Logo PTI Logo FedCSIS

Communication Papers of the 18th Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 37

Use of Dynamic Neural Networks for Modeling Nonlinear Objects with Significant Nonlinearity

, , , ,

DOI: http://dx.doi.org/10.15439/2023F3874

Citation: Communication Papers of the 18th Conference on Computer Science and Intelligence Systems, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 37, pages 97–102 ()

Full text

Abstract. The work is devoted to the problem of nonlinear modeling of objects based on dynamic neural networks. The aim of the work is to improve the accuracy of modeling dynamic objects with significant nonlinearities using neural network models, and identify the scope of their effective application. This aim is achieved by applying the apparatus of time delay neural networks for building dynamic nonlinear models. The most significant results consist in obtaining the method of building the neural network models of objects with significant nonlinearities with preservation of nonlinear and dynamic properties of the research object. Significance of the obtained results: the application of the proposed method allows both high accuracy and efficiency of the construction nonlinear dynamic models, allows providing modelling of the objects that are in a functional mode. The proposed method verified using the data of the test dynamical objects with significant nonlinearities. The verification results demonstrates high accuracy and efficiency of the models building.

References

  1. A. Agresti, "Foundations of linear and generalized linear models", Wiley series in probability and statistics, 2017, 480 p.
  2. J. Schoukens and L. Ljung, "Nonlinear System Identification: A User-Oriented Road Map", in IEEE Control Systems Magazine, vol. 39, no. 6, pp. 28-99, Dec. 2019, http://dx.doi.org/10.1109/MCS.2019.2938121.
  3. C. Rudin and J. Radin, "Why are we using black box models in AI when we don’t need to? A lesson from an explainable AI competition", Harvard Data Science Review, vol. 2, no. 1, 2019, http://dx.doi.org/10.1162/99608f92.5a8a3a3d.
  4. C. Maszczyk, M. Kozielski and M. Sikora, "Rule-based approximation of black-box classifiers for tabular data to generate global and local explanations", 2022 17th Conference on Computer Science and Intelligence Systems (FedCSIS), Sofia, Bulgaria, 2022, pp. 89-92, http://dx.doi.org/10.15439/2022F258.
  5. Gomolka, Z., Dudek-Dyduch, E., Kondratenko, Y.P. "From homogeneous network to neural nets with fractional derivative mechanism", International Conference on Artificial Intelligence and Soft Computing, ICAISC-2017, Rutkowski, L. et al. (Eds), Part I, Zakopane, Poland, 11-15 June 2017, LNAI 10245, Springer, Cham, 2017, pp. 52-63, http://dx.doi.org/10.1007/978-3-319-59063-9_5.
  6. N. Todorovic and P. Klan, "State of the Art in Nonlinear Dynamical System Identification using Artificial Neural Networks", 2006 8th Seminar on Neural Network Applications in Electrical Engineering, Belgrade, Serbia, 2006, pp. 103-108, http://dx.doi.org/10.1109/NEUREL.2006.341187.
  7. Chi-Hsu Wang, Pin-Cheng Chen, Ping-Zong Lin and Tsu-Tian Lee, "A dynamic neural network model for nonlinear system identification", 2009 IEEE International Conference on Information Reuse & Integration, Las Vegas, NV, USA, 2009, pp. 440-441, http://dx.doi.org/10.1109/IRI.2009.5211647.
  8. W. Liu, W. Na, L. Zhu and Q. -J. Zhang, "A review of neural network based techniques for nonlinear microwave device modeling", 2016 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), Beijing, China, 2016, pp. 1-2, http://dx.doi.org/10.1109/NEMO.2016.7561677.
  9. W. Liu, Y. Su and L. Zhu, "Nonlinear Device Modeling Based on Dynamic Neural Networks: A Review of Methods", 2021 IEEE 4th International Conference on Electronic Information and Communication Technology (ICEICT), Xi'an, China, 2021, pp. 662-665, http://dx.doi.org/10.1109/ICEICT53123.2021.9531270.
  10. L. Zhu, Q. Zhang, K. Liu, Y. Ma, B. Peng and S. Yan, "A Novel Dynamic Neuro-Space Mapping Approach for Nonlinear Microwave Device Modeling", in IEEE Microwave and Wireless Components Letters, vol. 26, no. 2, pp. 131-133, Feb. 2016, http://dx.doi.org/10.1109/LMWC.2016.2516761.
  11. Wenyuan Liu, L. Zhu, Weicong Na and Q. -J. Zhang, "An overview of Neuro-space mapping techniques for microwave device modeling", 2016 IEEE MTT-S Latin America Microwave Conference (LAMC), Puerto Vallarta, Mexico, 2016, pp. 1-3, http://dx.doi.org/10.1109/LAMC.2016.7851276.
  12. M. Sugiyama, H. Sawai and A. H. Waibel, "Review of TDNN (time delay neural network) architectures for speech recognition", 1991 IEEE International Symposium on Circuits and Systems (ISCAS), Singapore, 1991, pp. 582-585 vol. 1, http://dx.doi.org/10.1109/ISCAS.1991.176402.
  13. L. Wenyuan, L. Zhu, F. Feng, W. Zhang, Q.-J. Zhang, L. Qian and G. Liu, "A time delay neural network based technique for nonlinear microwave device modelling, in: Micromachines", Basel, vol. 11, no. 9, 2020, p. 831, http://dx.doi.org/10.3390/mi11090831.
  14. W. Liu, Y. Su, H. Tan, F. Feng and B. Zhang, "A Review of Wiener-Type Dynamic Neural Network for Nonlinear Device Modeling", 2022 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP), Guangzhou, China, 2022, pp. 1-3, http://dx.doi.org/10.1109/IMWS-AMP54652.2022.10106887.
  15. W. Liu, W. Na, F. Feng, L. Zhu and Q. Lin, "A Wiener-Type Dynamic Neural Network Approach to the Modeling of Nonlinear Microwave Devices and Its Applications", 2020 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO), Hangzhou, China, 2020, pp. 1-3, http://dx.doi.org/10.1109/NEMO49486.2020.9343530.
  16. A. Balestrino and A. Caiti, "Approximation of Hammerstein/Wiener dynamic models", Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, Como, Italy, 2000, pp. 70-74 vol.1, http://dx.doi.org/10.1109/IJCNN.2000.857816.
  17. G. Stegmayer, M. Pirola, G. Orengo and O. Chiotti, "Towards a Volterra series representation from a neural network model", WSEAS Transactions on Circuits and Systems, archive 1, 2004, pp. 55–61.
  18. L. Wenyuan, L. Zhu, F. Feng, W. Zhang, Q.-J. Zhang, L. Qian and G. Liu, “A time delay neural network based technique for nonlinear microwave device modelling, in: Micromachines”, Basel, vol. 11, no. 9, 2020, p. 831, http://dx.doi.org/10.3390/mi11090831.
  19. F. Alleau, E. Poisson, C. V. Gaudin and P. Le Callet, "TDNN with masked inputs", Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint, Singapore, 2003, pp. 989-993 vol.2, http://dx.doi.org/10.1109/ICICS.2003.1292607.
  20. Fomin, O., Polozhaenko, S., Krykun, V., Orlov, A., Lys, D., "Interpretation of Dynamic Models Based on Neural Networks in the Form of Integral-Power Series", In: Arsenyeva, O., Romanova, T., Sukhonos, M., Tsegelnyk, Y. (eds) Smart Technologies in Urban Engineering. STUE 2022. Lecture Notes in Networks and Systems, vol 536. Springer, 2022, Cham, pp. 258-265, http://dx.doi.org/10.1007/978-3-031-20141-7_24.
  21. J. Sen, "Machine Learning – Algorithms, Models and Applications", London, United Kingdom, IntechOpen, 2021, 154 p., http://dx.doi.org/10.5772/intechopen.94615.
  22. Kondratenko, Y.; Atamanyuk, I.; Sidenko, I.; Kondratenko, G.; Sichevskyi, S. "Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing". Sensors 2022, 22(3), p. 1062, http://dx.doi.org/10.3390/s22031062.
  23. A. R. Rao and M. Reimherr, "Non-linear functional modelling using neural networks", 2021, https://arxiv.org/abs/2104.09371, http://dx.doi.org/10.48550/arXiv.2104.09371.
  24. Kondratenko, Y., Gerasin, O., Topalov, A., "A simulation model for robot's slip displacement sensors", International Journal of Computing, Vol.15, Issue 4, 2016, pp. 224-236, http://dx.doi.org/10.47839/ijc.15.4.854.
  25. W. Liu, W. Na, W. Zhang, L. Zhu and M. Wang, "A Review of Recent Neural Network Approaches to the Modeling of Nonlinear Microwave Devices," 2020 13th UK-Europe-China Workshop on Millimetre-Waves and Terahertz Technologies (UCMMT), Tianjin, China, 2020, pp. 1-3, http://dx.doi.org/10.1109/UCMMT49983.2020.9296017.
  26. L. Zhang and Q. -J. Zhang, "Simple and Effective Extrapolation Technique for Neural-Based Microwave Modeling," in IEEE Microwave and Wireless Components Letters, vol. 20, no. 6, pp. 301-303, June 2010, http://dx.doi.org/10.1109/LMWC.2010.2047450.
  27. A. C. Meruelo, D. M. Simpson, S. M. Veres and Ph. L. Newland, "Improved system identification using artificial neural networks and analysis of individual differences in responses of an identified neuron", Neural Networks, vol 75, 2016, pp. 56–65, http://dx.doi.org/10.1016/j.neunet.2015.12.002.
  28. C. A. Mitrea, C. K. M. Lee and Z. Wu, "A comparison between neural networks and traditional forecasting methods: case study", International journal of engineering business management, vol. 1, no. 2, 2009, pp. 19–24, http://dx.doi.org/10.5772/6777.
  29. Pavlenko, V.D. and Pavlenko, S.V., "Deterministic identification methods for nonlinear dynamical systems based on the Volterra Model", Applied Aspects of Information Technology, vol. 1, no. 2, 2018, pp. 11-32, http://dx.doi.org/10.15276/aait.01.2018.1.
  30. V. Z. Marmarelis and X. Zhao, "Volterra models and three-layer perceptrons", in IEEE Transactions on Neural Networks, vol. 8, no. 6, pp. 1421-1433, Nov. 1997, http://dx.doi.org/10.1109/72.641465.
  31. G. Govind and P. A. Ramamoorthy, "Multi-layered neural networks and Volterra series: The missing link", 1990 IEEE International Conference on Systems Engineering, Pittsburgh, PA, USA, 1990, pp. 633-636, http://dx.doi.org/10.1109/ICSYSE.1990.203237.