Deep Learning Based-Model Observer For Prediction Of Nonlinear With Time-Delay System

Authors

  • Santo Wijaya Computer Science Department BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University, Jakarta 11480, Indonesia
  • Muhammad Zarlis Information System Management Department BINUS Graduate Program – Master of Information System Management, Bina Nusantara University, Jakarta 11480, Indonesia
  • Ford Lumban Gaol Computer Science Department BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University, Jakarta 11480, Indonesia
  • Antoni Wibowo Computer Science Department BINUS Graduate Program – Master of Computer Science, Bina Nusantara University, Jakarta 11480, Indonesia

Keywords:

Deep learning, Model observer, Nonlinear time delay system, N-step ahead prediction, Time series prediction

Abstract

Nonlinear time-delay systems, such as cloud-based control systems (CCS), have wide implementations, from robotics to multi-agent systems, but data-driven research on this complex system is still in its infancy. This study presents a model observer designed for the prediction of nonlinear time-delay systems utilizing Deep Learning (DL) methods. The time-delay Markov decision process is considered in the augmented state as an input feature for the model observer. Furthermore, additional input features include the dynamic rate of change to provide temporal nonlinearity and time delay for better prediction. The time-series prediction analysis is conducted on a dataset from an arbitrary nonlinear mass spring damper system induced by a time delay in the system input and output. This study thoroughly evaluates the performance of three DL networks, including the Feed Forward Neural Network (FFNN), Long Short Term Memory (LSTM), and Radial Basis Function Neural Network (RBFNN). While, the model prediction performance is evaluated with Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) performance metrics. Results show that the FFNN architecture of two hidden layers with 15 nodes in each layer and the LeakyReLU activation function achieves the best performance, outperforming other network layers with an average MAPE value of 8.4% and an average RMSE value of 0.0006038. The N-step ahead prediction performance of the model observer with the proposed features in this study serves as an important fundamental model for the development of control methods based on a data-driven approach for CCS.

Downloads

Download data is not yet available.

References

P. Zheng et al., “Smart manufacturing systems for Industry 4.0: Conceptual framework, scenarios, and future perspectives,” Frontiers of Mechanical Engineering, vol. 13, no. 2, pp. 137–150, 2018, doi: 10.1007/s11465-018-0499-5.

R. Langmann and M. Stiller, “The PLC as a smart service in industry 4.0 production systems,” Applied Sciences, vol. 9, no. 18, p. 3815, Sep. 2019, doi: 10.3390/app9183815.

Y. Xia, “Cloud control systems,” IEEE/CAA Journal of Automatica Sinica, vol. 2, no. 2, pp. 134–142, Apr. 2015, doi: 10.1109/jas.2015.7081652.

P. Papcun, E. Kajati, C. Liu, R. Y. Zhong, J. Koziorek, and I. Zolotova, “Cloud-based control of industrial cyber-physical systems,” Proceedings of International Conference on Computers and Industrial Engineering, CIE, pp. 1–14, 2018.

P. Skarin and K.-E. Årzén, “Explicit MPC recovery for cloud control systems,” 2021 60th IEEE Conference on Decision and Control (CDC), pp. 5394–5401, Dec. 2021, doi: 10.1109/cdc45484.2021.9683307.

M. S. Darup and T. Jager, “Encrypted Cloud-based Control using Secret Sharing with One-time Pads,” 2019 IEEE 58th Conference on Decision and Control (CDC), pp. 7215–7221, Dec. 2019, doi: 10.1109/cdc40024.2019.9029342.

J. Zhang, Y. Xia, Z. Sun, and D. Chen, “Event-Triggered Disturbance Rejection control for CPSs,” in CRC Press eBooks, 2021, pp. 153–180. doi: 10.1201/9781003260882-12.

H. Yang, S. Ju, Y. Xia, and J. Zhang, “Predictive cloud control for networked multiagent systems with quantized signals under DOS attacks,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 51, no. 2, pp. 1345–1353, Feb. 2021, doi: 10.1109/tsmc.2019.2896087.

S. Wijaya, A. Ramadhan, and A. Andhika, “Cloud-based control systems: a systematic literature review,” International Journal of Reconfigurable & Embedded Systems (IJRES), vol. 12, no. 1, p. 135, Mar. 2023, doi: 10.11591/ijres.v12.i1.pp135-148.

A. Dong, Z. Du, and Z. Yan, “Round trip time prediction using recurrent neural networks with minimal gated unit,” IEEE Communications Letters, vol. 23, no. 4, pp. 584–587, Apr. 2019, doi: 10.1109/lcomm.2019.2899603.

W. Hao and Y. Han, “Data Driven Control with Learned Dynamics: Model-Based versus Model-Free Approach.,” arXiv (Cornell University), Jun. 2020, [Online]. doi: 10.48550/ARXIV.2006.09543

N. Verba, K.-M. Chao, J. Lewandowski, N. Shah, A. James, and F. Tian, “Modeling industry 4.0 based fog computing environments for application analysis and deployment,” Future Generation Computer Systems, vol. 91, pp. 48–60, Feb. 2019, doi: 10.1016/j.future.2018.08.043.

N. N. Hasibuan, M. Zarlis, and S. Efendi, “Detection and tracking different type of cars with YOLO model combination and deep sort algorithm based on computer vision of traffic controlling,” Jurnal Dan Penelitian Teknik Informatika, vol. 6, no. 1, pp. 210–221, 2021, doi: 10.33395/sinkron.v6i1.11231.

F. Izhari, M. Zarlis, and S. Sutarman, “Analysis of backpropagation neural neural network algorithm on student ability based cognitive aspects,” IOP Conference Series, vol. 725, no. 1, p. 012103, 2020, doi: 10.1088/1757-899x/725/1/012103.

S. F. Wijaya, F. L. Gaol, A. Wibowo, and L. Wang, “Neural controller design for a class of nonlinear systems with time-varying delay: A bibliometric analysis-based short literature review,” 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), Feb. 2023, doi: 10.1109/iccosite57641.2023.10127776.

S. Ramstedt, “Real-Time Reinforcement learning,” arXiv.org, Nov. 11, 2019. http://arxiv.org/abs/1911.04448

B. Chen, M. Xu, L. Zhang, and D. Zhao, “Delay-aware model-based reinforcement learning for continuous control,” Neurocomputing, vol. 450, pp. 119–128, Aug. 2021, doi: 10.1016/j.neucom.2021.04.015.

S. F. Wijaya, Y. Heryadi, Y. Arifin, W. Suparta, and L. Lukas, “Long short-term memory (LSTM) model-based reinforcement learning for nonlinear mass spring damper system control,” Procedia Computer Science, vol. 216, pp. 213–220, Jan. 2023, doi: 10.1016/j.procs.2022.12.129.

S. J. Yoo, “Neural-Network-Based adaptive resilient dynamic surface control against unknown deception attacks of uncertain nonlinear Time-Delay cyberphysical systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 10, pp. 4341–4353, Oct. 2020, doi: 10.1109/tnnls.2019.2955132.

J. P. Yang, “Theoretical formulation of Three-Mass vehicle model for Vehicle–Bridge Interaction,” International Journal of Structural Stability and Dynamics, vol. 21, no. 07, p. 2171004, Apr. 2021, doi: 10.1142/s0219455421710048.

Z. Li, F. A. Khasawneh, X. Yin, A. Li, and Z. Song, “A new microscopic traffic model using a Spring-Mass-Damper-Clutch system,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 8, pp. 3322–3331, Aug. 2020, doi: 10.1109/tits.2019.2926146.

E. I. Altman, “Applications of Distress Prediction Models: What Have We Learned After 50 Years from the Z-Score Models?,” International Journal of Financial Studies, vol. 6, no. 3, p. 70, Aug. 2018, doi: 10.3390/ijfs6030070.

LiTeng, XuZhiyuan, TangJian, and WangYanzhi, “Model-free control for distributed stream data processing using deep reinforcement learning,” Proceedings of the VLDB Endowment, vol. 11, no. 6, pp. 705–718, Feb. 2018, doi: 10.14778/3199517.3199521.

A. Nagabandi, G. Kahn, R. S. Fearing, and S. Levine, “Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning,” 2018 IEEE International Conference on Robotics and Automation (ICRA), May 2018, doi: 10.1109/icra.2018.8463189.

F. Kurniawan, S. Sulaiman, S. Konate, and M. A. A. Abdalla, “Deep learning approaches for MIMO time-series analysis,” International Journal of Advances in Intelligent Informatics, vol. 9, no. 2, p. 286, Jul. 2023, doi: 10.26555/ijain.v9i2.1092.

A. H. Fath, F. Madanifar, and M. Abbasi, “Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks to predict solution gas-oil ratio of crude oil systems,” Petroleum, vol. 6, no. 1, pp. 80–91, Mar. 2020, doi: 10.1016/j.petlm.2018.12.002.

Y. Mao, A. Pranolo, A. P. Wibawa, A. B. P. Utama, and F. A. Dwiyanto, “Robust LSTM with Tuned-PSO and Bifold-Attention mechanism for analyzing multivariate Time-Series,” IEEE Access, vol. 10, pp. 78423–78434, Jan. 2022, doi: 10.1109/access.2022.3193643.

B. Jiang, D. Liu, H. R. Karimi, and B. Li, “RBF Neural Network Sliding Mode Control for Passification of Nonlinear Time-Varying Delay Systems with Application to Offshore Cranes,” Sensors, vol. 22, no. 14, p. 5253, Jul. 2022, doi: 10.3390/s22145253.

L. Wu, G. Perin, and S. Picek, “I choose you: Automated hyperparameter tuning for deep learning-based side-channel analysis,” IEEE Transactions on Emerging Topics in Computing, pp. 1–12, Jan. 2022, doi: 10.1109/tetc.2022.3218372.

Z. Wu, A. Tran, D. Rincón, and P. D. Christofides, “Machine learning‐based predictive control of nonlinear processes. Part I: Theory,” AIChE Journal, vol. 65, no. 11, Aug. 2019, doi: 10.1002/aic.16729.

J. Arroyo, C. Manna, F. Spiessens, and L. Helsen, “Reinforced model predictive control (RL-MPC) for building energy management,” Applied Energy, vol. 309, p. 118346, Mar. 2022, doi: 10.1016/j.apenergy.2021.118346.

S. Sabzevari, R. Heydari, M. Mohiti, M. Savaghebi, and J. Rodríguez, “Model-Free neural Network-Based predictive control for robust operation of power converters,” Energies, vol. 14, no. 8, p. 2325, Apr. 2021, doi: 10.3390/en14082325.

Downloads

Published

27.12.2023

How to Cite

Wijaya, S. ., Zarlis, M. ., Gaol, F. L. ., & Wibowo, A. . (2023). Deep Learning Based-Model Observer For Prediction Of Nonlinear With Time-Delay System. International Journal of Intelligent Systems and Applications in Engineering, 12(9s), 142–149. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4214

Issue

Vol. 12 No. 9s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.