استفاده از مدل وینر-همرشتاین بهینه شده با الگوریتم ژنتیک در شناسایی سیستم فتوولتائیک
ایمان سهرابی مقدم چافجیری
1
(
دانشکده فنی و مهندسی، واحد رشت، دانشگاه آزاد اسلامی، رشت، ایران
)
علیرضا آزادبر
2
(
دانشکده مهندسی هسته ای، واحد لاهیجان، دانشگاه آزاد اسلامی، لاهیجان، ایران
)
عباس قدیمی
3
(
دانشکده فنی و مهندسی، دانشگاه آزاد اسلامی واحد لاهیجان ، لاهیجان ، ایران
)
سید جواد موسوی
4
(
دانشکده فیزیک، واحد رشت، دانشگاه آزاد اسلامی، رشت، ایران
)
کلید واژه: شناسایی سیستم, مدل وینر-همرشتاین, سیستم فتوولتائیک, الگوریتم ژنتیک.,
چکیده مقاله :
شناسایی سیستم روشی برای شناسایی یا اندازه‌گیری مدل ریاضی یک سیستم با اندازه‌گیری ورودی‌ها و خروجی‌های سیستم است. در این مقاله رویکرد الگوریتم ژنتیک (GA) را برای مدل‌سازی سیستم‌های فتوولتائیک (PV) با ساختار وینر-هامرشتاین اعمال می‌کنیم. سیستم‌های دینامیکی غیرخطی دارای هر دو عنصر پویا (عناصر ذخیره انرژی) هستند و در این نوع سیستم‌ها بین برخی از متغیرها روابط غیرخطی وجود دارد. اگر در چنین سیستم هایی بتوان فرض کرد که قطعات دینامیکی و قطعات غیرخطی قابل تفکیک هستند، می توان آنها را با ساختارهای مدل های بلوک گرا مدل کرد. این نوع مدل ها از ترکیب بلوک(های) دینامیکی خطی و بلوک(های) غیرخطی استاتیکی تشکیل شده اند. این رویکرد به تخمین یک سیستم فتوولتائیک (PV) بر اساس داده‌های مشاهده‌شده مربوط می‌شود. ورودی و خروجی غیرخطی به ترتیب از داده های تابش و جریان خروجی DC سیستم واقعی گرفته شده است. نتایج شبیه‌سازی اثربخشی و استحکام مدل پیشنهادی را با استفاده از الگوریتم ژنتیک نشان داد. نتایج شبیه سازی مقدار MSE 0.000774 را برای عملکرد عادی سیستم PV و 0.009863 را برای اثر سایه بین نرخ اطلاعات تخمینی و مرجع نشان می دهد.
چکیده انگلیسی :
System identification is a method of identification or measuring a mathematical model of a system by measuring the inputs and outputs of the system. In this paper we apply the Genetic Algorithm (GA) approach to model a photovoltaic (PV) systems with a Wiener-Hammerstein structure. Non-linear dynamic systems have both dynamic elements (energy storage elements) and in these types of systems there are non-linear relationships between some variables. If in such systems it can be assumed that dynamic parts and non-linear parts are separable, they can be modeled with the structures of block-oriented models. These types of models are composed of a combination of linear dynamic block(s) and static nonlinear block(s). This approach is concerned with the estimation of a photovoltaic (PV) system based on observed data. The nonlinear input and output are taken from the irradiance and DC output current data of the real system, respectively. The simulation results revealed the effectiveness and robustness of the proposed model using a genetic algorithm. The simulation results show an MSE value of 0.000774 for normal operation of the PV system and 0.009863 for the shading effect between the estimated and reference information rates.
شناسایی سیستم فتوولتائیک در شرایط عملیاتی نرمال و سایه
استفاده از مدل بلوکگرا
استفاده از مدل وینر- همرشتاین بهینه شده با الگوریتم ژنتیک
[1] L. Jin, Z. Liu and L. Li, “Prediction and identification of nonlinear dynamical systems using machine learning approaches,” J. Ind. Inf. Integr, vol. 35, p. 100503, 2023, doi: 10.1016/j.jii.2023.100503 .
[2] A. Cheng and Y. M. Low, “Improved generalization of NARX neural networks for enhanced metamodeling of nonlinear dynamic systems under stochastic excitations,” Mech. Syst. Signal Process, vol. 200, p. 110543, 2023, doi: 10.1016/j.ymssp.2023.110543.
[3] H.V.A. Truong; M. H. Nguyen, D.T. Tran and K.K. Ahn, “A novel adaptive neural network-based time-delayed estimation control for nonlinear systems subject to disturbances and unknown dynamics,” ISA Trans, vol. 142, pp. 214-227, 2023, doi: 10.1016/j.isatra.2023.07.032.
[4] Z. Sheikhlar, M. Hedayati; A. D. Tafti and H. F. Farahani, “Fuzzy Elman Wavelet Network: Applications to function approximation, system identification, and power system control,” Inf. Sci, vol. 583, pp. 306-331, 2022, doi: 10.1016/j.ins.2021.11.009.
[5] M.H. Hamedani, M. Zekri, F. Sheikholeslam, M. Selvaggio, F. Ficuciello and B. Siciliano, “Recurrent fuzzy wavelet neural network variable impedance control of robotic manipulators with fuzzy gain dynamic surface in an unknown varied environment,” Fuzzy Sets Syst., vol. 416, pp. 1-26, 2021, doi: 10.1016/j.fss.2020.05.001.
[6] R. Kumar, "Memory Recurrent Elman Neural Network-Based Identification of Time-Delayed Nonlinear Dynamical System," in IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 53, no. 2, pp. 753-762, Feb. 2023, doi: 10.1109/TSMC.2022.3186610.
[7] S. Luo, F.L Lewis, Y. Song and R. Garrappa, “Dynamical analysis and accelerated optimal stabilization of the fractional-order self-sustained electromechanical seismograph system with fuzzy wavelet neural network,” Nonlinear Dyn. vol. 104,no. 2, pp. 1389–1404, 2021, doi: 10.1007/s11071-021-06330-5.
[8] J. Fei and L. Liu, "Real-Time Nonlinear Model Predictive Control of Active Power Filter Using Self-Feedback Recurrent Fuzzy Neural Network Estimator," in IEEE Transactions on Industrial Electronics, vol. 69, no. 8, pp. 8366-8376, Aug. 2022, doi: 10.1109/TIE.2021.3106007.
[9] W.L. Xiong, X.Q. Yang, L. Ke and B.G. Xu, “EM algorithm-based identification of a class of nonlinear Wiener systems with missing output data,” Nonlinear Dyn. vol. 80, no. 1, pp. 329–339, 2015.
[10] M. Kazemi and M.M. Arefi, “A fast iterative recursive least squares algorithm for Wiener model identification of highly nonlinear systems” ISA Trans. vol. 67, pp. 382–388, 2017, doi: 10.1016/j.isatra.2016.12.002.
[11] P.S. Pal, R. Kar, D. Mandal and S.P. Ghoshal, “Parametric identification with performance assessment of Wiener systems using brain storm optimization algorithm,” Circuits Syst. Signal Process. Vol. 36, no. 8, pp. 3143–3181, 2017, doi: 10.1007/s00034-016-0464-7.
[12] J.H. Li and X. Li, “Particle swarm optimization iterative identification algorithm and gradient iterative identification algorithm for Wiener systems with colored noise,” Complexity , vol. 2018, Article Number : 7353171,pp. 1-8, 2018, doi: 10.1155/2018/7353171.
[13] G. Bottegal, R. Castro-Garcia and J.A.K. Suykens, “A two-experiment approach to Wiener system identification,” Automatica, vol. 93, pp. 282–289, 2018, doi: 10.1016/j.automatica.2018.03.069.
[14] J. Li, T. Zong, J. Gu and L. Hua, “Parameter Estimation of Wiener Systems Based on the Particle Swarm Iteration and Gradient Search Principle,” Circuits, Systems, and Signal Processing, vol. 39, no. 10, 2020, doi: 10.1007/s00034-019-01329-1.
[15] G. Mzyk and P. Wachel, “Wiener system identification by input injection method,” Int. J. Adapt. Control Signal Process., vol. 34, pp. 1105–1119, 2020.
[16] S. Mete, H. Zorlu and Ş. Özer, “An improved wiener model for system identification,” NÖHÜ Müh. Bilim. Derg. / NOHU J. Eng. Sci., vol. 9, no. 2, pp. 796-810, 2020, doi: 10.28948/ngumuh.553279.
[17] S. Gupta, A. Kumar Sahoo and U. Kumar Sahoo, “Volterra and Wiener Model Based Temporally and Spatio-Temporally Coupled Nonlinear System Identification: A Synthesized Review,” IETE Technical Review, vol. 38, no. 3, pp. 303-327, 2020, doi: 10.1080/02564602.2020.1732233.
[18] R. Castro-Garcia, K. Tiels, J. Schoukens and J. A. K. Suykens, "Incorporating Best Linear Approximation within LS-SVM-based Hammerstein System Identification," in IEEE Conference on Decision and Control (CDC), Osaka, Japan, 2015, pp. 7392-7397, doi: 10.1109/CDC.2015.7403387.
[19] H. Ase and T. Katayama, “A subspace-based identification of Wiener-Hammerstein benchmark model,” Control Engineering Practice, vol. 44, pp. 126–137, 2015, doi: 10.1016/j.conengprac.2015.07.011 .
[20] B. Aissaoui, M. Soltani and A. Chaari, “Subspace Identification of Hammerstein Model with Unified Discontinuous Nonlinearity,” Mathematical Problems in Engineering, vol. 2016, Article Number: 1794921, pp. 1-10, 2016, doi: 10.1155/2016/1794921.
[21] R. Castro-Garcia, K. Tiels, O. Mauricio Agudelo and J. A. K. Suykens, “Hammerstein system identification through best linear approximation inversion and regularisation,” International Journal of Control, vol. 91, no. 8, pp. 1757-1773, 2018, doi: 10.1080/00207179.2017.1329550.
[22] R. Castro-Garcia, O. Mauricio Agudelo and J. A.K. Suykens, “Impulse response constrained LS-SVM modeling for Hammerstein system identification,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 14046-14051, doi: 10.1016/j.ifacol.2017.08.2435.
[23] I. A. Aljamaan, M. M. Al-Dhaifallah and D. T. Westwick, “Hammerstein Box-Jenkins System Identification of the Cascaded Tanks Benchmark System,” Mathematical Problems in Engineering, vol. 2021, Article Number: 6613425, 2021, doi: 10.1155/2021/6613425.
[24] R. Castro-Garcia, O. Mauricio Agudelo and J. A.K. Suykens, “Impulse response constrained LS-SVM modelling for MIMO Hammerstein system identification,” International Journal of Control, vol. 92, no. 4, pp. 908-925, 2017, doi: 10.1080/00207179.2017.1373862.
[25] V. Prasad, K. Kothari and U. Mehta, “Parametric Identification of Nonlinear Fractional Hammerstein Models,” fractal and fractional, vol. 4, no. 1, pp. 1-12, 2020, doi: 10.3390/fractalfract4010002.
[26] A. Mehmood, A. Zameer, N.I. Chaudhary and M.A.Z. Raja, “Backtracking search heuristics for identification of electrical muscle stimulation models using Hammerstein structure,” Appl. Soft Comput. vol. 84, p. 105705, 2019, doi: 10.1016/j.asoc.2019.105705.
[27] F. Yu, Z. Mao and D. He, "Identification of Time-Varying Hammerstein-Wiener Systems," in IEEE Access, vol. 8, pp. 136906-136916, 2020, doi: 10.1109/ACCESS.2020.3011608.
[28] R. Moriyasu, T. Ikeda, S. Kawaguchi and K. Kashima, "Structured Hammerstein-Wiener Model Learning for Model Predictive Control," in IEEE Control Systems Letters, vol. 6, pp. 397-402, 2022, doi: 10.1109/LCSYS.2021.3077201.
[29] B. D. S. Pês, E. Oroski, J. G. Guimarães and M. J. C. Bonfim, "A Hammerstein–Wiener Model for Single-Electron Transistors," in IEEE Transactions on Electron Devices, vol. 66, no. 2, pp. 1092-1099, Feb. 2019, doi: 10.1109/TED.2018.2885060.
[30] T. Bogodorova and L. Vanfretti, "Model Structure Choice for a Static VAR Compensator Under Modeling Uncertainty and Incomplete Information," in IEEE Access, vol. 5, pp. 22657-22666, 2017, doi: 10.1109/ACCESS.2017.2758845.
[31] A. Brouri, “Wiener–Hammerstein nonlinear system identification using spectral analysis,” International Journal of Robust and Nonlinear Control, 2022, doi: 10.1002/rnc.6135.
[32] P. Dreesen and M. Ishteva, “Parameter Estimation of Parallel Wiener-Hammerstein Systems by Decoupling their Volterra Representations,” IFAC-PapersOnLine,vol. 54, no. 7, pp. 457-462, 2021, doi: 10.1016/j.ifacol.2021.08.402.
[33] J. Zambrano, J. Sanchis, J. M. Herrero and M. Martínez, "WH-MOEA: A Multi-Objective Evolutionary Algorithm for Wiener-Hammerstein System Identification. A Novel Approach for Trade-Off Analysis Between Complexity and Accuracy," in IEEE Access, vol. 8, pp. 228655-228674, 2020, doi: 10.1109/ACCESS.2020.3046352.
[34] M. A. H. Shaikh and K. Barbé, "Study of Random Forest to Identify Wiener–Hammerstein System," in IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-12, 2021, Article Number: 6500712, doi: 10.1109/TIM.2020.3018840.
[35] M. A. H. Shaikh and K. Barbé, "Wiener–Hammerstein System Identification: A Fast Approach Through Spearman Correlation," in IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 5, pp. 1628-1636, May 2019, doi: 10.1109/TIM.2019.2896366.
[36] M. A. H. Shaikh and K. Barbé, "Spearman correlation for initial estimation of Wiener-Hammerstein system,"in IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Houston, TX, USA, 2018, pp. 1-6, doi: 10.1109/I2MTC.2018.8409602.
[37] J. Zambrano, J. Sanchis, J. M. Herrero and M. Martínez, “WH-EA: An Evolutionary Algorithm for Wiener-Hammerstein System Identification,” vol. 2018, Article Number: 1753262, 2018, doi: 10.1155/2018/1753262.
[38] L. Li and X. Ren, “Identification of nonlinear Wiener-Hammerstein systems by a novel adaptive algorithm based on cost function framework,” ISA Transactions, vol. 80, pp. 146-159, 2018, doi: 10.1016/j.isatra.2018.07.015.
[39] G. Giordano, Sébastien. Gros and J. Sjöberg, “An improved method for Wiener–Hammerstein system identification based on the Fractional Approach,” Automatica, vol. 94, pp. 349-360, 2018, doi: 10.1016/j.automatica.2018.04.046.
[40] G. Mzyk and P. Wachel, “Kernel-based identification of Wiener–Hammerstein system,” Automatica, vol. 83, pp. 275-281, 2017, doi: 10.1016/j.automatica.2017.06.038.
[41] G. Giordano and J. Sjoberg, “A Time-Domain Fractional Approach for Wiener-Hammerstein Systems Identification,” IFAC-PapersOnLine, vol. 48, pp. 1232-1237, doi: 10.1016/j.ifacol.2015.12.300.
[42] E. Zhang, M. Schoukens and J. Schoukens, "Structure Detection of Wiener–Hammerstein Systems With Process Noise," in IEEE Transactions on Instrumentation and Measurement, vol. 66, no. 3, pp. 569-576, March 2017, doi: 10.1109/TIM.2016.2647418.
[43] M. Schoukens and K. Tiels, “Identification of block-oriented nonlinear systems starting from linear approximations: A survey,” Automatica, vol. 85, pp. 272-292, 2017, doi: 10.1016/j.automatica.2017.06.044 .
[44] M. N. Mohd Hussain, A. Maliki Omar and P. Saidin, “Samat and Zakaria Hussain, “Identification of Hammerstein-Weiner System for Normal and Shading Operation of Photovoltaic System,” International Journal of Machine Learning and Computing, vol. 2, no. 3, June 2012, doi: 10.7763/IJMLC.2012.V2.122.