Abstract
In practical engineering, it is difficult to establish complex nonlinear dynamic equations based on theories of mechanics. Data-driven models are built using neural networks in this paper to meet the needs of high dimension, multi-scale and high precision. We construct a two-coefficient loss function for whole data-driven modeling and substructure data-driven modeling according to the linear multi-step method. The forward Euler method is combined with trained neural networks to predict a five-degree-of-freedom duffing oscillator system. Comparative results show that the prediction accuracy of substructure data-driven modeling is higher than whole data-driven modeling, and the generalization and robustness of the model are verified. Meanwhile, the selection of training data and the number of hidden layers have a great impact on the prediction ability. Adopting an adjustable learning rate, adding control parameters to the network input shows better performance than not adding control parameters to the network input.
Similar content being viewed by others
Data availability
The data included in this study are available from the corresponding author upon request.
References
Zhang, D.: Nonlinear bending analysis of FGM beams based on physical neutral surface and high order shear deformation theory. Compos. Struct. 100(3), 121–126 (2013)
Tang, Y., Ding, Q.: Nonlinear vibration analysis of a bi-directional functionally graded beam under hygro-thermal loads. Compos. Struct. 225, 111076 (2019)
Li, L., Li, X.B., Hu, Y.J.: Free vibration analysis of nonlocal strain gradient beams made of functionally graded material. Int. J. Eng. Sci. 102, 77–92 (2016)
Wickert, J.A.: Non-linear vibration of a traveling tensioned beam. Int. J. Non-Linear Mech. 27(3), 503–517 (1992)
Belabed, Z., Houari, M.S.A., Tounsi, A., Mahmoud, S.R., Bég, O.A.: An efficient and simple higher order shear and normal deformation theory for functionally graded material (FGM) plates. Compos. Part B Eng. 60, 274–283 (2014)
Beni, Y.T., Mehralian, F., Razavi, H.: Free vibration analysis of size-dependent shear deformable functionally graded cylindrical shell on the basis of modified couple stress theory. Compos. Struct. 120, 65–78 (2015)
Rong, B., Rui, X.T., Tao, L., Wang, G.P.: Theoretical modeling and numerical solution methods for flexible multibody system dynamics. Nonlinear Dyn. 98(2), 1519–1553 (2019)
Wade, M.J.: Not just numbers: mathematical modelling and its contribution to anaerobic digestion processes. Processes 8, 888 (2020)
Brauer, F., Driessche, P., Wu, J.: Mathematical Epidemiology. Springer, Berlin (2008)
Rodhouse, P.G.K., Pierce, G.J., Nichols, O.C., et al.: Environmental effects on cephalopod population dynamics: Implications for management of fisheries. Adv. Mar. Biol. 67, 99–234 (2014)
Mike, S., Farmer, J.D.: An empirical behavioral model of liquidity and volatility. J. Econ. Dyn. Control 32, 200–234 (2008)
Chiuso, A., Pillonetto, G.: System identification: a machine learning perspective. Annu. Rev. Control Robot. Auton. Syst. 2, 281–304 (2019)
Li, H.R., Yamamoto, S.: Polynomial regression based model-free predictive control for nonlinear systems. In: 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE), pp. 578–582
Guo, F., Liu, B., Shi, X., Hao, X.C.: T-S fuzzy model identification of MIMO nonlinear systems based on data-driven. In: 2011 IEEE International Conference on Electronics, Communications and Control (ICECC), pp. 1186–1189 (2011)
Liu, J.Y., Zhu, B.L.: Application of BP neural network based on GA in function fitting. In: Proceedings of 2012 2nd International Conference on Computer Science and Network Technology (ICCSNT), pp. 875–878 (2012)
Song, X.X., Guo, Y., Li, N., Sun, B.M.: Target trajectory prediction based on optimized neural network. In: 2017 3rd IEEE International Conference on Computer and Communications (ICCC), pp. 1956–1960 (2017)
Cai, Y.J., Li, X., Han, J., Zeng, X.Y.: A configurable nonlinear operation unit for neural network accelerator. In: 2017 IEEE 12th International Conference on ASIC (ASICON), pp. 319–322 (2017)
Zhang, Y.L., Niu, J.G., Na, S.Y.: A novel nonlinear function fitting model based on FOA and GRNN. Math. Probl. Eng. 2019, 2697317 (2019)
Li, M., Wibowo, S., Guo, W.: Nonlinear curve fitting using extreme learning machines and radial basis function networks. Comput. Sci. Eng. 21(5), 6–15 (2019)
Xin, L., Wang, Y.C., Fu, H.X.: Omnidirectional mobile robot dynamic model identification by NARX neural network and stability analysis using the APLF method. Symmetry 12(9), 1430 (2020)
Zhang, J.B., Xiong, J.J., Lan, X.H., Shen, Y.N., Chen, X., Xi, Q.S.: Trajectory prediction of hypersonic glide vehicle based on empirical wavelet transform and attention convolutional long short-term memory network. IEEE Sens. J. 22(5), 4601–4615 (2022)
Liu, T.J., Liu, Y.B., Liu, J.Y., et al.: A Bayesian learning based scheme for online dynamic security assessment and preventive control. IEEE Trans. Power Syst. 35(5), 4088–4099 (2020)
Bingi, K., Prusty, B.R.: Forecasting models for chaotic fractional-order oscillators using neural networks. Int. J. Appl. Math. Comput. Sci. 31(3), 387–398 (2021)
Li, X., Ding, Q., Sun, J.Q.: Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Saf. 172, 1–11 (2018)
Li, K., Kou, J.Q., Zhang, W.W.: Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers. Nonlinear Dyn. 96(3), 2157–2177 (2019)
Li, W.J., Laima, S.J., Jin, X.W., Yuan, W.Y., Li, H.: A novel long short-term memory neural-network-based self-excited force model of limit cycle oscillations of nonlinear flutter for various aerodynamic configurations. Nonlinear Dyn. 100(3), 2071–2087 (2020)
Chen, H.C., Wei, D.Q.: Chaotic time series prediction using echo state network based on selective opposition grey wolf optimizer. Nonlinear Dyn. 104(4), 3925–3935 (2021)
Sui, Y.B., Gao, H.: Modified echo state network for prediction of nonlinear chaotic time series. Nonlinear Dyn. 110(4), 3581–3603 (2022)
Sharma, S., Padhy, P.K.: Extended B-polynomial neural network for time-delayed system modeling using sampled data. J. Intell. Fuzzy Syst. 41(2), 3277–3288 (2021)
Han, S., Choi, H.S., Choi, J., Choi, J.H., Kim, J.G.: A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations. Comput. Methods Appl. Mech. Eng. 373, 113480 (2020)
Eshkevari, S.S., Takáč, M., Pakzad, S.N., Jahani, M.: DynNet: Physics-based neural architecture design for nonlinear structural response modeling and prediction. Eng. Struct. 229, 111582 (2021)
Kampffmeyer, M., Løkse, S., Bianchi, F.M., Livi, L., Salberg, A.B., Jenssen, R.: Deep divergence-based approach to clustering. Neural Netw. 113, 91–101 (2019)
Xu, S., Amira, O., Liu, J.M., Zhang, C.X., Zhang, J.S., Li, G.H.: HAM-MFN: hyperspectral and multispectral image multiscale fusion network with RAP loss. IEEE Trans. Geosci. Remote Sens. 58(7), 4618–4628 (2020)
Togami, M.: Multi-channel Itakura Saito distance minimization with deep neural network. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 536–540 (2019)
Kumar, H., Sastry, P.S.: Robust loss functions for learning multi-class classifiers. In: 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 687–692 (2018)
Pan, S.W., Duraisamy, K.: Long-time predictive modeling of nonlinear dynamical systems using neural networks. Complexity 2018, 4801012 (2018)
Zhang, R.Y., Liu, Y., Sun, H.: Physics-informed multi-LSTM networks for metamodeling of nonlinear structures. Comput. Methods Appl. Mech. Eng. 369(4), 113226 (2020)
Lu, X.X., Yvonnet, J., Papadopoulos, L., Kalogeris, I., Papadopoulos, V.: A stochastc FE2 data-driven method for nonlinear multiscale modeling. Materials 14(11), 2875 (2021)
Morales, J., Yu, W.: Improving neural network’s performance using Bayesian inference. Neurocomputing 461, 319–326 (2021)
Ma, Z.S., Ding, Q., Zhai, Y.J.: Hybrid modeling of nonlinear-jointed structures via finite-element model reduction and deep learning techniques. J. Vib. Eng. Technol. 9(4), 575–585 (2020)
Yu, Y., Yao, H.P., Liu, Y.M.: Structural dynamics simulation using a novel physics-guided machine learning method. Eng. Appl. Artif. Intell. 96, 103947 (2020)
Li, M.W., Xu, D.Y., Geng, J., Hong, W.C.: A ship motion forecasting approach based on empirical mode decomposition method hybrid deep learning network and quantum butterfly optimization algorithm. Nonlinear Dyn. 107(3), 2447–2467 (2022)
Ahmad, Z., Ali, F., Khan, N., Khan, I.: Dynamics of fractal-fractional model of a new chaotic system of integrated circuit with Mittag-Leffler kernel. Chaos Solitons Fractals 153, 111602 (2021)
Khan, N., Ahmad, Z., Ahmad, H., Tchier, F., Zhang, X.Z., Murtaza, S.: Dynamics of chaotic system based on image encryption through fractal-fractional operator of non-local kernel. AIP Adv. 12(5), 055129 (2022)
Xu, W.T., Stein, M.L., Wisher, I.: Modeling and predicting chaotic circuit data. SIAM/ASA J. Uncertain. Quant. 7(1), 31–52 (2019)
Huang, W.J., Li, Y.T., Huang, Y.: Deep hybrid neural network and improved differential neuroevolution for chaotic time series prediction. IEEE Access 8, 159552–159565 (2020)
Bompas, S., Georgeot, B., Guery-Odelin, D.: Accuracy of neural networks for the simulation of chaotic dynamics: Precision of training data vs precision of the algorithm. Chaos 30(11), 113118 (2020)
Chen, Z., Xiu, D.B.: On generalized residual network for deep learning of unknown dynamical systems. J. Comput. Phys. 438, 110362 (2021)
Guo, Y.A., Cao, X.Q., Liu, B.N., Gao, M.: Solving partial differential equations using deep learning and physical constraints. Appl. Sci. 10(17), 5917 (2020)
Pu, J.C., Li, J., Chen, Y.: Solving localized wave solutions of the derivative nonlinear Schrödinger equation using an improved PINN method. Nonlinear Dyn. 105(2), 1723–1739 (2021)
Li, J.H., Chen, J.C., Li, B.A.: Gradient-optimized physics-informed neural networks (GOPINNs): a deep learning method for solving the complex modified KdV equation. Nonlinear Dyn. 107(1), 781–792 (2021)
Panghal, S., Kumar, M.: Optimization free neural network approach for solving ordinary and partial diferential equations. Eng. Comput. 37(4), 2989–3002 (2021)
Derkevorkian, A., Hernandez-Garcia, M., Yun, H.B., Masri, S.F., Li, P.Z.: Nonlinear data-driven computational models for response prediction and change detection. Struct. Control Health Monit. 22(2), 273–288 (2014)
Cai, J.T., Yin, Q., Ding, Q.: Data-driven modeling and response prediction of nonlinear multi-degree-of-freedom systems. J. Vib. Eng. 35(5), 1101–1108 (2022)
Yu, S.D., Wang, D.L.: Periodic, aperiodic and chaotic motions of harmonically excited SDOF and MDOF nonlinear dynamical systems. Eur. Phys. J. Spec. Top. 228(9), 1855–1871 (2019)
Funding
This project was funded by the National Natural Science Foundation of China (Nos. 11902038, 12272058 and 12272057).
Author information
Authors and Affiliations
Contributions
All authors contributed to the design and analysis of the model. Material preparation, data collection and analysis were performed by LZ, YS, AW and JZ. The first draft of the manuscript was written by LZ and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
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
Zhang, L., Sun, Y., Wang, A. et al. Neural network modeling and dynamic behavior prediction of nonlinear dynamic systems. Nonlinear Dyn 111, 11335–11356 (2023). https://doi.org/10.1007/s11071-023-08407-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-023-08407-9