Abstract
The goal of this study is to use the deep artificial neural network (DLNN) and support vector machines (SVM) methods to predict the biochar, bio-oil, and synthesis gas yields of the Atriplex nitens S. plant. Furthermore, the study’s sensitivity analysis predicted the importance levels of factors influencing carbonization yields. Three different carbonization temperatures (400 °C, 500 °C, and 600 °C), two different holding times (30 and 60 min), and two different gas flow rate rates (0.2 and 0.5 L min−1) were used as input parameters in the DLNN and SVM models for this purpose. The DLNN method employed two hidden layers. The learning function was Levenberg–Marquardt. As activation functions, the hyperbolic tangent sigmoid transfer function and the linear transfer function were used. The network was tested with various numbers of neurons, and 21 different architectures were created using the number of neurons that produced the lowest MAE value. In the SVM model, the L1QB solver was used. According to the study’s findings, the DLNN method made more accurate predictions than the SVM. The DLNN11 (R2 = 0.987), DLNN19 (R2 = 0.983), and DLNN7 (R2 = 0.960) network architectures produced the best results in this method for biochar, bio-oil, and synthesis gas yield, respectively. As a result of sensitivity analysis, the effect of holding time on biochar and bio-oil yields was found to be greater than other parameters. The synthesis gas yield was most affected by the carbonization temperature.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aleboyeh A, Kasiri MB, Olya ME, Aleboyeh H (2008) Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks. Dyes Pigments 77:288–294. https://doi.org/10.1016/j.dyepig.2007.05.014
Anuse A, Vyas V (2016) A novel training algorithm for convolutional neural network. Complex Intell Syst 2:221–234. https://doi.org/10.1007/s40747-016-0024-6
Aysu T, Kucuk MM (2014) Biomass pyrolysis in a fixed-bed reactor: effects of pyrolysis parameters on product yields and characterization of products. Energy 64:1002–1025. https://doi.org/10.1016/j.energy.2013.11.053
Beis SH, Onay Ö, Kockar ÖM (2002) Fixed-bed pyrolysis of safflower seed: influence of pyrolysis parame-ters on product yields and composition. Renew Energy 26:21–32. https://doi.org/10.1016/S0960-1481(01)00109-4
Biswas B, Pandey N, Bisht Y, Singh R, KumarJ BT (2017) Pyrolysis of agricultural biomass residues: comparative study of corn cob, wheat straw, rice straw and rice husk. Biores Technol 237:57–63. https://doi.org/10.1016/j.biortech.2017.02.046
Bridgwater AV (2003) Renewable fuels and chemicals by thermal processing of biomass. Chem Eng J 91:87–102. https://doi.org/10.1016/S1385-8947(02)00142-0
Cao H, Xin Y, Yuan Q (2016) Prediction of biochar yield from cattle manure pyrolysis via least squares support vector machine intelligent approach. Biores Technol 202:158–164. https://doi.org/10.1016/j.biortech.2015.12.024
Demirbas MF (2001) Biomass resource facilities and biomass conversion processing for fuels and chemicals. Energy Convers Manag 42:1357–1378. https://doi.org/10.1016/S0196-8904(00)00137-0
Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17:37–54. https://doi.org/10.1609/aimag.v17i3.1230
Goyal HB, Seal D, Saxena RC (2008) Bio-fuels from thermochemical conversion of renewable resources: a review. Renew Sustain Energy Rev 12:504–517. https://doi.org/10.1016/j.rser.2006.07.014
Kankar PK, Sharma SC, Harsha SP (2011) Fault diagnosis of ball bearings using machine learning methods. ExpertSyst Appl 38:1876–1886. https://doi.org/10.1016/j.eswa.2010.07.119
Kartal F, Özveren F (2020) A deep learning approach for prediction of syngas lower heating value from CFB gasifier in Aspen plus®. Energy 209:118457. https://doi.org/10.1016/j.energy.2020.118457
Li H, Xu Q, Xiao K, Yang J, Liang S, Hu J, Liu B (2020) Predicting the higher heating value of syngas pyrolyzed from sewage sludge using an artificial neural network. Environ Sci Pollut Res 27:785–797. https://doi.org/10.1007/s11356-019-06885-2
Ling ZH, Kang SY, Zen H, Senior A, Schuster M, Qian XJ, Meng HM, Deng L (2015) Deep learning for acoustic modeling in parametric speech generation: a systematic review of existing techniques and future trends. IEEE Signal Process Mag 32(3):35–52. https://doi.org/10.1109/MSP.2014.2359987
Maes WH, Verbist B (2012) Increasing the sustainability of household cooking in developing countries: policy implications. Renew Sustain Energy Rev 16:4204–4221. https://doi.org/10.1016/j.rser.2012.03.031
MATLAB (2020) Statistics and machine learning Toolbox™ user’s Guide. The MathWorks, Inc., MA
Mighani M, Shahi A, Antonioni G (2017) Catalytic pyrolysis of plastic waste products: time series modeling using least square support vector machine and artificial neural network. In: 16th international conference on sustainable energy technologies – SET 2017 17th - 20th of July 2017, Bologna, IT
Neves D, Thunman H, Matos A (2011) Characterization and prediction of biomass pyrolysis products. Progr Energy Combust Sci 37:611–630. https://doi.org/10.1016/j.pecs.2011.01.001
Ozbas EE, Aksu D, Ongen A, Aydin MA, Ozcan HK (2019) Hydrogen production via biomass gasification, and modeling by supervised machine learning algorithms. Int J Hydrog Energy 44(32):17260–17268. https://doi.org/10.1016/j.ijhydene.2019.02.108
Özçimen D, Meriçboyu AE (2010) Technical note: characterization of biochar and bio-oil samples obtained from carbonization of various biomass materials. Renew Energy 35:1319–1324. https://doi.org/10.1016/j.renene.2009.11.042
Pandey DS, Pan I, Das S, Leahy JJ, Kwapinski W (2015) Multi-gene genetic programming based predictive models for municipal solid waste gasification in a fluidized bed gasifier. Bioresour Technol 179:524–533. https://doi.org/10.1016/j.biortech.2014.12.048
Ren J (2012) ANN vs. SVM: which one performs better in classification of MCCs in mammogram imaging. Knowl Based Syst 26:144–153. https://doi.org/10.1016/j.knosys.2011.07.016
Seidel A (2008) Charcoal in Africa – importance, problems and possible solution strategies. On behalf of the Deutsche Gesellschaft für Technische Zusammenarbeit (GTZ) GmbH, Household Energy Programme – HERA. Eschborn, April 2008
Selvarajoo A, Muhammad D, Arumugasamy SK (2020) An experimental and modelling approach to produce biochar from banana peels through pyrolysis as potential renewable energy resources. Model Earth Syst Environ 6:115–128. https://doi.org/10.1007/s40808-019-00663-2
Smola AJ, Schölkopf BA (2004) Tutorial on support vector regression. Stat Comput 14:199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
Trninic M, Stojiljkovic D, Manic N, Skreiberg Ø, Wang L, Jovovic A, Hide H (2020) A mathematical model of biomass downdraft gasification with an integrated pyrolysis model. Fuel 265:116867. https://doi.org/10.1016/j.fuel.2019.116867
Ucar S, Ozkan AR (2008) Charact bioresource technology erization of products from the pyrolysis of rapeseed oil cake. Biores Technol 99:8771–8776. https://doi.org/10.1016/j.biortech.2008.04.040
Uzun H, Yıldız Z, Goldfarb JL, Ceylan S (2017) Improved prediction of higher heating value of biomass using an artificial neural network model based on proximate analysis. Bioresour Technol 234:122–130. https://doi.org/10.1016/j.biortech.2017.03.015
Wu T, Huang S, Meng Y (2008) Evaluation of ANN and SVM classifiers as predictors to the diagnosis of students with learning disabilities. Expert Syst Appl 34:1846–1856. https://doi.org/10.1016/j.eswa.2007.02.026
Yaman S (2004) Pyrolysis of biomass to produce fuels and chemical feedstocks. Energy Convers Manag 45:651–671. https://doi.org/10.1016/S0196-8904(03)00177-8
Acknowledgements
This research was supported by the scientific research project unit of Iğdır University. The authors are thankful to the University of Igdir for providing the supports
Funding
This study was funded by Iğdır University Scientific Research Projects Unit and Turkish Academy of Sciences (TUBA). Thank you for their contribution.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Editorial responsibility: Zhenyao Shen.
Rights and permissions
About this article
Cite this article
Altikat, A., Alma, M.H. Prediction carbonization yields and the sensitivity analyses using deep learning neural networks and support vector machines. Int. J. Environ. Sci. Technol. 20, 5071–5080 (2023). https://doi.org/10.1007/s13762-022-04407-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13762-022-04407-1