Makine öğrenimi kullanarak ÇBAG'a dayalı rüzgâr türbininin FRT yeteneğinin iyileştirilmesi

Yıl 2022, Cilt: 11 Sayı: 4, 911 - 918, 14.10.2022

Altan Gencer

https://doi.org/10.28948/ngumuh.1165004

Cited By: 1

Öz

Çift beslemeli asenkron generatörü (ÇBAG), şebeke arızası sırasında meydana gelen yüksek gerilimin ve akımın zararlı etkilerine karşı çok hassastır. Makine öğrenmesi (ML) yöntemlerinden biri olan destek vektör makineye (DVM) dayalı bir kapasitif köprü tipi arıza akım sınırlayıcısı (KKTAAS), üç fazlı arızada geçiş (FRT) performansını iyileştirmek için önerilmiştir. Bu çalışmada, normal şebeke koşullarında çalışan ÇBAG tabanlı bir rüzgâr türbininde oluşabilecek faz-toprak (3LG) simetrik şebeke hatası DVM' ye dayalı makine öğrenimi algoritması hem ÇBAG dönüştürücülerin kontrol sistemlerinde hem de KKTAAS' in bir kontrol sisteminde uygulanmıştır. Rotor tarafında, şebeke tarafında dönüştürücüde ve KKTAAS' in devre topolojisinde kullanılan elektronik anahtarlama elemanlarının anahtarlama sinyallerini üretmek için dört farklı DVM sınıflandırıcı algoritması uygulanmıştır. DVM sınıflandırıcılarının eğitiminde İnce Gauss, Kuadratik, Kübik ve Doğrusal kernel fonksiyonları tercih edilmiştir. Geliştirilen DVM’ ler, normal ve şebeke arızası koşulları sırasında dönüştürücülerin davranışlarını doğru tahmin etmek ve karar vermek için uygun şekilde eğitilmiştir. İnce gauss ve Doğrusal DVM türlerinin performansı, ÇBAG’ ye dayalı bir rüzgâr türbini için eğitim verimliliğinin etkinliği ile karşılaştırılmıştır. DVM' in İnce Gaussian' in doğruluk oranı %100’dür, Doğrusal DVM' in doğruluk oranı ise %22'dir. Simülasyon sonuçları, İnce Gaussian DVM' in, ÇBAG tabanlı bir rüzgâr türbini için Doğrusal DVM' ye kıyasla 3LG şebeke hatasının zararlı etkilerinden daha verimli bir şekilde koruduğunu göstermektedir.

Anahtar Kelimeler

Çift Beslemeli Asenkron Generatör (ÇBAG), Machine Learning (ML), Kapasitif Köprü Tipi Arıza Akım Sınırlayıcı (KKTAAS), Rüzgâr Türbini (RT)

FRT capability enhancement of wind turbine based on DFIG using machine learning

Öz

The doubly fed induction generator (DFIG) is very sensitive to the high voltage and current harmful effects that occur during the grid fault. A capacitive bridge type fault current limiter (CBFCL) based on the support vector machine (SVM), which is one of the machine learning (ML) methods, is presented to improve the fault ride-through (FRT) performance of in three phase-to-ground (3LG) symmetric grid fault that may occur in a wind turbine based on DFIG working under normal operating conditions in this study. The machine learning algorithm based on SVM has been implemented in both the control systems of DFIG converters and a control system of CBFCL. Four different SVM classifier algorithms are applied to generate the switching signals of electronic switching elements used in rotor side, grid side converter, and circuit topology of CBFCL. Fine Gaussian, Quadratic, Cubic and Linear kernel functions are preferred in the training of SVM classifiers. The developed SVMs have been suitably trained to true predict and decide behaviours of converters during normal and grid fault conditions. The performance of Fine Gaussian and Linear types of SVM is compared to the effectiveness of training efficiency for a wind turbine based on DFIG. The accuracy rate of the Fine Gaussian of SVM is 100 %, while the accuracy rate of Linear SVM is 22 %. The simulation results show that the Fine Gaussian SVM protects more efficiently from the harmful effects of 3LG grid fault compared to the Linear SVM for a wind turbine based on DFIG.

Anahtar Kelimeler

Doubly Fed Induction Generator (DFIG), Machine Learning (ML), Capacitive Bridge Type Fault Current Limiter (CBFCL), Wind Turbine (WT)

Kaynakça

• M. Samiei Sarkhanloo, H. Bevrani and R. Mirzaei, A comprehensive coordinated frequency control scheme for double- fed induction generator wind turbine, battery, and diesel generators in islanded microgrids, Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 23, 1556-7036, 2021 https://doi.org/10.1080/15567036.2020.1868623.
• A. Gencer, Analysis of fault ride through capability improvement of the permanent magnet synchronous generator based on WT using a BFCL, 2019 1st Global Power, Energy and Communication Conference (GPECOM), pp. 353-357, Nevsehir, Türkiye, 2019. https://doi.org/10.1109/GPECOM.2019.8778624.
• A. Rini Ann Jerin, P. Kaliannan, and U. Subramaniam, Improved fault ride through capability of DFIG based wind turbines using synchronous reference frame control based dynamic voltage restorer, ISA Transactions, 70, 465–474, 2017. https://doi.org/ doi: 10.1016/j.isatra.2017.06.029.
• K. Kim, Y. Jeung, D. Lee and H. Kim, LVRT scheme of PMSG wind power systems based on feedback linearization, in IEEE Transactions on Power Electronics, 27(5), 2376-2384, 2012. https://doi.org/ 10.1109/TPEL.2011.2171999.
• M. R. Islam, J. Hasan, M. R. R. Shipon, M. A. H. Sadi, A. Abuhussein and T. K. Roy, Neuro fuzzy logic controlled parallel resonance type fault current limiter to improve the fault ride through capability of DFIG based wind farm, in IEEE Access, 8, 115314-115334, 2020. https://doi.org/10.1109/ACCESS.2020.3000462.
• A. M. A. Haidar, K. M. Muttaqi and M. T. Hagh, A coordinated control approach for DC link and rotor crowbars to improve fault ride-through of DFIG-based wind turbine, in IEEE Transactions on Industry Applications, 53(4), 4073-4086, 2017. https://doi.org1 0.1109/TIA.2017.2686341.
• S. Yang, T. Zhou, D. Sun, Z. Xie, and X. Zhang, A SCR crowbar commutated with power converter for DFIG-based wind turbines, International Journal of Electrical Power & Energy Systems, 81, 87–103, 2016. https:// doi.org/10.1016/j.ijepes.2016.01.039.
• A. Gencer, Analysis and control of fault ride through capability improvement PMSG based on WECS using active crowbar system during different fault conditions. Elektronika ir Elektrotechnika, 24, 64–69, 2018. https:/ /doi.org/10.5755/j01.eie.24.2.20637.
• J. Qi, W. Zhao and X. Bian, Comparative study of SVC and STATCOM reactive power compensation for prosumer microgrids with DFIG-based wind farm integration, in IEEE Access, 8, 209878-209885, 2020, https://doi.org/10.1109/ACCESS.2020.3033058.
• H. Geng, L. Liu and R. Li, Synchronization and reactive current support of PMSG-based wind farm during severe grid fault, in IEEE Transactions on Sustainable Energy, 9(4), 1596-1604, 2018. https:// doi.org/10.1109/TSTE.2018.2799197.
• L. Wang and D. Truong, Stability enhancement of a power system with a PMSG-based and a DFIG-based offshore wind farm using a SVC with an adaptive-network-based fuzzy inference system, in IEEE Transactions on Industrial Electronics, 60, 7, 2799-2807, 2013. https://doi.org/10.1109/TIE.2012.2218557
• S. Yan, A. Zhang, H. Zhang, J. Wang and B. Cai, Transient stability enhancement of DC-connected DFIG and its converter system using fault protective device, in Journal of Modern Power Systems and Clean Energy, 5(6), 887-896, 2017. https://doi.org/10.1007/s 40565-017-0333-9.
• F. Jiang, C. Tu, Q. Guo, Z. Shuai, X. He and J. He, Dual-functional dynamic voltage restorer to limit fault current, in IEEE Transactions on Industrial Electronics, 66(7), 5300-5309, 2019. https://doi.org/10.1109/TIE.2 018.28682.
• A. O. Ibrahim, T. H. Nguyen, D. Lee and S. Kim, A fault ride-through technique of DFIG wind turbine systems using dynamic voltage restorers, in IEEE Transactions on Energy Conversion, 26(3), 871-882, 2011. https://doi.org/10.1109/TEC.2011.2158102.
• H. Tseng, W. Jiang and J. Lai, A modified bridge switch-type flux-coupling nonsuperconducting fault current limiter for suppression of fault transients, in IEEE Transactions on Power Delivery, 33(6), 624-2633, 2018. https://doi.org/10.1109/TPWRD.2018.282 0428.
• H. Nourmohamadi, M. Nazari-Heris, M. Sabahi and M. Abapour, A novel structure for bridge-type fault current limiter: capacitor-based nonsuperconducting FCL, in IEEE Transactions on Power Electronics, 33 (4), 3044-3051, 2018. https://doi.org/10.1109/TPEL.20 17.2710018.
• M. A. H. Sadi, A. AbuHussein and M. A. Shoeb, Transient performance improvement of power systems using fuzzy logic controlled capacitive-bridge type fault current limiter, in IEEE Transactions on Power Systems, 36(1), 323-335, 2021. https://doi.org/10.110 9/TPWRS.2020.3003294.
• M. Firouzi and G. B. Gharehpetian, LVRT performance enhancement of DFIG-based wind farms by capacitive bridge-type fault current limiter, in IEEE Transactions on Sustainable Energy, 9 (3), 1118-1125, 2018. https://doi.org/10.1109/TSTE.2017.2771321.
• N. Rezaei, M. N. Uddin, I. K. Amin, M. L. Othman, M. B. Marsadek and M. M. Hasan, A novel hybrid machine learning classifier-based digital differential protection scheme for intertie zone of large-scale centralized DFIG-based wind farms, in IEEE Transactions on Industry Applications, 56(4), 3453-3465, 2020. https://doi.org/10.1109/TIA.2020.299058 4.
• H. S. Jang, K. Y. Bae, H. Park and D. K. Sung, Solar Power prediction based on satellite images and support vector machine, in IEEE Transactions on Sustainable Energy, 7(3), 1255-1263, 2016. https://doi.org/10.1109 /TSTE.2016.2535466.
• S. Edun et al., Finding faults in PV systems: supervised and unsupervised dictionary learning with SSTDR, in IEEE Sensors Journal, 21 (4), 4855-4865, 2021. https://doi.org/10.1109/JSEN.2020.3029707.
• S. Asaly, L. -A. Gottlieb and Y. Reuveni, Using support vector machine (SVM) and ionospheric total electron content (TEC) data for solar flare predictions, in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 1469-1481, 2021. https://doi.org/10.1109/JSTARS.2020.3044470.
• T. Gunda et al., A Machine Learning evaluation of maintenance records for common failure modes in PV inverters, in IEEE Access, 8, 211610-211620, 2020. https://doi.org/10.1109/ACCESS.2020.3039182.
• T. Hai et al., Global solar radiation estimation and climatic variability analysis using extreme learning machine based predictive model, in IEEE Access, 8, 12026-12042, 2020. https://doi.org/10.1109/ACCESS. 2020.2965303.
• D. Upadhyay, J. Manero, M. Zaman and S. Sampalli, Gradient boosting feature selection with machine learning classifiers for intrusion detection on power grids, in IEEE Transactions on Network and Service Management, 18(1), 1104-1116, 2021. https://doi.org/ 10.1109/TNSM.2020.3032618.
• Z. Li, H. Liu, J. Zhao, T. Bi and Q. Yang, Fast power system event identification using enhanced LSTM network with renewable energy integration, in IEEE Transactions on Power Systems, 36 (5), 4492-4502, 2021. https://doi.org/10.1109/TPWRS.2021.3064250
• H. Yun, C. Zhang, C. Hou and Z. Liu, An adaptive approach for ice detection in wind turbine with inductive transfer learning, in IEEE Access, 7, 122205-122213, 2019. https://doi.org/10.1109/ACCESS.2019. 2926575.
• J. Hsu, Y. Wang, K. Lin, M. Chen and J. H. Hsu, Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning, in IEEE Access, 8, 23427-23439, 2020. https://doi.org/10.1109/ACCESS.2020.2968615.
• X. Zhang, P. Han, L. Xu, F. Zhang, Y. Wang and L. Gao, Research on bearing fault diagnosis of wind turbine gearbox based on 1DCNN-PSO-SVM, in IEEE Access, 8, 192248-192258, 2020. https://doi.org/10.11 09/ACCESS.2020.3032719.
• S. Tohidi, P. Tavner, R. McMahon, H. Oraee, MR. Zolghadri, S.Shao S, et al. Low voltage ride-through of DFIG and brushless DFIG: similarities and differences Electric Power System Research, 110, 64-72, 2014. https://doi.org/10.1016/j.epsr.2013.12.018.
• S. Bayhan, S. Demirbas and H. Abu-Rub, Fuzzy-PI-based sensorless frequency and voltage controller for doubly fed induction generator connected to a DC microgrid, in IET Renewable Power Generation, 10(8), 1069-1077, 2016. https://doi.org/10.1049/iet-rpg.2015. 0504.
• S. Demirbas, Self-tuning fuzzy-PI-based current control algorithm for doubly fed induction generator, in IET Renewable Power Generation, 11(13), 1714-1722, 2017. https://doi.org/10.1049/ietrpg.2016.0700.
• A. Gencer, Comparison of t-type converter and NPC for the wind turbine based on doubly-fed induction generator", Balkan Journal of Electrical and Computer Engineering, 9(2), 123-128, 2021, https://doi.org/10. 17694/bajece.826624.