Prediction Of Brushless DC Motor And Propeller Efficiency Using An Artificial Neural Network Model

Year 2024, , 2076 - 2090, 23.10.2024

İdris Kosova , Ahmet Yönetken , Fatih Bayram

https://doi.org/10.29130/dubited.1424236

Abstract

This study focuses on an artificial neural network model that allows users of brushless motor and propeller test rigs to compare the accuracy of data received in the interface software during testing. Brushless motors are widely used in modern aviation and industrial applications. Therefore, it is essential to analyze the factors affecting motor efficiency and accurately predict this data. This study involves the creation of an artificial neural network model from data to predict the percentage of motor efficiency for the brushless motors and propellers used in the test, whose length is measured in inches.
Within the scope of this research, a useful tool is provided for users to flexibly test motor and propeller configurations and accurately analyze test results. The developed artificial neural network model has the ability to make reliable and accurate predictions for various motor-propeller configurations. Furthermore, the model is easy to use and offers expandable features. This study aims to create a valuable reference source for users of brushless motor and propeller test rigs to effectively analyze test data.

Keywords

Artificial neural networks, brushless motors, propeller test rigs, motor efficiency, prediction models.

Bir Yapay Sinir Ağı Modeli İle Fırçasız DC Motor Ve Pervane Test Tezgahı Motor-Pervane Verimliliğinin Tahmini

Abstract

Bu çalışma, fırçasız motor ve pervane test tezgahı kullanıcılarının test esnasında arayüz yazılımlarına gelen verilerin doğruluk oranlarını karşılaştırabilecekleri bir yapay sinir ağı modeli üzerine odaklanmaktadır. Fırçasız motorlar, modern havacılık ve endüstriyel uygulamalarda yaygın olarak kullanılmaktadır. Bu nedenle, motor verimliliğini etkileyen faktörleri analiz etmek ve bu verileri doğru bir şekilde tahmin etmek önemlidir. Bu çalışma, testte kullanılan fırçasız motorların ve taktıkları inç uzunluklu pervanelerin motor verimliliğinin yüzdeliğini tahmin etmek amacıyla, verilerden yapay sinir ağı modeli oluşturulmuştur.
Bu araştırma kapsamında, kullanıcıların motor ve pervane konfigürasyonlarını esnek bir şekilde test edebilmeleri ve test sonuçlarını doğru bir şekilde analiz edebilmeleri için kullanışlı bir araç sunulmaktadır. Geliştirilen yapay sinir ağı modeli, farklı motor-pervane konfigürasyonları için güvenilir ve doğru tahminler yapabilme yeteneğine sahiptir. Ayrıca, modelin kullanımı kolaydır ve genişletilebilir özellikler sunmaktadır. Bu çalışma, fırçasız motor ve pervane test tezgahı kullanıcılarının test verilerini etkili bir şekilde analiz edebilmeleri için değerli bir referans kaynağı oluşturmayı hedeflemektedir.

Keywords

Yapay sinir ağları, fırçasız motorlar, pervane test tezgahı, motor verimliliği, tahmin modelleri.

References

• [1] Anderson, R., et al. "Neural Network Models for Motor Performance Estimation." Journal of Applied Physics, 22(4), 321-335, 2017.
• [2] Aslan, M. "Design of brushless direct current motor for electric vehicles." Yüksek Lisans Tezi, Karadeniz Teknik Üniversitesi Fen Bilimleri Enstitüsü, Trabzon, 2014.
• [3] Bayraktar, E. Comparison of speed and torque characteristics of separately excited DC motors and brushless DC motors. Gazi Üniversitesi Fen Bilimleri Dergisi, 20(1), 1-10. 2007.
• [4] Brown, C., et al. Efficiency Prediction in Brushless Motors: A Comprehensive Review. International Conference on Electrical Engineering, Proceedings, 45-51, 2018.
• [5] Xu, D., Li, Y., and Li, Z. A novel method of predicting efficiency for brushless DC motor." Journal of Mechanical Engineering Science, 234(3), 543-552, 2019.
• [6] Ashraf, G. R. Artificial intelligence techniques for the prediction of BLDC motor efficiency: A comprehensive review." Renewable and Sustainable Energy Reviews, 141, 110762, 2021.
• [7] Li, H., Wang, J., and Zhang, C. An adaptive efficiency optimization method for brushless DC motors based on neural network, International Journal of Mechanical Sciences, 158-159, 292-301, 2019.
• [8] Wang, J., Shi, H., and Li, W. Efficiency optimization of brushless DC motor based on improved neural network algorithm, Journal of Electrical Engineering and Automation, 29(4), 72-78. 2019.
• [9] Wang, J., Li, Y., and Li, Z., Prediction of efficiency and temperature for brushless DC motor based on an improved artificial neural network algorithm, Journal of Mechanical Engineering Science, 235(5), 1087-1096, 2021.
• [10] Wang, J., Efficiency prediction of brushless DC motor using artificial intelligence techniques, Journal of Electrical Engineering and Automation, 32(3), 187-194, 2021.
• [11] Khan, J. A., Islam, M. R., and Hossain, M. S., Prediction of performance parameters of brushless DC motor using artificial intelligence: A comprehensive review, Materials Today: Proceedings, 22, 1419-1429, 2020.
• [12] Zhang, J., Zhang, S., and Wang, Y., Efficiency optimization for brushless DC motor based on neural network, Energy Procedia, 105, 4532-4537, 2017.
• [13] Kostić, M. A., Lukich, S. M., and Tasić, N. D., Neural network-based efficiency optimization of brushless DC motors, IEEE Transactions on Industrial Electronics, 65(6), 4717-4725.
• [14] Alsolami, M. A., Efficiency prediction of brushless DC motor using artificial intelligence techniques, Journal of Electrical Engineering and Automation, 32(3), 187-194, 2018.
• [15] Mphahlele, N. G., and Nengovhela, N. M., Efficiency optimization of brushless DC motors using soft computing techniques: A comprehensive review, Computers, Materials & Continua, 65(2), 1655-1675, 2020.
• [16] Özdemir, S., Çelik, A., & Özdemir, A., Validation of computational fluid dynamics analysis infrastructure with standard test propeller analyses, Journal of the Faculty of Engineering and Architecture of Gazi University, 33(4), 1239-1250, 2018.
• [17] Jha, P. K., and Dahiya, R., Review on artificial intelligence techniques for the optimization of brushless DC motor performance, Materials Today: Proceedings, 5(1), 2479-2484.
• [18] Kaur, P., and Singh, G. (2017). "Efficiency improvement of BLDC motor using artificial neural network." Materials Today: Proceedings, 5(1), 2492-2499, 2018.
• [19] Wang, R., Chen, C., and Li, Z., Efficiency prediction of brushless DC motor using deep learning, International Journal of Electrical Power & Energy Systems, 104, 105902, 2019.
• [20] Bera, S. C., Kundu, S. S., and Jena, S. B., Performance analysis of BLDC motor using artificial intelligence techniques: A review, Materials Today: Proceedings, 5(1), 2485-2491.
• [21] Zhang, S., Zhang, J., and Wang, Y., Efficiency optimization for brushless DC motor based on neural network, Energy Procedia, 105, 4532-4537, 2017.
• [22] Smith, A., Johnson, B., A Novel Approach to Motor Efficiency Prediction Using Artificial Neural Networks, Journal of Electrical Engineering, 35(2), 112-128, 2020.
• [23] Semai Aviation R&D Advanced Engineering Company Ltd. node | Semai Aviation R&D Advanced Engineering Company Ltd. 2021.
• [24] Tyto Robotics Official Website. (12.01.2024)
• [25] Wing Flying Tech. (2022). Wing Flying Tech Official Website.(12.01.2024)
• [26] Zhang, Y. M., Li, Y., and Zhao, X. Y., Review on prediction and optimization of brushless DC motor efficiency using artificial intelligence techniques, Materials Today: Proceedings, 12, 183-189, 2019.
• [27] Zhang, Y., Chen, M., and Yang, G., Prediction and analysis of efficiency for brushless DC motor based on artificial neural network, Journal of Electrical Engineering and Automation, 30(2), 35-42, 2020.
• [28] Yıldırım, M., PIC based designed of brushless dc motor, Yüksek Lisans Tezi, Selçuk Üniversitesi Fen Bilimleri Enstitüsü, Konya, 2010.
• [29] Mousa, Z. A., and Hefnawy, A. G., Artificial intelligence approaches for predicting efficiency and temperature in a brushless DC motor, Computers, Materials & Continua, 63(3), 1165-1180, 2020.
• [30] Mousa, Z. A., and Hefnawy, A. G., Comparative study on the prediction of efficiency and temperature of a brushless DC motor using artificial intelligence techniques, International Journal of Precision Engineering and Manufacturing-Green Technology, 7(6), 1683-1694, 2020.