mech Mach Theory 169:104649
26.
Zurück zum Zitat Kraft S, Causse J, Martinez A (2019) Black-box modelling of nonlinear railway vehicle dynamics for track geometry assessment using neural networks. Veh Syst Dyn 57:1241–1270 Kraft S, Causse J, Martinez A (2019) Black-box modelling of nonlinear railway vehicle dynamics for track geometry assessment using neural networks. Veh Syst Dyn 57:1241–1270
27.
Zurück zum Zitat Martin TP, Zaazaa KE, Whitten B, Tajaddini A (2007) Using a multibody dynamic simulation code with neural network technology to predict railroad vehicle-track interaction performance in real time. In: International design engineering technical conferences and computers and information in engineering conference, pp 1881–1891 Martin TP, Zaazaa KE, Whitten B, Tajaddini A (2007) Using a multibody dynamic simulation code with neural network technology to predict railroad vehicle-track interaction performance in real time. In: International design engineering technical conferences and computers and information in engineering conference, pp 1881–1891
28.
Zurück zum Zitat Ansari H, Tupy M, Datar M, Negrut D (2010) Construction and use of surrogate models for the dynamic analysis of multibody systems. SAE Int J Passenger Cars Mech Syst 3:8–20 Ansari H, Tupy M, Datar M, Negrut D (2010) Construction and use of surrogate models for the dynamic analysis of multibody systems. SAE Int J Passenger Cars Mech Syst 3:8–20
29.
Zurück zum Zitat Angeli A, Naets F, Desmet W (2019) A machine learning approach for minimal coordinate multibody simulation. In: European congress on computational methods in applied sciences and engineering. Springer, pp 417–424 Angeli A, Naets F, Desmet W (2019) A machine learning approach for minimal coordinate multibody simulation. In: European congress on computational methods in applied sciences and engineering. Springer, pp 417–424
30.
Zurück zum Zitat Angeli A, Desmet W, Naets F (2021) Deep learning for model order reduction of multibody systems to minimal coordinates. Comput Methods Appl Mech Eng 373:113517MathSciNet Angeli A, Desmet W, Naets F (2021) Deep learning for model order reduction of multibody systems to minimal coordinates. Comput Methods Appl Mech Eng 373:113517MathSciNet
31.
Zurück zum Zitat Byravan A, Fox D (2017) Se3-nets: learning rigid body motion using deep neural networks. In: 2017 IEEE international conference on robotics and automation (ICRA). IEEE, pp 173–180 Byravan A, Fox D (2017) Se3-nets: learning rigid body motion using deep neural networks. In: 2017 IEEE international conference on robotics and automation (ICRA). IEEE, pp 173–180
32.
Zurück zum Zitat Peng H, Song N, Li F, Tang S (2022) A mechanistic-based data-driven approach for general friction modeling in complex mechanical system. J Appl Mech 89:071005 Peng H, Song N, Li F, Tang S (2022) A mechanistic-based data-driven approach for general friction modeling in complex mechanical system. J Appl Mech 89:071005
33.
Zurück zum Zitat Ahn J-G, Yang H-I, Kim J-G (2022) Multi-fidelity meta modeling using composite neural network with online adaptive basis technique. Comput Methods Appl Mech Eng 388:114258MathSciNet Ahn J-G, Yang H-I, Kim J-G (2022) Multi-fidelity meta modeling using composite neural network with online adaptive basis technique. Comput Methods Appl Mech Eng 388:114258MathSciNet
34.
Zurück zum Zitat Choi H-S, An J, Han S, Kim J-G, Jung J-Y, Choi J, Orzechowski G, Mikkola A, Choi JH (2021) Data-driven simulation for general-purpose multibody dynamics using deep neural networks. Multibody SysDyn 51:419–454MathSciNet Choi H-S, An J, Han S, Kim J-G, Jung J-Y, Choi J, Orzechowski G, Mikkola A, Choi JH (2021) Data-driven simulation for general-purpose multibody dynamics using deep neural networks. Multibody SysDyn 51:419–454MathSciNet
35.
Zurück zum Zitat Ye YU, Huang P, Sun Y, Shi DC (2021) MBSNet: a deep learning model for multibody dynamics simulation and its application to a vehicle-track system. Mech Syst Signal Process 157:107716 Ye YU, Huang P, Sun Y, Shi DC (2021) MBSNet: a deep learning model for multibody dynamics simulation and its application to a vehicle-track system. Mech Syst Signal Process 157:107716
36.
Zurück zum Zitat Kurvinen E, Suninen I, Orzechowski G, Choi JH, Kim J-G, Mikkola A (2021) Accelerating design processes using data-driven models. In: Real-time simulation for sustainable production. Routledge, pp 65–76 Kurvinen E, Suninen I, Orzechowski G, Choi JH, Kim J-G, Mikkola A (2021) Accelerating design processes using data-driven models. In: Real-time simulation for sustainable production. Routledge, pp 65–76
37.
Zurück zum Zitat Hashemi A, Orzechowski G, Mikkola A, McPhee J (2023) Multibody dynamics and control using machine learning. Multibody Syst Dyn 2023:1–35MathSciNet Hashemi A, Orzechowski G, Mikkola A, McPhee J (2023) Multibody dynamics and control using machine learning. Multibody Syst Dyn 2023:1–35MathSciNet
38.
Zurück zum Zitat Han S, Choi H-S, Choi J, Choi JH, Kim J-G (2021) A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations. Comput Methods Appl Mech Eng 373:113480MathSciNet Han S, Choi H-S, Choi J, Choi JH, Kim J-G (2021) A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations. Comput Methods Appl Mech Eng 373:113480MathSciNet
39.
Zurück zum Zitat Go M-S, Han S, Lim JH, Kim J-G (2024) An efficient fixed-time increment-based data-driven simulation for general multibody dynamics using deep neural networks. Eng Comput 40:323–341 Go M-S, Han S, Lim JH, Kim J-G (2024) An efficient fixed-time increment-based data-driven simulation for general multibody dynamics using deep neural networks. Eng Comput 40:323–341
40.
Zurück zum Zitat Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2:37–52 Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2:37–52
41.
Zurück zum Zitat Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin ZM, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai JJ, Chintala S (2019) PyTorch: an imperative style, high-performance deep learning library. Adv Neur 32:8026–8037 Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin ZM, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai JJ, Chintala S (2019) PyTorch: an imperative style, high-performance deep learning library. Adv Neur 32:8026–8037
42.
Zurück zum Zitat Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536 Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536
43.
Zurück zum Zitat Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:1MathSciNet Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:1MathSciNet
44.
Zurück zum Zitat He X, Zhao K, Chu X (2021) AutoML: a survey of the state-of-the-art. Knowl-Based Syst 212:106622 He X, Zhao K, Chu X (2021) AutoML: a survey of the state-of-the-art. Knowl-Based Syst 212:106622
45.
Zurück zum Zitat Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, PMLR, pp 448–456 Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, PMLR, pp 448–456
46.
Zurück zum Zitat Jackson JE (2005) A user’s guide to principal components. Wiley, London Jackson JE (2005) A user’s guide to principal components. Wiley, London
47.
49.
Zurück zum Zitat MATLAB (2022) Version R2022a. The MathWorks Inc, Natick MATLAB (2022) Version R2022a. The MathWorks Inc, Natick
Metadaten
Titel
A rapidly trained DNN model for real-time flexible multibody dynamics simulations with a fixed-time increment
verfasst von
Myeong-Seok Go
Young-Bae Kim
Jeong-Hoon Park
Jae Hyuk Lim
Jin-Gyun Kim
Publikationsdatum
04.04.2024
Verlag
Springer London
Erschienen in
Engineering with Computers / Ausgabe 5/2024
Print ISSN: 0177-0667
Elektronische ISSN: 1435-5663
DOI
https://doi.org/10.1007/s00366-024-01962-8