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

Yunus Emre Yağan

Article Details

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

Authors:

Yunus Emre Yağan

Publisher:

Bursa Uludağ University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Uludağ Üniversitesi Mühendislik Fakültesi Dergisi Vol.29 Issue 2, pp.507-520

Document Type:

Article

Publication Date:

8/2024

Document Language:

Turkish

Document ID (Org No.):

2001324874

pISSN:

2148-4155

Keywords:

Abstract:

 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 MATLABSimulink 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 MATLABSimulink environment. The test results are presented in comparison with the results obtained using PI controllers in the same inverter system.

 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 MATLABSimulink 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 MATLABSimulink environment. The test results are presented in comparison with the results obtained using PI controllers in the same inverter system.

 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 MATLABSimulink 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 MATLABSimulink environment. The test results are presented in comparison with the results obtained using PI controllers in the same inverter system.

 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, MATLABSimulink 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 MATLABSimulink 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.

Article Details

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

Authors:

Yunus Emre Yağan

Publisher:

Bursa Uludağ University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Uludağ Üniversitesi Mühendislik Fakültesi Dergisi Vol.29 Issue 2, pp.507-520

Document Type:

Article

Publication Date:

8/2024

Document Language:

Turkish

Document ID (Org No.):

2001324874

pISSN:

2148-4155

Artificial neural networks

Grid-connected inverter

Neutral point clamped inverter

Proportional-integral controller.Nötr noktası kenetli evirici

Oransal-integral kontrolcü

Şebeke bağlantılı evirici

Yapay sinir ağları.

Issues

Article Details

Authors: Yunus Emre Yağan

Publisher: Bursa Uludağ University

Main Topics: Elektrik Mühendisliği (Diğer)

Journal: Uludağ Üniversitesi Mühendislik Fakültesi Dergisi Vol.29 Issue 2, pp.507-520

Document Type: Article

Publication Date: 8/2024

Document Language: Turkish

Document ID (Org No.): 2001324874

pISSN: 2148-4155

Issues

Authors:

Yunus Emre Yağan

Publisher:

Bursa Uludağ University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Uludağ Üniversitesi Mühendislik Fakültesi Dergisi Vol.29 Issue 2, pp.507-520

Document Type:

Article

Publication Date:

8/2024

Document Language:

Turkish

Document ID (Org No.):

2001324874

pISSN:

2148-4155