Su Elektrolizi Yoluyla Hidrojen Üretimi için Yapay Sinir Ağlarının Modellenmesi

Öz

Yapay sinir ağları, reaksiyon durumu optimizasyonu için hidrojen üretim süreci değişkenlerini tahmin etmek için umut verici bir araç olarak ortaya çıkmıştır. Burada, hidrojen üretimini su elektrolizi yoluyla modellemek için yapay sinir ağlarını kullanan karmaşık doğrusal olmayan sistemleri tahmin etmeyi ve ortaya çıkan ortak zorlukları değerlendirmeyi amaçlıyoruz. Elektrolit malzemesi, elektrolit türü, sağlanan güç (voltaj ve akım), sıcaklık ve zaman gibi farklı elektrolizör sistemleri giriş parametrelerinin hidrojen üretimi üzerindeki etkisini tahmin etmek için bir tahmin modeli geliştirilmiştir. Girdi parametrelerinin hidrojen üretimine yüzde katkıları ve hesaplama süresini en aza indirmek ve ağ doğruluğunu en üst düzeye çıkarmak için en iyi ağ mimarisi gösterildi. Sonuçlar, elektrolizden gelen hidrojen üretim parametrelerinin ve tahmin edilen güvenlik patlama sınırının, ortalama karekök ortalama hatanın %7'si olduğunu göstermektedir. Ayrıca, belirleme katsayısı değeri 0.93 olarak bulunmuştur. Bu tahmin edilen değer, gözlemlenen değerlere çok yakındır. Bu çalışmada geliştirilen sinir ağı algoritması, hidrojen üretimini etkileyen parametreler için elektroliz sürecinde kritik kararlar vermek için kullanılabilir.

Anahtar Kelimeler

• Yapay Sinir Ağları
• Hidrojen Üretimi
• Su elektrolizi

Modeling of Artificial Neural Networks for Hydrogen Production via Water Electrolysis

Öz

Artificial neural networks have emerged as a promising tool for estimating hydrogen production process variables for reaction condition optimization. Here we aim to predict complex nonlinear systems that use of artificial neural networks for modeling hydrogen production via water electrolysis and to evaluate the common challenges that arise. To estimate the effect of different electrolyzer systems input parameters such as electrolyte material, electrolyte type, supplied power (voltage and current), temperature, and time on hydrogen production, a predictive model was developed. The percentage contributions of the input parameters to hydrogen production and the best network architecture to minimize computation time and maximize network accuracy were shown. The results show that the hydrogen production parameters from electrolysis and the predicted safety explosive limit are 7% of the average root mean square error. Furthermore, coefficient of determination value was found 0.93. This predicted value is very close to the observed values. The neural network algorithm developed in this study could be used to make critical decisions in the electrolysis process for parameters affecting hydrogen production.

Anahtar Kelimeler

• Artificial Neural Networks
• Hydrogen Production
• Water electrolysis

Kaynakça

1. Elias L., Cao P., Chitharanjan Hegde A., Magnetoelectrodeposition of Ni-W alloy coatings for enhanced hydrogen evolution reaction, RSC Advances, 2016, 6, 111358–11136
2. Lui J., Chen W.H., Tsang D.C.W., You S., A critical review on the principles, applications, and challenges of waste-to-hydrogen technologies, Renewable and Sustainable Energy Reviews, 2020, 134
3. Wang Q., Hydrogen production, Handbook of Climate Change Mitigation, 2012, 2, 1091–1130 Idriss H., Hydrogen production from water: past and present, Current Opinion in Chemical Engineering, 2020, 29, 74–82
4. Scott K., Chapter 1 Introduction to Electrolysis, Electrolysers and Hydrogen Production, RSC Energy and Environment Series, 2019, 2020-January, 1–27
5. Kaplan H., Şahin M., Bilgiç G., The Influence of Magnetic Field on Newly Designed Oxyhydrogen and Hydrogen Production by Water Electrolysis, Energy Technology, 2021, 9
6. Kaya M.F., Demir N., Albawabiji M.S., Taş M., Investigation of alkaline water electrolysis performance for different cost effective electrodes under magnetic field, International Journal of Hydrogen Energy, 2017, 42, 17583–17592
7. Kothari R., Buddhi D., Sawhney R.L., Studies on the effect of temperature of the electrolytes on the rate of production of hydrogen, International Journal of Hydrogen Energy, 2005, 30, 261–263
8. Shiva Kumar S., Himabindu V., Hydrogen production by PEM water electrolysis – A review, Materials Science for Energy Technologies, 2019, 2, 442–454

9. Abiodun O.I., Jantan A., Omolara A.E., Dada K.V., Mohamed N.A.E., Arshad H., State-of-the-art in artificial neural network applications: A survey, Heliyon, 2018, 4
10. Walczak S., Cerpa N., Artificial Neural Networks, Encyclopedia of Physical Science and Technology, 2003, 631–645
11. Abdelkareem M.A., Soudan B., Mahmoud M.S., Sayed E.T., AlMallahi M.N., Inayat A., et al., Progress of artificial neural networks applications in hydrogen production, Chemical Engineering Research and Design, 2022, 182, 66–86
12. Paul S., Kumar V., Jha P., Artificial neural network and its applications: Unraveling the efficiency for hydrogen production, Applications of Artificial Intelligence in Process Systems Engineering, 2021, 187–206
13. Zamaniyan A., Joda F., Behroozsarand A., Ebrahimi H., Application of artificial neural networks (ANN) for modeling of industrial hydrogen plant, International Journal of Hydrogen Energy, 2013, 38, 6289–6297
14. Nasr N., Hafez H., El Naggar M.H., Nakhla G., Application of artificial neural networks for modeling of biohydrogen production, International Journal of Hydrogen Energy, 2013, 38, 3189–3195
15. Karaci A., Caglar A., Aydinli B., Pekol S., The pyrolysis process verification of hydrogen rich gas (H–rG) production by artificial neural network (ANN), International Journal of Hydrogen Energy, 2016, 41, 4570–4578
16. Döner A., Solmaz R., Kardaş G., Enhancement of hydrogen evolution at cobalt–zinc deposited graphite electrode in alkaline solution, International Journal of Hydrogen Energy, 2011, 36, 7391–7397
17. Colasante G., Gosling P.D., Including Shear in a Neural Network Constitutive Model for Architectural Textiles, Procedia Engineering, 2016, 155, 103–112
18. Agatonovic-Kustrin S., Beresford R., Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research, Journal of Pharmaceutical and Biomedical Analysis, 2000, 22, 717–727
19. Taghavifar H., Mardani A., Application of artificial neural networks for the prediction of traction performance parameters, Journal of the Saudi Society of Agricultural Sciences, 2014, 13, 35–43
20. Smith G., Multiple Regression, Essential Statistics, Regression, and Econometrics, 2015, 301–337
21. Węglarczyk S., Kernel density estimation and its application, ITM Web of Conferences, 2018, 23, 00037