Comparative study of different training algorithms in backpropagation neural networks for generalized biomass higher heating value prediction

Abstract

When selecting biomass feedstock for sustainable heat and electricity generation, higher heating value (HHV) is an important consideration. Meanwhile, the laboratory procedures of using an adiabatic oxygen bomb calorimeter to determine the HHV are strenuous, costly, and time-consuming. As a result, researchers have turned to artificial intelligence techniques such as artificial neural networks (ANN) to predict HHV using data from proximate analysis. Notwithstanding, this approach has been hampered by different case-specific techniques and methodologies given the heterogeneous nature of biomass materials and intricate ANN structures. This study, therefore, examined and compared the efficacy of six training algorithms comprising thirteen distinct training functions of feedforward backpropagation neural networks to predict the HHV of a variety of biomass materials as a function of the proximate analysis. In creating the networks, the neurons of the hidden layer were iterated from 1 to 20 leading to 260 investigated scenarios. Compared to other training algorithms, the Bayesian Regularization and Levenberg-Marquardt with 15 and 12 hidden neurons respectively, demonstrated superior prediction performances based on the Nash-Sutcliff's efficiencies of 0.9044 and 0.8877, and mean squared errors of 0.002271 and 0.00267. It is envisaged that this study will create an insightful paradigm for a rapid selection of best-performing ANN algorithms for biomass HHV prediction.

Keywords

Artificial intelligence / Calorific value / Hidden neuron / Machine learning / Proximate analysis / Training functions

Declaration of competing interest

We wish to submit an original research article entitled “Comparative study of different training algorithms in backpropagation neural networks for generalized biomass higher heating value prediction” for consideration by your reputable journal (Green Energy and Resources).

We have no conflict of interest associated with this publication, and there has been no grant or financial support that could have influenced its outcome. The publication of this article is approved by all authors and, if accepted, it will not be published elsewhere in the same form, in English or any other language.

Appendix A. Supplementary data

Supplementary data to this article can be found online at https://doi.org/10.1016/j.gerr.2024.100060.

References

[1] Adetoro, S.A., Olatomiwa, L., Tsado, J., Dauda, S.M., 2023. Techno-economic and environmental impact assessment of a hybrid renewable energy system employing an enhanced combined dispatch strategy. Green Energy Resour 1, 1-15. https://doi.org/10.1016/j.gerr.2023.100044.

[2] Afolabi, I.C., Epelle, E.I., Gunes, B., Güleç F., Okolie, J.A., 2022. Data-driven machine learning approach for predicting the higher heating value of different biomass classes. Cleanroom Technol. 4, 1227-1241. https://doi.org/10.3390/cleantechnol4040075.

[3] Aghel, B., Yahya, S.I., Rezaei, A., Alobaid, F., 2023. A dynamic recurrent neural network for predicting higher heating value of biomass. Int. J. Mol. Sci. 24, 1-13. https://doi.org/10.3390/ijms24065780.

[4] Anifowose, F., Khoukhi, A., Abdulraheem, A., 2016. Investigating the effect of training - testing data stratification on the performance of soft computing techniques: an experimental study. J. Exp. Theor. Artif. Intell. 1-20. https://doi.org/10.1080/0952813X.2016.1198936.

[5] Anisa, N., Jegalakshimi, N., 2019. Performance comparison of feedforward neural network training algorithms in modelling microwave pyrolysis of oil palm fibre for hydrogen and biochar production. Asia Pac. J. Chem. Eng. 1-16. https://doi.org/10.1002/apj.2388.

[6] Anushka, P., Hazi, M.D.,A., Upaka, R., 2021. Comparison of different artificial neural network (ANN) training algorithms to predict the atmospheric temperature in Tabuk, Saudi Arabia. Mausam 71, 233-244. https://doi.org/10.54302/mausam.v71i2.22.

[7] Aye, P.P., Koontanakulvong, S., Long, T.T., 2017. Estimation of groundwater flow budget in the upper central plain, Thailand from regional groundwater model. Internet J. Soc. Soc. Manag. Syst. 11, 17-3216.

[8] Brandi_c, I., Pezo, L., Biland_zija, N., Peter, A., _Suri_c, J., Vo_ca, N., 2022. Artificial neural network as a tool for estimation of the higher heating value of miscanthus based on ultimate analysis. Mathematics 10, 1-12. https://doi.org/10.3390/math10203732.

[9] Çakman, G., Gheni, S., Ceylan, S., 2021. Prediction of higher heating value of biochars using proximate analysis by artificial neural network. Biomass Convers. Biorefinery 1-9. https://doi.org/10.1007/s13399-021-01358-4.

[10] Chinatamby, P., Jewaratnam, J., 2023. A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforwardbackpropagation neural network (FBNN). Chemosphere 317, 1-12. https://doi.org/10.1016/j.chemosphere.2023.137788.

[11] Cömert, Z., Kocamaz, A., 2017. A study of artificial neural network training algorithms for classification of Cardiotocography signals. Bitlis Eren Univ. J. Sci. Technol. 7, 93-103. https://doi.org/10.17678/beuscitech.338085.

[12] Dodo, U.A., Ashigwuike, E.C., 2023. In-depth physico-chemical characterisation and estimation of the grid power potential of municipal solid wastes in Abuja city. Energy Nexus 10, 1-9. https://doi.org/10.1016/j.nexus.2023.100192.

[13] Dodo, U.A., Ashigwuike, E.C., Abba, S.I., 2022a. Machine learning models for biomass energy content prediction: a correlation-based optimal feature selection approach. Bioresour. Technol. Rep. 19, 1-10. https://doi.org/10.1016/j.biteb.2022.101167.

[14] Dodo, U.A., Ashigwuike, E.C., Emechebe, J.N., Abba, S.I., 2022b. Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm. Energy Nexus 8, 1-15. https://doi.org/10.1016/j.nexus.2022.100157.

[15] Dodo, U.A., Dodo, M.A., Shehu, A.F., Badamasi, Y.A., 2023. Performance analysis of intelligent computational algorithms for biomass higher heating value prediction. Niger. J. Technol. Dev. 20, 44-52.

[16] Estiati, I., Freire, F.B., Freire, J.T., Aguado, R., Olazar, M., 2016. Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass. Fuel 180, 377-383. https://doi.org/10.1016/j.fuel.2016.04.051.

[17] Güleç F., Pekaslan, D., Williams, O., Lester, E., 2022. Predictability of higher heating value of biomass feedstocks via proximate and ultimate analyses - a comprehensive study of artificial neural network applications. Fuel 320, 1-16. https://doi.org/10.1016/j.fuel.2022.123944.

[18] Gunamantha, M., 2016. Prediction of higher heating value bioorganic fraction of municipal solid waste from proximate analysis data. Int. J. Eng. Res. Technol. 5, 442-447.

[19] Kujawska, J., Kulisz, M., Oleszczuk, P., Cel, W., 2023. Improved prediction of the higher heating value of biomass using an artificial neural network model based on the selection of input parameters. Energies 16, 1-16. https://doi.org/10.3390/en16104162.

[20] Matveeva, A., Bychkov, A., 2022. How to train an artificial neural network to predict higher heating values of biofuel. Energies 15, 1-13. https://doi.org/10.3390/en15197083.

[21] Nguyen, T.-A., Ly, H.-B., Thi Mai, H.-V., Tran, V.Q., 2022. On the training algorithms for artificial neural network in predicting compressive strength of recycled aggregate concrete. Lect. Notes Civ. Eng. 203, 1867-1874. https://doi.org/10.1007/978-981-16-7160-9_189.

[22] Nhuchhen, D.R., Salam, P.A., 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.

[23] Olatunji, O.O., Akinlabi, S., Madushele, N., Adedeji, P.A., Felix, I., 2019. Multilayer perceptron artificial neural network for the prediction of heating value of municipal solid waste. AIMS Energy 7, 944-956. https://doi.org/10.3934/energy.2019.6.944.

[24] 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 11, 2499-2508.

[25] Phichai, K., Pragrobpondee, P., Khumpart, T., Hirunpraditkoon, S., 2013. Prediction heating values of lignocellulosics from biomass characteristics. Int. J. Chem. Mol. Eng. 7, 532-535.

[26] Qian, C., Li, Q., Zhang, Z., Wang, X., Hu, J., Cao, W., 2020. Prediction of higher heating values of biochar from proximate and ultimate analysis. Fuel 265, 1-8. https://doi.org/10.1016/j.fuel.2019.116925.

[27] Qian, X., Lee, S., Soto, A., Chen, G., 2018. Regression model to predict the higher heating value of poultry waste from proximate analysis. Resources 7, 1-14. https://doi.org/10.3390/resources7030039.

[28] Salami, B.A., Abba, S.I., Adewumi, A.A., Dodo, U.A., Otukogbe, G.K., Oyedele, L.O., 2023. Building energy loads prediction using bayesian-based metaheuristic optimizedexplainable tree-based model. Case Stud. Constr. Mater. 19, 1-23. https://doi.org/10.1016/j.cscm.2023.e02676.

[29] Shi, Z., Liu, S., Wang, S., Niedzwiecki, L., Baranowski, M., Czerep, M., Tang, C., Kawi, S., Wang, C.-H., Jiang, J., Hedenqvist, M.S., Pawlak-Kruczek, H., Mu, W., Wen, Y., Jönsson, P.G., Yang, W., 2023. Hydrothermal carbonization coupled with pyrolysis: an innovative approach to digestate management. Green Energy Resour 1, 1-12. https://doi.org/10.1016/j.gerr.2023.100034.

[30] Taki, M., Rohani, A., 2022. Machine learning models for prediction the higher heating value (HHV) of municipal solid waste (MSW) for waste-to-energy evaluation. Case Stud. Therm. Eng. 31, 1-13. https://doi.org/10.1016/j.csite.2022.101823.

[31] Uzun, H., Yildiz, Z., Goldfarb, J.L., 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.

[32] Veza, I., Irianto Panchal, H., Paristiawan, P.A., Idris, M., Fattah, I.M.R., Putra, N.R., Silambarasan, R., 2022. Improved prediction accuracy of biomass heating value using proximate analysis with various ANN training algorithms. Results Eng 16, 100688. https://doi.org/10.1016/j.rineng.2022.100688.

[33] Wang, K., Tester, J.W., 2023. Sustainable management of unavoidable biomass wastes. Green Energy Resour 1, 1-25. https://doi.org/10.1016/j.gerr.2023.100005.

[34] Wang, X., Daryapour, M., Shahrabadi, A., Pirasteh, S., Razavirad, F., 2023. Artificial neural networks in predicting of the gas molecular diffusion coefficient. Chem. Eng. Res. Des. 200, 407-418. https://doi.org/10.1016/j.cherd.2023.10.035.

[35] Wu, D., Huang, H., Qiu, S., Liu, Y., Wu, Y., Ren, Y., Mou, J., 2022. Application of Bayesian regularization back propagation neural network in sensorless measurement of pump operational state. Energy Rep. 8, 3041-3050. https://doi.org/10.1016/j.egyr.2022.02.072.