Three-Phase Four-Wire Grid-Connected Neutral Point Clamped Inverter with ANN Controllers

Yıl 2024, Cilt: 29 Sayı: 2, 507 - 520, 30.08.2024

Yunus Emre Yağan

https://doi.org/10.17482/uumfd.1387523

Öz

In this study, an artificial neural network (ANN) controller with a multilayer perceptron structure is designed and tested for the control of a three-phase, four-wire grid-connected neutral point clamped (NPC) inverter. The designed ANN controller is trained using the Levenberg Marquardt backpropagation training algorithm, with data obtained from a control loop created using proportional-integral (PI) controllers in the MATLAB/Simulink environment. The tasks of the ANN controller are to provide current control and capacitor voltage balancing control in the NPC inverter. The performance of the proposed ANN controller is tested using the grid-connected NPC inverter system modeled in the MATLAB/Simulink environment. The test results are presented in comparison with the results obtained using PI controllers in the same inverter system.

Anahtar Kelimeler

Artificial neural networks, Grid-connected inverter, Neutral point clamped inverter, Proportional-integral controller.

ÜÇ-FAZLI DÖRT-TELLİ ŞEBEKE BAĞLANTILI NÖTR NOKTASI KENETLİ BİR EVİRİCİ’NİN YSA İLE KONTROLÜ

Öz

Bu çalışmada üç fazlı dört telli şebeke bağlantılı nötr noktası kenetli (NNK) bir eviricinin kontrolü için çok katmanlı algılayıcı yapısında olan bir yapay sinir ağı (YSA) kontrolcüsü tasarlanmış ve test edilmiştir. Tasarlanan YSA kontrolcü, MATLAB/Simulink ortamında oransal-integral (PI) kontrolcüler kullanılarak oluşturulan bir kontrol döngüsünden elde edilen veriler ile, Levenberg Marquardt geri yayılım eğitim algoritmasıyla eğitilmiştir. YSA kontrolcünün görevleri, NNK eviricide akım kontrolünü ve kapasitör gerilimlerinin dengelenmesini sağlamaktır. Önerilen YSA kontrolcünün performansı MATLAB/Simulink ortamında modellenen şebeke bağlantılı NNK evirici sistemi kullanılarak test edilmiştir. Test sonuçları, aynı evirici sisteminde PI kontrolcüler kullanılarak elde edilen sonuçlar ile karşılaştırmalı olarak sunulmuştur.

Anahtar Kelimeler

Nötr noktası kenetli evirici, Oransal-integral kontrolcü, Şebeke bağlantılı evirici, Yapay sinir ağları.

Kaynakça

• Babaie, M., Sharifzadeh, M., ve Al-Haddad, K. (2020, August) Three-phase grid-connected NPC inverter based on a robust artificial neural network controller, IEEE Power & Energy Society General Meeting (PESGM), 1-5. doi:10.1109/PESGM41954.2020.9281531.
• Bana, P. R., ve Amin, M. (2022, October) Comparative assessment of supervised learning ANN controllers for grid-connected VSC system, 48th Annual Conference of the IEEE Industrial Electronics Society (IECON 2022), 1-6. doi:10.1109/IECON49645.2022.9969070.
• Bana, P. R., ve Amin, M. (2023, March) State-space modelling and stability analysis of ANN controller for grid-connected VSC system, IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies (GlobConHT), 1-6. doi:10.1109/GlobConHT56829.2023.10087412.
• Babaie, M., Sebaaly, F., Sharifzadeh, M., Kanaan, H. Y., ve Al-Haddad, K. (2019, February) Design of an artificial neural network control based on levenberg-marquart algorithm for gridconnected packed U-Cell inverter, IEEE International Conference on Industrial Technology (ICIT), 1202-1207. doi:10.1109/ICIT.2019.8755098.
• Li, S., Fairbank, M., Johnson, C., Wunsch, D. C., Alonso, E., ve Proao, J. L. (2014) Artificial neural networks for control of a grid-connected rectifier/inverter under disturbance, dynamic and power converter switching conditions, IEEE transactions on neural networks and learning systems, 25(4), 738-750. doi:10.1109/TNNLS.2013.2280906.
• Li, S., Sun, Y., Ramezani, M., ve Xiao, Y. (2019) Artificial neural networks for Volt/VAR control of DER inverters at the grid edge, IEEE Transactions on Smart Grid, 10(5), 5564- 5573. doi:10.1109/TSG.2018.2887080.
• Yağan, Y. E., ve Vardar, K. (2023) Artificial neural networks controllers for three-phase neutral point clamped inverters, Engineering Science and Technology, an International Journal, 41, 101390. doi:10.1016/j.jestch.2023.101390.
• Aslan, Y., ve Yağan, Y. E. (2016, June) ANN based fault location for medium voltage distribution lines with remote-end source, International Symposium on Fundamentals ofElectrical Engineering (ISFEE), 1-5. doi:10.1109/ISFEE.2016.7803203.
• Lim, S. K., Kim, J. H., ve Nam, K. (1999, July) A DC-link voltage balancing algorithm for 3-level converter using the zero sequence current, 30th Annual IEEE Power Electronics Specialists Conference. Record.(Cat. No. 99CH36321) 2, 1083-1088. doi:10.1109/PESC.1999.785646.
• Nabae, A., Takahashi, I., ve Akagi, H. (1981) A new neutral-point-clamped PWM inverter, IEEE Transactions on industry applications, (5), 518-523. doi: 10.1109/TIA.1981.4503992.
• Aslan, Y., ve Yağan, Y. E. (2017) Artificial neural-network-based fault location for power distribution lines using the frequency spectra of fault data, Electrical Engineering, 99, 301- 311. doi:10.1007/s00202-016-0428-8.
• Adak, S., ve Cangi, H. (2015). Analysis and simulation total harmonic distortion of output voltage three level diode clamped inverter in photovoltaic system, Bitlis Eren University. Fen Bilimleri Dergisi, ISSN, 2147-3129.
• https://www.mathworks.com/help/sps/powersys/ref/thd.html, Erişim Tarihi:15.03.2024, Konu: Toplam Harmonik Bozulma.