PERFORMANCE EVALUATION OF TRAINING FUNCTIONS IN NEURAL NETWORKS FOR OPTIMAL BIOMASS ENERGY CONTENT PREDICTION
DOI:
https://doi.org/10.33003/fjs-2025-0911-4009Keywords:
Artificial neural networks; biomass; higher heating value; transfer functions; ultimate analysisAbstract
This study compares the performance of ten training functions in artificial neural networks for predicting the higher heating value (HHV) of biomass using ultimate analysis. A 5-10-1 feed-forward back-propagation neural network architecture was implemented, with data normalized and divided into 70% training and 30% testing. Model accuracy was assessed using the coefficient of determination (R²), mean squared error (MSE), and mean absolute error (MAE). Results obtained showed that the Bayesian Regularization algorithm (trainbr, M3) outperformed other models, achieving an R² of 0.8358, MSE of 0.001432, and MAE of 0.000321 in the training phase, and an R² of 0.9451, MSE of 0.003077, and MAE of 0.001225 in the testing phase. The Levenberg‑Marquardt algorithm (trainlm, M1) followed closely, while the Gradient Descent algorithms (traingd and traingdm) gave the weakest results with low or negative R² values. The findings demonstrate that the trainbr function provides superior predictive reliability for biomass HHV.
References
Abba, S. I., Linh, N. T. T., Abdullahi, J., Ali, S. I. A., Pham, Q. B., Abdulkadir, R. A., Costache, R., Nam, V. T., & Anh, D. T. (2020). Hybrid machine learning ensemble techniques for modeling dissolved oxygen concentration. IEEE Access, 8(September), 157218–157237. https://doi.org/10.1109/ACCESS.2020.3017743
Abdollahi, S. A., Basem, A., Alizadeh, A., Jasim, D. J., Ahmed, M., Sultan, A. J., Ranjbar, S. F., & Maleki, H. (2024). Combining artificial intelligence and computational fluid dynamics for optimal design of laterally perforated finned heat sinks. Results in Engineering, 21(March), 102002. https://doi.org/10.1016/j.rineng.2024.102002
Adeleke, A. A., Adedigba, A., Adeshina, S. A., Ikubanni, P. P., Lawal, M. S., Olosho, A. I., Yakubu, H. S., Ogedengbe, T. S., Nzerem, P., & Okolie, J. A. (2024). Comparative studies of machine learning models for predicting higher heating values of biomass. Digital Chemical Engineering, 12(100159), 10. https://doi.org/10.1016/j.dche.2024.100159
Agha, D. C., Dodo, U. A., & Hussein, M. A. (2025). Analysis of the Electricity Generation Potentials of Plastic Wastes on a University Campus. Journal of Science Technology and Education, 13(1), 7–15.
Aghel, B., Yahya, S. I., Rezaei, A., & Alobaid, F. (2023). A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass. International Journal of Molecular Sciences, 24(6), 1–13. https://doi.org/10.3390/ijms24065780
Balsora, H. K., Kartik, A., Dua, V., Joshi, J. B., Kataria, G., Sharma, A., & Chakinala, A. G. (2022). Machine learning approach for the prediction of biomass pyrolysis kinetics from preliminary analysis. Journal of Environmental Chemical Engineering, 10(3), 108025. https://doi.org/10.1016/j.jece.2022.108025
Brandić, I., Antonović, A., Pezo, L., Matin, B., Krička, T., Jurišić, V., Špelić, K., Kontek, M., Kukuruzović, J., Grubor, M., & Matin, A. (2023). Energy Potentials of Agricultural Biomass and the Possibility of Modelling Using RFR and SVM Models. Energies. https://doi.org/10.3390/en16020690
Brandić, I., Pezo, L., Bilandžija, N., Peter, A., Šurić, J., & Voća, N. (2023). Comparison of Different Machine Learning Models for Modelling the Higher Heating Value of Biomass. Mathematics, 11(9), 2098. https://doi.org/10.3390/MATH11092098/S1
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. Nigerian Journal of Technological Development, 20(4), 44–52.
Dodo, U. A., Ashigwuike, E. C., & Emechebe, J. N. (2022). Optimization of Standalone Hybrid Power System Incorporating Waste-to-electricity Plant: A Case Study in Nigeria. 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON), 1–5. https://doi.org/10.1109/NIGERCON54645.2022.9803081
Dodo, U. A., Dodo, M. A., Belgore, A. T., Husein, M. A., Ashigwuike, E. C., Mohammed, A. S., & Abba, S. I. (2024). Comparative study of different training algorithms in backpropagation neural networks for generalized biomass higher heating value prediction. Green Energy and Resources, 2(1), 100060. https://doi.org/10.1016/j.gerr.2024.100060
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(123944), 1–16. https://doi.org/10.1016/j.fuel.2022.123944
Jayapal, A., Ordonez Morales, F., Ishtiaq, M., Kim, S. Y., & Reddy, N. G. S. (2025). Modeling the Higher Heating Value of Spanish Biomass via Neural Networks and Analytical Equations. Energies, 18(15), 4067. https://doi.org/10.3390/EN18154067/S1
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(10), 1–16. https://doi.org/10.3390/en16104162
Liou, J. L., Liao, K. C., Wen, H. T., & Wu, H. Y. (2024). A study on nitrogen oxide emission prediction in the Taichung thermal power plant using an artificial intelligence (AI) model. International Journal of Hydrogen Energy. https://doi.org/10.1016/j.ijhydene.2024.03.120
Msheliza, S. A., & Dodo, U. A. (2025). Performance Comparison of Different Activation Functions in Neural Networks for Biomass Energy Content Prediction. FUDMA Journal of Sciences, 9(4), 285 – 294. https://doi.org/https://doi.org/10.33003/fjs-2025-0904-3493
Nguyen, T. A., Ly, H. B., Mai, H. V. T., & Tran, V. Q. (2021). On the Training Algorithms for Artificial Neural Networks in Predicting the Shear Strength of Deep Beams. Complexity, 2021. https://doi.org/10.1155/2021/5548988
Singh, D., Satija, A., & Hussain, A. (2018). Predicting the calorific value of municipal solid waste of Ghaziabad City, Uttar Pradesh, India, using an artificial neural network approach. In Advances in Intelligent Systems and Computing (Vol. 584, pp. 495–503). https://doi.org/10.1007/978-981-10-5699-4_46
Tahir, J., Ahmad, R., & Tian, Z. (2023). Calorific value prediction models of processed refuse-derived fuel 3 using ultimate analysis. Biofuels. https://doi.org/10.1080/17597269.2022.2116771
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2025 Aisha Saeed Bello, Usman Alhaji Dodo
This work is licensed under a Creative Commons Attribution 4.0 International License.
