Abstract
A new set of software tools for the prediction of the higher heating values (HHV) of arbitrarily chosen biomass species is presented. A comparative qualitative and quantitative analysis of 12 algorithms for training artificial neural networks (ANN) which predict the HHV of biomass using the proximate analysis is given. Fixed carbon, volatile matter and ash percentage were utilized as inputs. Each ANN had the same structure but a different training algorithm (BFGS Quasi Newton, Bayesian Regularization, Conjugate Gradient—Powell/Beale Restarts, Fletcher–Powell Conjugate Gradient, Polak–Ribiére Conjugate Gradient, Gradient Descent, Gradient Descent Momentum, Variable Learning Rate Gradient Descent, Levenberg–Marquardt, One Step Secant, Resilient Backpropagation, Scaled Conjugate Gradient). To ensure an extended applicability of our results to a wide range of different biomass species, the data conditioning was based on diverse experimental data gathered from the literature, 447 samples overall. Out of these, 301 datasets were used for the training, validation and testing by MathWorks MATLAB Neural Network Fitting Application and by custom designed codes, and 146 remaining datasets were used for the independent evaluation of all training algorithms. The HHV predictions of the ANN-based fitting functions were thoroughly tested and intercompared, to which purpose we developed a test suite which applies mean squared error, coefficient of the determination, mean Poisson deviance, mean Gamma deviance and Friedman test. The comparative analysis showed that several algorithms resulted in ANN-based fitting functions whose outputs correlated well with measured values of the HHV. All programming codes are freely downloadable.
Similar content being viewed by others
Availability of data and material
All data are available on open online repository Mendeley Data.
Code availability
All custom code is available on open online repository Mendeley Data.
References
Abdulsalam J, Lawal AI, Setsepu RL, Onifade M, Bada S (2020) Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties. Bioresour Bioprocess 7:1–22. https://doi.org/10.1186/s40643-020-00350-6
Akkaya AV (2009) Proximate analysis based multiple regression models for higher heating value estimation of low rank coals. Fuel Process Technol 90(2):165–170. https://doi.org/10.1016/j.fuproc.2008.08.016
Alaba PA, Popoola SI, Abnisal F, Lee CS, Ohunakin OS, Adetiba E, Akanle MB, Abdul Patah MF, Atayero AAA, Wan Daud WMA (2020) Thermal decomposition of rice husk: a comprehensive artificial intelligence predictive model. J Therm Anal Calorim 140:1811–1823. https://doi.org/10.1007/s10973-019-08915-0
Alagić SČ, Maluckov BS, Radojičić VB (2015) How can plants manage polycyclic aromatic hydrocarbons? May these effects represent a useful tool for an effective soil remediation? A review. Clean Technol Environ Policy 17:597–614. https://doi.org/10.1007/s10098-014-0840-6
Boumanchar I, Charafeddine K, Chhiti Y, Alaoui FEMH, Sahibed-Dine A, Bentiss F, Jama C, Bensitel M (2019) Biomass higher heating value prediction from ultimate analysis using multiple regression and genetic programming. Biomass Convers Biorefinery 9(3):499–509. https://doi.org/10.1007/s13399-019-00386-5
Channiwala S, Parikh P (2002) A unified correlation for estimating HHV of solid, liquid and gaseous fuels. Fuel 81:1051–1063. https://doi.org/10.1016/S0016-2361(01)00131-4
Conag AT, Villahermosa JER, Cabatingan LK, Go AW (2019) Predictive HHV model for raw and torrefied sugarcane residues. Waste Biomass Valorization 10:1929–1943. https://doi.org/10.1007/s12649-018-0204-2
Cordero T, Marquez F, Rodriguez-Mirasol J, Rodriguez J (2001) Predicting heating values of lignocellulosics and carbonaceous materials from proximate analysis. Fuel 80:1567–1571. https://doi.org/10.1016/S0016-2361(01)00034-5
Dashti A, Noushabadi AS, Raji M, Razmi A, Ceylan S, Mohammadi AH (2019) Estimation of biomass higher heating value (HHV) based on the proximate analysis: smart modeling and correlation. Fuel 257:115931. https://doi.org/10.1016/j.fuel.2019.115931
Deep Learning Toolbox Documentation: Choose a Multilayer Neural Network Training Function. MathWorks. Jan 18, 2021. Available from: https://au.mathworks.com/help/deeplearning/ug/choose-a-multilayer-neural-network-training-function.html
Demirbaş A, Demirbaş AH (2004) Estimating the calorific values of lignocellulosic fuels. Energy Explor Exploit 22:135–143. https://doi.org/10.1260/0144598041475198
García R, Pizarro C, Lavín AG, Bueno JL (2014) Spanish biofuels heating value estimation. Part II: Proximate analysis data. Fuel 117:1139–1147. https://doi.org/10.1016/j.fuel.2013.08.049
Ghugare S, Tiwary S, Elangovan V, Tambe S (2014) Prediction of higher heating value of solid biomass fuels using artificial intelligence formalisms. BioEnergy Res 7:681–692. https://doi.org/10.1007/s12155-013-9393-5
Jakšić O (2021) HHVannPRO: ANN trained to predict the biomass HHV based on the results of the proximate analysis Mendeley Data. https://doi.org/10.17632/dx8kbs5yxc.2
Keybondorian E, Zanbouri H, Bemani A, Hamule T (2017) Application of MLP-ANN strategy to predict higher heating value of biomass in terms of proximate analysis. Energy Sour a: Recov Utiliz Environ Effects 39(22):2105–2111. https://doi.org/10.1080/15567036.2017.1403519
Klass DL (1998) Biomass for renewable energy, fuels, and chemicals. Academic Press, San Diego. https://doi.org/10.1016/B978-0-12-410950-6.X5000-4
Krishnan R, Hauchhum L, Gupta R, Pattanayak S. (2018) Prediction of equations for higher heating values of biomass using proximate and ultimate analysis. In: Proceedings of 2018 2nd international conference on power, energy and environment: towards smart technology (ICEPE), Shillong, India, pp 1–5. https://doi.org/10.1109/EPETSG.2018.8658984
Lakovic N, Khan A, Petković B, Petkovic D, Kuzman B, Resic S, Jermsittiparsert K, Azam S (2021) Management of higher heating value sensitivity of biomass by hybrid learning technique. Biomass Convers Biorefinery. https://doi.org/10.1007/s13399-020-01223-w
Liang M, Lu W, Lei P, Wang L, Wang B, Li B, Shen Y, Zhang K (2019) Physical and combustion properties of binder-assisted hydrochar pellets from hydrothermal carbonization of tobacco stem. Waste Biomass Valorization. https://doi.org/10.1007/s12649-019-00848-x
Merckel RD, Heydenrych M (2017) Mass-fraction of oxygen as a predictor of HHV of gaseous, liquid and solid fuels. Energy Procedia 142:4124–4130. https://doi.org/10.1016/j.egypro.2017.12.335
Mijailovic I, Radojicic V, Ecim-Djuric O, Stefanovic G, Kulic G (2014) Energy potential of tobacco stalks in briquettes and pellets production. J Environ Prot Ecol 15:1034–1041
Nhuchhen DR, Salam PA (2012) Estimation of higher heating value of biomass from proximate analysis: a new approach. Fuel 99:55–63. https://doi.org/10.1016/j.fuel.2012.04.015
Pattanayak S, Loha C, Hauchhum L, Sailo L (2020) Application of MLP-ANN models for estimating the higher heating value of bamboo biomass. Biomass Convers Biorefinery. https://doi.org/10.1007/s13399-020-00685-2
Priya AD, Setty YP (2019) Cashew apple juice as substrate for microbial fuel cell. Fuel 246:75–78. https://doi.org/10.1016/j.fuel.2019.02.100
Qian X, Lee S, Soto A-M, Chen G (2018) Regression model to predict the higher heating value of poultry waste from proximate analysis. Resources 7(3):39. https://doi.org/10.3390/resources7030039
Samadi SH, Ghobadian B, Nosrati M (2021) "Prediction of higher heating value of biomass materials based on proximate analysis using gradient boosted regression trees method. Energy Sour a: Recovery Utiliz Environ Effects 43(6):672–681. https://doi.org/10.1080/15567036.2019.1630521
Sekh AA, Dogra DP, Kar S, Roy PP, Prasad DK (2020a) ELM-HTM guided bio-inspired unsupervised learning for anomalous trajectory classification. Cognit Syst Res 63:30–41
Sekh AA, Dogra DP, Kar S, Roy PP (2020b) Video trajectory analysis using unsupervised clustering and multi-criteria ranking. Soft Comput 24:16643–16654. https://doi.org/10.1007/s00500-020-04967-9
Tan P, Zhang C, Xia Ji, Fang Q-Y, Chen G (2015) Estimation of higher heating value of coal based on proximate analysis using support vector regression. Fuel Process Technol 138:298–304. https://doi.org/10.1016/j.fuproc.2015.06.013
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. Biores Technol 234:122–130. https://doi.org/10.1016/j.biortech.2017.03.015
Wahid FRAA, Saleh S, Samad NAFA (2017) Estimation of higher heating value of torrefied palm oil wastes from proximate analysis. Energy Procedia 138:307–312. https://doi.org/10.1016/j.egypro.2017.10.102
Wang C, Li L, Chen R, Ma X, Lu M, Ma W, Peng H (2019) Thermal conversion of tobacco stem into gaseous products. J Therm Anal Calorim 137:811–823. https://doi.org/10.1007/s10973-019-08010-4
Yu W, Chen C (2014) Predicting the heating value of rice husk with neural network. In: Practical applications of intelligent systems. Springer, Berlin, Heidelberg, pp 877–885. https://doi.org/10.1007/978-3-642-54927-4_84
Acknowledgements
This work was financially supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia (Grant No. 451-03-9/2021-14/200026). The authors would like to express their gratitude to Miss Maja Malnar for kindling the authors’ interest in the topic of biomass HHV, as well as for procuring references on tobacco biomass.
Funding
This work was financially supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia, Grant No. 451-03-9/2021-14/200026.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Consent to participate
All authors expressed their explicit consent to participate in this work.
Consent for publication
All authors expressed their explicit consent with the publication of this joint manuscript in soft computing.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jakšić, O., Jakšić, Z., Guha, K. et al. Comparing artificial neural network algorithms for prediction of higher heating value for different types of biomass. Soft Comput 27, 5933–5950 (2023). https://doi.org/10.1007/s00500-022-07641-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-022-07641-4