Comparison of Random Forest and Support Vector Regression Models in Predicting Hydrogen Production Process from Biomass

Yıl 2024, Cilt: 39 Sayı: 2, 475 - 488, 11.07.2024

Gülbahar Bilgiç , Ali Emre Gök

https://doi.org/10.21605/cukurovaumfd.1514518

Öz

The need for energy in the world is increasing day by day and various energy production methods are used to meet this need. Production of hydrogen from biomass is one of these methods. Hydrogen production from biomass is a promising process to produce hydrogen and energy which has advantages such as the ability to use sustainable energy sources like biomass and solid waste, being carbon neutral, and increasing energy independence thanks to the variation of resources and the availability of local resources. The catalysts used in this process which can be conducted in three separate ways, affect hydrogen and energy production positively or negatively. One of the most important steps in effectively acquiring the ideal amount of product is predicting the outcomes of this procedure. This article compares a support vector regression (SVR) and random forest (RF) model to predict how various inputs used to produce hydrogen from biomass will affect hydrogen output. Additionally, the effect of catalyst addition on hydrogen yield in biomass processes was examined. In this context, 57 experimental studies from the literature were selected as a data set. From this data, 90% was selected for training and 10% for testing. The outputs were evaluated according to parameters such as R2, RMSE and MSE. The results show that RF and SVR models can significantly predict catalyst activity and hydrogen production.

Anahtar Kelimeler

Hydrogen, Biomass, Random forest, Support vector regression

Biyokütleden Hidrojen Üretiminde Rastgele Orman ve Destek Vektör Regresyon Modellerinin Kıyaslaması

Öz

Dünyadaki enerji ihtiyacı günden güne artış göstermekte ve bu ihtiyacın karşılanması için, çeşitli enerji üretim yöntemleri kullanılmaktadır. Bu yöntemlerden biri biyokütleden hidrojen üretimidir. Biyokütle ve atık benzeri yenilenebilir enerji kaynaklarından yararlanma kabiliyeti, karbon nötr olması, kaynak çeşitliliği ve yerel kaynakların kullanılabilirliği sayesinde enerji bağımsızlığını artırması gibi avantajları bulunan biyokütleden hidrojen üretimi, gelecek vaat eden bir hidrojen ve enerji üretim sürecidir. Üç farklı yöntem kullanılarak gerçekleştirilebilen bu süreçte kullanılan katalizörler, hidrojen üretimine olumlu ve olumsuz etki etmektedir. Bu sürecin sonuçlarını tahmin etmek, optimum miktarda ürünü verimli bir şekilde elde etmede kritik bir adımdır. Bu makalede, biyokütleden hidrojen üretmek için kullanılan çeşitli girdilerin hidrojen çıktısını nasıl etkileyeceğini tahmin etmek için bir destek vektör regresyonunu (SVR) ve rastgele orman (RF) modelini karşılaştırılmıştır. Ayrıca biyokütle süreçlerinde katalizör ilavesinin hidrojen verimi üzerinde etkisini incelenmiştir. Bu bağlamda literatürden 57 deneysel çalışma veri seti olarak seçilmiştir. Bu verilerden eğitim için %90 ve test için %10 seçilmiştir. Sonuçlar R2, RMSE ve MSE gibi parametrelere göre değerlendirilmiştir. Sonuç olarak RF ve SVR modellerinin katalizör aktivitesini ve hidrojen üretimini önemli ölçüde tahmin edebildiğini göstermektedir.

Anahtar Kelimeler

Hidrojen, Biyokütle, Rastgele orman, Destek vektör regresyonu

Kaynakça

• 1. Jamro, I.A., Raheem, A., Khoso, S., Baloch, H.A., Kumar, A., Chen, G., Bhagat, W.A., Wenga, T., Ma, W., 2023. Investigation of Enhanced H2 Production from Municipal Solid Waste Gasification Via Artificial Neural Network with Data on Tar Compounds. Journal of Environmental Management, 328, 117014.
• 2. He, M., Hu, Z., Xiao, B., Li, J., Guo, X., Luo, S., Yang, F., Feng, Y., Yang, G., Liu, S., 2009. Hydrogen-rich Gas from Catalytic Steam Gasification of Municipal Solid Waste (MSW): Influence of Catalyst and Temperature on Yield and Product Composition. International Journal of Hydrogen Energy, 34(1), 195-203.
• 3. Wu, M.-H., Lin, C.-L., Zeng, W.-Y., 2014. Effect of Waste Incineration and Gasification Processes on Heavy Metal Distribution. Fuel Processing Technology, 125, 67-72.
• 4. Gao, N., Liu, S., Han, Y., Xing, C., Li, A., 2015. Steam Reforming of Biomass Tar for Hydrogen Production over NIO/Ceramic Foam Catalyst. International Journal of Hydrogen Energy, 40(25), 7983-7990.
• 5. Irfan, M., Li, A., Zhang, L., Javid, M., Wang, M., Khushk, S., 2019. Enhanced H2 Production from Municipal Solid Waste Gasification Using Ni–Cao–Tio2 Bifunctional Catalyst Prepared by DC Arc Plasma Melting. Industrial & Engineering Chemistry Research, 58(29), 13408-13419.
• 6. Zhou, C., Yrjas, P., Engvall, K., 2021. Reaction Mechanisms for H2O-Enhanced Dolomite Calcination at High Pressure. Fuel Processing Technology, 217, 106830.
• 7. Soomro, A., Chen, S., Ma, S., Xiang, W., 2018. Catalytic Activities of Nickel, Dolomite, and Olivine for Tar Removal and H2-Enriched Gas Production in Biomass Gasification Process. Energy & Environment, 29(6), 839-867.
• 8. Irfan, M., Li, A., Zhang, L., Ji, G., Gao, Y., Khushk, S., 2021. Hydrogen-rich Syngas from Wet Municipal Solid Waste Gasification Using Ni/waste Marble Powder Catalyst Promoted by Transition Metals. Waste Management, 132, 96-104.
• 9. Li, B., Magoua Mbeugang, C. F., Huang, Y., Liu, D., Wang, Q., Zhang, S., 2022. A Review of Cao Based Catalysts for Tar Removal During Biomass Gasification. Energy, 244, 123172.
• 10. Shen, Y., Yoshikawa, K., 2013. Recent Progresses in Catalytic Tar Elimination During Biomass Gasification or Pyrolysis - A Review. Renewable and Sustainable Energy Reviews, 21, 371-392.
• 11. Bilgiç, G., Bendeş, E., Öztürk, B., Atasever, S., 2023. Recent Advances in Artificial Neural Network Research for Modeling Hydrogen Production Processes. International Journal of Hydrogen Energy, 48(50), 18947- 18977.
• 12. Bilgiç, G., Öztürk, B., Atasever, S., Şahin, M., Kaplan, H., 2023. Prediction of Hydrogen Production by Magnetic Field Effect Water Electrolysis Using Artificial Neural Network Predictive Models. International Journal of Hydrogen Energy, 48(53), 20164-20175.
• 13. Qi, J., Zhang, K., Hu, M., Xu, P., Huhe, T., Ling, X., Yuan, H., Wang, Y., Chen, Y., 2023. Study on Waste Tire Pyrolysis Product Characteristics Based on Machine Learning. Journal of Environmental Chemical Engineering, 11(6), 111314.
• 14. Lei, C., Deng, J., Cao, K., Xiao, Y., Ma, L., Wang, W., Ma, T., Shu, C., 2019. A Comparison of Random Forest and Support Vector Machine Approaches to Predict Coal Spontaneous Combustion in Gob. Fuel, 239, 297- 311.
• 15. Potnuri, R., Rao, C.S., Surya, D.V., Kumar, A., Basak, T., 2023. Utilizing Support Vector Regression Modeling to Predict Pyro Product Yields from Microwave-Assisted Catalytic Co-pyrolysis of Biomass and Waste Plastics. Energy Conversion and Management, 292, 117387.
• 16. Breiman, L., 2001. Random Forests. Machine Learning, 45(1), 5-32.
• 17. Yu, P.-S., Yang, T.-C., Chen, S.-Y., Kuo, C.-M., Tseng, H.-W., 2017. Comparison of Random Forests and Support Vector Machine for Real-Time Radar-Derived Rainfall Forecasting. Journal of Hydrology, 552, 92-104
• 18. Smola, A.J., Schölkopf, B., 2004. A Tutorial on Support Vector Regression. Statistics and Computing, 14(3), 199-222.
• 19. Awad, M., Khanna, R., 2015. Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers. Springer Natures, 268.
• 20. Mutlu, A. Y., Yucel, O., 2018. An Artificial Intelligence Based Approach to Predicting Syngas Composition for Downdraft Biomass Gasification. Energy, 165, 895-901.
• 21. Elmaz, F., Yücel, Ö., Mutlu, A.Y., 2020. Predictive Modeling of Biomass Gasification with Machine Learning-based Regression Methods. Energy, 191, 116541.
• 22. Leng, E., He, B., Chen, J., Liao, G., Ma, Y., Zhang, F., Liu, S., E, J., 2021. Prediction of Three-phase Product Distribution and Bio-oil Heating Value of Biomass Fast Pyrolysis Based on Machine Learning. Energy, 236, 121401.
• 23. Xing, J., Luo, K., Wang, H., Fan, J., 2019. Estimating Biomass Major Chemical Constituents from Ultimate Analysis Using a Random Forest Model. Bioresource Technology, 288, 121541.
• 24. Irfan, M., Li, A., Zhang, L., Ji, G., Gao, Y., Khushk, S., 2021. Hydrogen-rich Syngas from Wet Municipal Solid Waste Gasification Using Ni/waste Marble Powder Catalyst Promoted by Transition Metals. Waste Management, 132, 96-104.
• 25. Choi, Y.-K., Cho, M.-H., Kim, J.-S., 2015a. Steam/oxygen Gasification of Dried Sewage Sludge in a Two-stage Gasifier: Effects of the Steam to Fuel Ratio and Ash of the Activated Carbon on the Production of
• Hydrogen and Tar Removal. Energy, 91, 160-167.
• 26. Kargbo, H.O., Zhang, J., Phan, A.N., 2023. Robust Modelling Development for Optimisation of Hydrogen Production from Biomass Gasification Process Using Bootstrap Aggregated Neural Network. International Journal of Hydrogen Energy, 48(29), 10812-10828.
• 27. Luo, S., Xiao, B., Hu, Z., Liu, S., Guo, X., He, M., 2009. Hydrogen-rich Gas from Catalytic Steam Gasification of Biomass in a Fixed Bed Reactor: Influence of Temperature and Steam on Gasification Performance. International Journal of Hydrogen Energy, 34(5), 2191-2194.
• 28. Nahil, M.A., Wang, X., Wu, C., Yang, H., Chen, H., Williams, P.T., 2013. Novel Bi-functional Ni-Mg-Al-Cao Catalyst for Catalytic Gasification of Biomass for Hydrogen Production with in Situ CO2 Adsorption. RSC Advances, 3(16), 5583.
• 29. Luo, S., Xiao, B., Hu, Z., Liu, S., Guo, X., He, M., 2009. Hydrogen-rich Gas from Catalytic Steam Gasification of Biomass in a Fixed Bed Reactor: Influence of Temperature and Steam on Gasification Performance. International Journal of Hydrogen Energy, 34(5), 2191-2194.
• 30. Barontini, F., Frigo, S., Gabbrielli, R., Sica, P., 2021. Co-gasification of Woody Biomass with Organic and Waste Matrices in a Down-draft Gasifier: An Experimental and Modeling Approach. Energy Conversion and Management, 245, 114566.
• 31. Li, B., Yang, H., Wei, L., Shao, J., Wang, X., Chen, H., 2017. Hydrogen Production from Agricultural Biomass Wastes Gasification in a Fluidized Bed with Calcium Oxide Enhancing. International Journal of Hydrogen Energy, 42(8), 4832-4839.
• 32. Gao, N., Liu, S., Han, Y., Xing, C., Li, A., 2015. Steam Reforming of Biomass Tar for Hydrogen Production over NIO/ceramic Foam Catalyst. International Journal of Hydrogen Energy, 40(25), 7983-7990.
• 33. Yusup, S., Khan, Z., Ahmad, M.M., Rashidi, N.A., 2014. Optimization of Hydrogen Production in In-situ Catalytic Adsorption (ICA) Steam Gasification Based on Response Surface Methodology. Biomass and Bioenergy, 60, 98-107.
• 34. Wei, L., Xu, S., Liu, J., Liu, C., Liu, S., 2008. Hydrogen Production in Steam Gasification of Biomass with CaO as a CO2 Absorbent. Energy & Fuels, 22(3), 1997-2004.
• 35. Faki, E., Üzden, Ş.T., Seçer, A., Hasanoğlu, A., 2022. Hydrogen Production from Low Temperature Supercritical Water CO-Gasification of Low Rank Lignites with Biomass. International Journal of Hydrogen Energy, 47(12), 7682-7692.
• 36. Ozbas, E.E., Aksu, D., Ongen, A., Aydin, M.A., Ozcan, H.K., 2019. Hydrogen Production Via Biomass Gasification, and Modeling by Supervised Machine Learning Algorithms. International Journal of Hydrogen Energy, 44(32), 17260-17268.
• 37. Balsora, H.K., Kartik, S., Joshi, J.B., Sharma, A., Chakinala, A.G., 2023. Artificial Neural Network-based Models for the Prediction of Biomass Pyrolysis Products from Preliminary Analysis. Industrial & Engineering Chemistry Research, 62(36), 14311-14319.
• 38. Chen, Y., Wang, Z., Lin, S., Qin, Y., Huang, X., 2023. A Review on Biomass Thermal-oxidative Decomposition Data and Machine Learning Prediction of Thermal Analysis. Cleaner Materials, 9, 100206.
• 39. Onsree, T., Tippayawong, N., 2021. Machine Learning Application to Predict Yields of Solid Products from Biomass Torrefaction. Renewable Energy, 167, 425-432.