On Selecting a Method of Constructing a Fuzzy Model for Prediction of the Battery State

Abstract

Battery-powered electric vehicles are being currently considered to replace conventional non-environmental vehicles. Batteries could not be used without a control system, which development requires a mathematical model to predict the state of a separate battery. The Takagi --- Sugeno fuzzy system (fuzzy model) could become such a model. There are methods for automatic construction of fuzzy models according to the table of observations. However, unambiguous criteriafor selecting the appropriate method in each specific case are missing. The problem is considered of determining a method making it possible to obtain a fuzzy model that predicts the lithiumion battery voltage from the load current and the state of charge when discharging with direct current with the lowest meansquare error. The existing methods and their classes were reviewed, and five methods were selected for comparison. Prediction error by all the models obtained was unevenly distributed along the axis of the charge state, and it took the highest values in the range of 97--100 %. The lowest meansquare error was registered in the model built by the combined method using subtractive clustering, least squares method and adaptive network based on the adaptive neurofuzzy inference system. The error in such model was changing stepwise, which was associated with feature of the subtractive clustering algorithm, i.e., the formed clusters were of the same size

Please cite this article in English as:

Yakovleva O.V., Stroganov Yu.V., Rudakov I.V. On selecting a method of constructing a fuzzy model for prediction of the battery state. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2022, no. 4 (141), pp. 36--55 (in Russ.). DOI: https://doi.org/10.18698/02363933202243655

References

[1] Prajwowski K., Golebiewski W., Lisowski M., et al. Road test of selected electrical parameters of the hybrid vehicle accumulation system. IEEE Trans. Veh. Technol., 2021, vol. 70, no. 1, pp. 203--211. DOI: https://doi.org/10.1109/TVT.2020.3043852

[2] Borisevich A.V. Modeling of lithium-ion batteries for battery management systems: the survey of current state. Sovremennaya tekhnika i tekhnologii [Modern Technics and Technologies], 2014, no. 5 (in Russ.). Available at: https://technology.snauka.ru/2014/05/3542

[3] Moura S.J., Chaturvedi N.A., Krstic M. Adaptive partial differential equation observer for battery state-of-charge/state-of-health estimation via an electrochemical model. J. Dyn. Sys., Meas., Control., 2014, vol. 136, no. 1, art. 011015. DOI: https://doi.org/10.1115/1.4024801

[4] Rahmoun A., Biechl H. Modelling of Li-ion batteries using equivalent circuit diagrams. Przeglad Elektrotechniczny, 2012, vol. 88, no. 7B, pp. 152--156.

[5] Soltani M., Telmoudi A.J., Belgacem Y.B., et al. Parameters identification and discharge capacity prediction of Nickel--Metal Hydride battery based on modified fuzzy c-regression models. Neural Comput. & Applic., 2020, vol. 32, no. 15, pp. 11361--11371. DOI: https://doi.org/10.1007/s00521-019-04631-w

[6] Guo Y., Yang Z., Liu K., et al. A compact and optimized neural network approach for battery state-of-charge estimation of energy storage system. Energy, 2021, vol. 219, no. 5, art. 119529. DOI: https://doi.org/10.1016/j.energy.2020.119529

[7] Fleischer C., Waag W., Bai Z., et al. On-line self-learning time forward voltage prognosis for lithium-ion batteries using adaptive neuro-fuzzy inference system. J. Power Sources, 2013, vol. 243, pp. 728--749. DOI: https://doi.org/10.1016/j.jpowsour.2013.05.114

[8] Khodashinskiy I.A. Identification of fuzzy systems: methods and algorithms. Problemy upravleniya [Control Sciences], 2009, no. 4, pp. 15--23 (in Russ.).

[9] Takagi T., Sugeno M. Fuzzy identification of systems and its application to modeling and control. IEEE Trans. Syst. Man Cybern., 1985, vol. 15, no. 1, pp. 116--132. DOI: https://doi.org/10.1109/TSMC.1985.6313399

[10] Mamdani E.H., Assilian S. An experiment in linguistic synthesis with a fuzzy logic controller. Int. J. Man. Mach. Stud., 1975, vol. 7, no. 1, pp. 1--13. DOI: https://doi.org/10.1016/S0020-7373(75)80002-2

[11] Hathaway R.J., Bezdek J.C. Switching regression models and fuzzy clustering. IEEE Trans. Fuzzy Syst., 1993, vol. 1, no. 3, pp. 195--204. DOI: https://doi.org/10.1109/91.236552

[12] Gustafson D.E., Kessel W.C. Fuzzy clustering with a fuzzy covariance matrix. Proc. IEEE CDC, 1979, pp. 761--766. DOI: https://doi.org/10.1109/CDC.1978.268028

[13] Gath I., Geva A.B. Unsupervised optimal fuzzy clustering. IEEE Trans. Pattern Anal. Mach. Intell., 1989, vol. 11, no. 7, pp. 773--781. DOI: https://doi.org/10.1109/34.192473

[14] Abonyi J., Babuska R., Szeifert F. Modified Gath --- Geva fuzzy clustering for identification of Takagi --- Sugeno fuzzy models. IEEE Trans. Syst. Man Cybern., 2002, vol. 32, no. 5, pp. 612--621. DOI: https://doi.org/10.1109/TSMCB.2002.1033180

[15] Yager R.R., Filev D.P. Approximate clustering via the mountain method. IEEE Trans. Pattern Anal. Mach. Intell., 1994, vol. 24, no. 8, pp. 1279--1284. DOI: https://doi.org/10.1109/21.299710

[16] Chiu S.L. Extracting fuzzy rules for pattern classification by cluster estimation. Proc. IFSA, 1995, vol. 95, pp. 273--276.

[17] Kennedy J., Ebenhart R. Particle swarm optimization. Proc. IEEE ICNN, 1995, pp. 1942--1948. DOI: https://doi.org/10.1109/ICNN.1995.488968

[18] Khosla A., Kumar S., Aggarwal K.K. A framework for identification of fuzzy models through particle swarm optimization algorithm. IEEE Indicon, 2005, pp. 388--391. DOI: https://doi.org/10.1109/INDCON.2005.1590196

[19] Holland J.H. Adaptation in natural and artificial systems. Cambridge, MIT Press, 1975.

[20] Civelek Z. Optimization of fuzzy logic (Takagi --- Sugeno) blade pitch angle controller in wind turbines by genetic algorithm. Eng. Sc. Technol. an Int. J., 2020, vol. 23, no. 1, pp. 1--9. DOI: https://doi.org/10.1016/j.jestch.2019.04.010

[21] Khodashinskiy I.A., Gnezdilova V.Yu., Dudin P.A., et al. [Derivative-based and metaheuristic methods for identifying parameters of fuzzy models]. Tr. VIII Mezhdunar. konf. SICPRO’08 [Proc. VIII Int. Conf. SICPRO’08]. Moscow, IPU RAN Publ., 2009, pp. 501--528 (in Russ.).

[22] Guillaume S. Designing fuzzy inference systems from data: an interpret ability-oriented review. IEEE Trans. Fuzzy Syst., 2001, vol. 9, no. 3, pp. 426--443. DOI: https://doi.org/10.1109/91.928739

[23] Shun-Hung T., Yu-Wen Ch. A novel identification method for Takagi --- Sugeno fuzzy model. Fuzzy Sets Syst., 2018, vol. 338, pp. 117--135. DOI: https://doi.org/10.1016/j.fss.2017.10.012

[24] Kalman R.E. A new approach to linear filtering and prediction problems. J. Basic Eng., 1960, vol. 82, no. 1, pp. 35--45. DOI: https://doi.org/10.1115/1.3662552

[25] Khodashinskiy I.A., Sarin K.S., Cherepanov S.A. Initialization method for fuzzy Takagi --- Sugeno systems. Optoelectron. Instrument. Proc., 2016, vol. 52, no. 3, pp. 266--273. DOI: https://doi.org/10.3103/S8756699016030080

[26] Junhong Y., Jizhen L., Xiangjie L., et al. Identification of nonlinear system based on ANFIS with subtractive clustering. 6th World Cong. on Intelligent Control and Automation, 2006, pp. 1852--1856. DOI: https://doi.org/10.1109/WCICA.2006.1712675

[27] Benmouiza K., Cheknane A. Clustered ANFIS network using fuzzy c-means, subtractive clustering, and grid partitioning for hourly solar radiation forecasting. Theor. Appl. Climatol., 2019, vol. 137, no. 1, pp. 31--43. DOI: https://doi.org/10.1007/s00704-018-2576-4

[28] Jang J.-S.R. ANFIS: adaptive network based fuzzy inference system. IEEE Trans. Syst. Man Cybern. Syst., 1993, vol. 23, no. 3, pp. 665--684. DOI: https://doi.org/10.1109/21.256541

[29] Kalman R.E., Falb P.L., Arbib M.A. Topics in mathematical system theory. New York, McGraw-Hill, 1969.

[30] Zadeh L.A., Desoer C.A. Linear system theory. The state space approach. New York, McGraw-Hill, 1963.