Abstract
This paper presents a formalization of steps for identification of echo-state network (ESN)-based models for multiple-input and multiple-output (MIMO) nonlinear dynamic systems models, employing the best practices found in the literature. The ESN is a recurrent neural network capable to model nonlinear dynamics and it can be trained using computationally efficient algorithms. A simplified ESN architecture from the literature for process identification tasks is used and a procedure to create the model and tune the main hyperparameters is proposed. The proposed method is evaluated using both a simulated pH neutralization process and a real refrigeration compressor test rig. For each case study, the procedure to obtain the data series, the model creation, and the influence of each hyperparameter in the model performance are discussed. In both cases, the proposed model architecture presented better results than the linear model and the two nonlinear models used as baseline, namely an extreme learning machine-based Hammerstein model and a long short-term memory network model. The results show that the proposed ESN-based system identification method can be used to obtain MIMO models for nonlinear processes using a computationally efficient training algorithm. For the ESN architecture considered in the case studies, the training time is about 80 s, while a prediction can be obtained in about 15 ms.
Similar content being viewed by others
References
Antonelo, E. A., Camponogara, E., & Foss, B. (2017). Echo state networks for data-driven downhole pressure estimation in gas-lift oil wells. Neural Networks, 85, 106–117.
Ayoubi, M. (1994). Nonlinear dynamic systems identification with dynamic neural networks for fault diagnosis in technical processes. Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 3, 2120–2125.
Bessa, R., & Barreto, G. A. (2019). Robust echo state network for recursive system identification. In I. Rojas, G. Joya, & A. Catala (Eds.), Advances in computational intelligence (pp. 247–258). Springer.
Björk, E., & Palm, B. (2006). Performance of a domestic refrigerator under influence of varied expansion device capacity, refrigerant charge and ambient temperature. International Journal of Refrigeration, 29(5), 789–798. https://doi.org/10.1016/j.ijrefrig.2005.11.008
Boussaada, Z., Curea, O., Remaci, A., Camblong, H., & Mrabet Bellaaj, N. (2018). A nonlinear autoregressive exogenous (NARX) neural network model for the prediction of the daily direct solar radiation. Energies, 11(3), 620.
Chen, Y., He, Z., Shang, Z., Li, C., Li, L., & Xu, M. (2019). A novel combined model based on echo state network for multi-step ahead wind speed forecasting: A case study of NREL. Energy conversion and management, 179, 13–29.
Fernandez, B., Parlos, A., & Tsai, W. (1990). Nonlinear dynamic system identification using artificial neural networks (ANNs). In 1990 IJCNN international joint conference on neural networks, (IEEE).
Ganguli, S., Huh, D., & Sompolinsky, H. (2008). Memory traces in dynamical systems. Proceedings of the National Academy of Sciences, 105(48), 18970–18975. https://doi.org/10.1073/pnas.0804451105
Gomez, J., Jutan, A., & Baeyens, E. (2004). Wiener model identification and predictive control of a pH neutralisation process. IEE Proceedings-Control Theory and Applications, 151(3), 329–338.
Guo, Y., Wang, F., Chen, B., & Xin, J. (2017). Robust echo state networks based on correntropy induced loss function. Neurocomputing, 267, 295–303. https://doi.org/10.1016/j.neucom.2017.05.087
Han, M., & Xu, M. (2018). Laplacian echo state network for multivariate time series prediction. IEEE Transactions on Neural Networks and Learning Systems, 29(1), 238–244. https://doi.org/10.1109/tnnls.2016.2574963
Henson, M. A., & Seborg, D. E. (1994). Adaptive nonlinear control of a pH neutralization process. IEEE Transactions on Control Systems Technology, 2(3), 169–182.
Hochreiter, S. (1998). The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(2), 107–116.
Inubushi, M., & Yoshimura, K. (2017). Reservoir computing beyond memory-nonlinearity trade-off. Scientific Reports. https://doi.org/10.1038/s41598-017-10257-6
Isermann, R., & Münchof, M. (2011). Identification of dynamic systems. Springer.
Jaeger, H. (2001). The “echo state” approach to analysing and training recurrent neural networks. Tech. Rep. 34, German National Research Center for Information Technology, Bonn, Germany.
Jaeger, H. (2003). Adaptive nonlinear system identification with echo state networks. Advances in Neural Information Processing Systems (NIPS 2003) (pp. 609–616).
Jaeger, H., Lukoševičius, M., Popovici, D., & Siewert, U. (2007). Optimization and applications of echo state networks with leaky: Integrator neurons. Neural Networks, 20(3), 335–352. https://doi.org/10.1016/j.neunet.2007.04.016
Li, D., Han, M., & Wang, J. (2012). Chaotic time series prediction based on a novel robust echo state network. IEEE Transactions on Neural Networks and Learning Systems, 23(5), 787–799. https://doi.org/10.1109/tnnls.2012.2188414
Ljung, L., Andersson, C., Tiels, K., & Schön, T. B. (2020). Deep learning and system identification. In Proc IFAC Congress.
Lukoševičius, M. (2012). A practical guide to applying echo state networks. In G. Montavon, G. B. Orr, & K. R. Müller (Eds.), Neural networks tricks of the trade (pp. 659–686). Springer.
Lukoševičius, M., & Jaeger, H. (2009). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3), 127–149.
Lun, S. X., Yao, X. S., Qi, H. Y., & Hu, H. F. (2015). A novel model of leaky integrator echo state network for time-series prediction. Neurocomputing, 159, 58–66. https://doi.org/10.1016/j.neucom.2015.02.029
Nelles, O. (2001). Nonlinear system identification. Springer.
Qiao, J., Wang, L., & Yang, C. (2018). Adaptive lasso echo state network based on modified Bayesian information criterion for nonlinear system modeling. Neural Computing and Applications (pp. 1–15).
Rodan, A., & Tino, P. (2010). Minimum complexity echo state network. IEEE Transactions on Neural Networks, 22(1), 131–144.
Schoukens, J., & Ljung, L. (2019). Nonlinear system identification: A user-oriented road map. IEEE Control Systems Magazine, 39(6), 28–99. https://doi.org/10.1109/MCS.2019.2938121
Schwedersky, B. B., Flesch, R. C. C., & Dangui, H. A. C. (2018). Practical nonlinear model predictive control using an echo state network model. In 2018 International Joint Conference on Neural Networks (IJCNN) (pp. 1–8). https://doi.org/10.1109/IJCNN.2018.8489446
Schwedersky, B. B., Flesch, R. C. C., & Dangui, H. A. (2019). Practical nonlinear model predictive control algorithm for long short-term memory networks. IFAC-PapersOnLine, 52(1), 468–473. https://doi.org/10.1016/j.ifacol.2019.06.106
Shi, Z., & Han, M. (2007). Support vector echo-state machine for chaotic time-series prediction. IEEE Transactions on Neural Networks, 18(2), 359–372. https://doi.org/10.1109/tnn.2006.885113
Tang, Y., Li, Z., & Guan, X. (2014). Identification of nonlinear system using extreme learning machine based Hammerstein model. Communications in Nonlinear Science and Numerical Simulation, 19(9), 3171–3183.
Verzelli, P., Alippi, C., & Livi, L. (2019). Echo state networks with self-normalizing activations on the hyper-sphere. Scientific Reports. https://doi.org/10.1038/s41598-019-50158-4
Wainrib, G., & Galtier, M. N. (2016). A local echo state property through the largest Lyapunov exponent. Neural Networks, 76, 39–45. https://doi.org/10.1016/j.neunet.2015.12.013
Yang, C., Qiao, J., Ahmad, Z., Nie, K., & Wang, L. (2019). Online sequential echo state network with sparse RLS algorithm for time series prediction. Neural Networks, 118, 32–42.
Yildiz, I. B., Jaeger, H., & Kiebel, S. J. (2012). Re-visiting the echo state property. Neural Networks, 35, 1–9.
Yu, W. (2004). Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms. Information Sciences, 158, 131–147. https://doi.org/10.1016/j.ins.2003.08.002
Zhou, H., Huang, J., Lu, F., Thiyagalingam, J., & Kirubarajan, T. (2018). Echo state kernel recursive least squares algorithm for machine condition prediction. Mechanical Systems and Signal Processing, 111, 68–86. https://doi.org/10.1016/j.ymssp.2018.03.047
Acknowledgements
An early version of paper was presented at XXIII Congresso Brasileiro de Automática (CBA 2020). This study was funded in part by the Brazilian National Council for Scientific and Technological Development (CNPq) under Grants 140283/2018-8 and 309244/2018-8, and in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-Brasil (CAPES)-Finance Code 001.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict 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
About this article
Cite this article
Schwedersky, B.B., Flesch, R.C.C. & Dangui, H.A.S. Nonlinear MIMO System Identification with Echo-State Networks. J Control Autom Electr Syst 33, 743–754 (2022). https://doi.org/10.1007/s40313-021-00874-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40313-021-00874-y