Published June 30, 2019 | Version v1
Journal article Open

Development of neural­network and fuzzy models of multimass electromechanical systems

Creators

  • 1. Ukrainian Engineering Pedagogics Academy
  • 2. DeVry University New York, USA, 10016 United States

Description

The study objective was to construct models of multimass electromechanical systems using neural nets, fuzzy inference systems and hybrid networks by means of MATLAB tools. A model of a system in a form of a neural net or a neuro-fuzzy inference system was constructed on the basis of known input signals and signals measured at the system output. Methods of the theory of artificial neural nets and methods of the fuzzy modeling technology were used in the study.

A neural net for solving the problem of identification of the electromechanical systems with complex kinematic connections was synthesized using the Neural Network Toolbox application package of the MATLAB system. A possibility of solving the identification problem using an approximating fuzzy system using the Fuzzy Logic Toolbox package was considered. A hybrid network was synthesized and implemented in a form of an adaptive neuro-fuzzy inference system using the ANFIS editor. Recommendations for choosing parameters that have the most significant effect on identification accuracy when applying the methods under consideration were given. It was shown that the use of neural nets and adaptive neuro-fuzzy inference systems makes it possible to identify systems with accuracy of 2 to 4%.

As a result of the conducted studies, efficiency of application of neural nets, fuzzy inference systems and hybrid nets to identification of systems with complex kinematic connections in the presence of "input-output" information was shown. The neural-network, fuzzy and neuro-fuzzy models of two-mass electromechanical systems were synthesized with the use of modern software tools.

The considered approach to using artificial intelligence technologies, that is neural nets and fuzzy logic is a promising line of construction of appropriate neural-network and neuro-fuzzy models of technical objects and systems. The study results can be used in synthesis of regulators for the systems with complex kinematic connections to ensure their high performance.

Files

Construction of the expert system of geo­spatial analysis that employs scenarios for the automated data generation for a digital map.pdf

Files (1.1 MB)

Additional details

References

  • Akimov, L. V., Kolotilo, V. I., Markov, V. S. (2000). Dinamika dvuhmassovyh sistem s netraditsionnymi regulyatorami skorosti i nablyudatelyami sostoyaniya. Kharkiv: HGPU, 93.
  • Kotlyarov, V. O., Osichev, A. V. (2010). O rezul'tatah resheniya zadach stabilizatsii sistem s otritsatel'nym vyazkim treniem posredstvom primeneniya nablyudayuschih ustroystv. Visnyk Natsionalnoho tekhnichnoho universytetu «Kharkivskyi politekhnichnyi instytut», 28, 242–248.
  • Kuznetsov, B. I., Nikitina, T. B., Kolomiets, V. V., Voloshko, O. V., Kobylianskyi, B. B. (2017). Bahatokryterialnyi syntez neliniynykh robastnykh elektromekhanichnykh system. Visnyk Natsionalnoho tekhnichnoho universytetu «Kharkivskyi politekhnichnyi instytut», 27 (1249), 58–61.
  • Pivniak, H. H., Beshta, O. S., Tulub, S. B.; Pivniak, H. H. (Ed.) (2004). Tsyfrova identyfikatsiya parametriv elektromekhanichnykh system v zadachakh enerho- i resursozberezhennia. Dnipropetrovsk: Natsionalnyi hirnychyi universytet, 197.
  • Balyuta, S., Kopilova, L., Klimenko, J. (2013). Identification of the parameters of electro-mechanical system model based on genetic algorithms. Naukovi pratsi NUKhT, 49, 88–97.
  • Saushev, A. V., Trojan, D. I. (2015). Identification of electric drives of port reloading cars. Vestnik Gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova, 5 (33), 169–183. doi: https://doi.org/10.21821/2309-5180-2015-7-5-169-183
  • Vodovozov, A. M., Еlyukov, A. S. (2009). Algorithms of parametrical identification of electromechanical systems protected against hindrance. Izvestiya vysshih uchebnyh zavedeniy, 52 (12), 40–43.
  • Luczak, D., Zawirski, K. (2015). Parametric identification of multi-mass mechanical systems in electrical drives using nonlinear least squares method. IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society. doi: https://doi.org/10.1109/iecon.2015.7392730
  • Nouri, K., Loussifi, H., Braiek, N. B. (2014). A comparative study on the identification of the dynamical model of multi-mass electrical drives using wavelet transforms. International Journal of Systems Science, 45 (11), 2223–2241. doi: https://doi.org/10.1080/00207721.2013.766772
  • Villwock, S., Pacas, M. (2008). Application of the Welch-Method for the Identification of Two- and Three-Mass-Systems. IEEE Transactions on Industrial Electronics, 55 (1), 457–466. doi: https://doi.org/10.1109/tie.2007.909753
  • Zoubek, H., Pacas, M. (2011). An identification method for multi-mass-systems in speed-sensorless operation. 2011 IEEE International Symposium on Industrial Electronics. doi: https://doi.org/10.1109/isie.2011.5984447
  • Zoubek, H., Pacas, M. (2010). A method for speed-sensorless identification of two-mass-systems. 2010 IEEE Energy Conversion Congress and Exposition. doi: https://doi.org/10.1109/ecce.2010.5618431
  • Luczak, D., Nowopolski, K. (2014). Identification of multi-mass mechanical systems in electrical drives. Proceedings of the 16th International Conference on Mechatronics - Mechatronika 2014. doi: https://doi.org/10.1109/mechatronika.2014.7018271
  • Saarakkala, S. E., Leppinen, T., Hinkkanen, M., Luomi, J. (2012). Parameter estimation of two-mass mechanical loads in electric drives. 2012 12th IEEE International Workshop on Advanced Motion Control (AMC). doi: https://doi.org/10.1109/amc.2012.6197104
  • Saarakkala, S. E., Hinkkanen, M. (2015). Identification of Two-Mass Mechanical Systems Using Torque Excitation: Design and Experimental Evaluation. IEEE Transactions on Industry Applications, 51 (5), 4180–4189. doi: https://doi.org/10.1109/tia.2015.2416128
  • Abou-Zayed, U., Ashry, M., Breikin, T. (2008). Experimental open-loop and closed-loop identification of a multi-mass electromechanical servo system. Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics Service, 188–196. doi: https://doi.org/10.5220/0001502601880193
  • Konev, V. V. (2016). Improved algorithms of teaching of neuronet system of authentication of the safe state of immobile objects of systems of critical application. Systemy obrobky informatsiyi, 3, 241–245.
  • Horbiichuk, M. I., Humeniuk, T. V. (2017). Neural network identification technology for manufacturing operations of drilling rig. Naukovyi visnyk NHU, 3, 107–113.
  • Lyashenko, S. A. (2007). Postroenie modeli nelineynogo dinamicheskogo obekta na osnove modifitsirovannoy radial'no-bazisnoy seti. Vestnik Hersonskogo natsional'nogo tekhnicheskogo universiteta, 4 (27), 33–35.
  • Kondratenko, Yu. P., Hordyenko, E. V. (2010). Neiromerezhevyi pidkhid do rishennia zadachi identyfikatsiyi nestatsionarnykh parametriv tekhnolohichnykh obiektiv. Visnyk NTU «KhPI». Tematychnyi vypusk: Informatyka i modeliuvannia, 21, 102–109.
  • Jurado, F., Flores, M. A., Santibanez, V., Llama, M. A., Castaneda, C. E. (2011). Continuous-Time Neural Identification for a 2 DOF Vertical Robot Manipulator. 2011 IEEE Electronics, Robotics and Automotive Mechanics Conference. doi: https://doi.org/10.1109/cerma.2011.20
  • Castañeda, C. E., Esquivel, P. (2012). Decentralized neural identifier and control for nonlinear systems based on extended Kalman filter. Neural Networks, 31, 81–87. doi: https://doi.org/10.1016/j.neunet.2012.03.005
  • Nidhil, K. J., Sreeraj, S., Vijay, B., Bagyaveereswaran, V. (2015). System identification using artificial neural network. 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]. doi: https://doi.org/10.1109/iccpct.2015.7159360
  • Zhang, J., Li, Y., Wu, X. (2015). Neural network identification and control for nonlinear dynamic systems with time delay. 2015 34th Chinese Control Conference (CCC). doi: https://doi.org/10.1109/chicc.2015.7260183
  • Ren, X. M., Rad, A. B. (2007). Identification of Nonlinear Systems With Unknown Time Delay Based on Time-Delay Neural Networks. IEEE Transactions on Neural Networks, 18 (5), 1536–1541. doi: https://doi.org/10.1109/tnn.2007.899702
  • Alanis, A. Y., Rios, J. D., Arana-Daniel, N., Lopez-Franco, C. (2016). Neural identifier for unknown discrete-time nonlinear delayed systems. Neural Computing and Applications, 27 (8), 2453–2464. doi: https://doi.org/10.1007/s00521-015-2016-7
  • Viattchenin, D. A., Starovoitov, V. V. (2010). Objects Identification Through Fuzzy Inference System. Shtuchnyi intelekt, 3, 312–321.
  • Udovenko, S. G., Dibe, G., Perepelitsa, V. I. (2008). Method of fuzzy identification of nonlinear objects of digital control. Zbirnyk naukovykh prats Kharkivskoho universytetu Povitrianykh Syl, 3 (18), 131–134.
  • Horbiychuk, M., Humeniuk, T., Povarchuk, D. (2015). Fuzzy Identification of Technological Objects. Energy Engineering and Control Systems, 1 (1), 35–42. doi: https://doi.org/10.23939/jeecs2015.01.035
  • Dovžan, D., Škrjanc, I. (2011). Recursive fuzzy c-means clustering for recursive fuzzy identification of time-varying processes. ISA Transactions, 50 (2), 159–169. doi: https://doi.org/10.1016/j.isatra.2011.01.004
  • Bertone, A. M. A., Martins, J. B., Yamanaka, K. (2018). Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model. TEMA (São Carlos), 18 (3), 405. doi: https://doi.org/10.5540/tema.2017.018.03.405
  • Kim, Y., Langari, R., Hurlebaus, S. (2011). MIMO fuzzy identification of building-MR damper systems. Journal of Intelligent and Fuzzy Systems, 22 (4), 185–205. doi: http://doi.org/10.3233/IFS-2011-0482
  • Bottura, C. P., de Oliveira Serra, G. L. (2004). An algorithm for fuzzy identification of nonlinear discrete-time systems. 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601). doi: https://doi.org/10.1109/cdc.2004.1429670
  • Wan, G., Wan, S., Chen, H., Wang, K., Lv, C. (2018). Fuzzy Identification of the Time- and Space-Dependent Internal Surface Heat Flux of Slab Continuous Casting Mold. Journal of Heat Transfer, 140 (12), 122301. doi: https://doi.org/10.1115/1.4040955
  • Zeng, F., Zhang, B., Zhang, L., Ji, J., Jin, W. (2016). Fuzzy Identification Based on T-S Fuzzy Model and Its Application for SCR System. Mechanical Engineering and Control Systems, 293–297. doi: https://doi.org/10.1142/9789814740616_0064
  • Sorokina, I. V., Tokareva, Е. V., Sorokin, R. V. (2015). Identifikatsiya nelineynyh obektov s ispol'zovaniem adaptivnyh nechetkih modeley. Tekhnologiya priborostroeniya, 2, 35–39.
  • Subbotin, S. A. (2011). The Identification of Neuro-Fuzzy Models for Technical Diagnosis Problem Solving. Shtuchnyi intelekt, 1 (33), 251–254.
  • Agamalov, O. N. (2003). Otsenka tekhnicheskogo sostoyaniya elektrooborudovaniya v real'nom masshtabe vremeni metodom neyro-nechetkoy identifikatsii. ExponentaPro: Matematika v prilozheniyah, 12, 36–44.
  • Liang, Y. C., Feng, D. P., Liu, G. R., Yang, X. W., Han, X. (2003). Neural identification of rock parameters using fuzzy adaptive learning parameters. Computers & Structures, 81 (24-25), 2373–2382. doi: https://doi.org/10.1016/s0045-7949(03)00303-1
  • Yu, W., Li, X. (2004). Fuzzy Identification Using Fuzzy Neural Networks With Stable Learning Algorithms. IEEE Transactions on Fuzzy Systems, 12 (3), 411–420. doi: https://doi.org/10.1109/tfuzz.2004.825067
  • Serra, G. L. O., Bottura, C. P. (2005). An IV-QR Algorithm for Neuro-Fuzzy Multivariable On-line Identification. 2005 IEEE International Conference on Systems, Man and Cybernetics. doi: https://doi.org/10.1109/icsmc.2005.1571589
  • D'yakonov, V. P., Kruglov, V. V. (2006). MATLAB 6.5 SR1/7/7 SR1/1 SR2 + Simulink 5/6: Instrumenty iskusstvennogo intellekta i bioinformatiki: seriya "Biblioteka professionala". Moscow: SOLON-PRЕSS, 456.