A nonlinear autoregressive exogenous neural network (NARX-NN) model for the prediction of solvent-based oil extraction from Hura crepitans seeds
-
Olajide Olukayode Ajala
,
Joel Olatunbosun Oyelade
Abstract
Vegetable oils are a crucial source of raw materials for many industries. In order to meet the rising demand for oil on global scale, it has become essential to investigate underutilized plant oilseeds. Hura crepitans seeds are one of the underused plant oilseeds from which oil can be produced via solvent-based extraction. For the purpose of predicting the oil yield from Hura crepitans seeds, the extraction process was modelled using a nonlinear autoregressive exogenous neural network (NARX-NN). The input variables to the model are seed/solvent ratio, extraction temperature and extraction time, while oil yield is the response output variable. NARX-NN model is based on 200 data samples, and model architecture comprises of 3 inputs, 1 hidden layer (with 15 neurons) and 1 output with 2 delay elements. The performance evaluation was carried out to examine the accuracy of the developed model in predicting oil yield from Hura crepitans using different statistical indices. The overall correlation coefficient, R (0.80829), mean square error, MSE (0.0120), root mean square error, RMSE (0.1080) and standard prediction error, SEP (0.1666) show that NARX-NN model can accurately be used for the prediction oil yield from Hura crepitans seeds.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Adepoju, T, Eyibio, U. Comparative study of response surface methodology (RSM) and artificial neural Network (ANN) on oil extraction from Citrus sinensis oilseed and its quality characterization. Chem Res J 2016;1:37–50.Search in Google Scholar
2. Oniya, O, Oyelade, JO, Ogunkunle, O, Idowu, DO. Optimization of solvent extraction of oil from sandbox kernels (Hura crepitans L.) by a response surface method. Energy Pol Res 2017;4:36–43. https://doi.org/10.1080/23815639.2017.1324332.Search in Google Scholar
3. Nde, D, Foncha, A. Optimization methods for the extraction of vegetable oils: a review. Processes 2020;8:1–21. https://doi.org/10.3390/pr8020209.Search in Google Scholar
4. Adewuyi, A, Awolade, P, Oderinde, R. Hura crepitans seed oil: an alternative feedstock for biodiesel production. J Fuel 2014;2014:1–8. https://doi.org/10.1155/2014/464590.Search in Google Scholar
5. Oniya, O, Akande, F, Adedeji, A, Olukayode, O. Transesterification of Hura crepitans oil for biodiesel production. J Eng Appl Sci Res 2014;6:91–9.Search in Google Scholar
6. Oraegbunam, J, Ishola, N, Sotunde, B, Betiku, E. Sandbox oil biodiesel production process modelling and optimization via artificial neural networks and genetic algorithm. In: Proceedings of the OAU faculty of technology conference. Ile-Ife; 2022:225–32 pp.Search in Google Scholar
7. Omilakin, R, Ibrahim, A, Sotunde, B, Betiku, E. Process modelling of solvent extraction of oil from Hura crepitans seeds: adaptive neuro-fuzzy inference system versus response surface methodology. Biomass Convers Biorefin 2020;13:247–60. https://doi.org/10.1007/s13399-020-01080-7.Search in Google Scholar
8. Nwosu-Obieogu, K, Aguele, F, Chiemenem, L. Soft computing prediction of oil extraction from Huracrepitan seeds. Kem Ind 2020;69:653–8. https://doi.org/10.15255/KUI.2020.006.Search in Google Scholar
9. Yusuff, A, Lala, M, Popoola, L, Adesina, O. Optimization of oil extraction from leucaena leucocephala seed as an alternative low-grade feedstock for biodiesel production. SN Appl Sci 2019;1:357. https://doi.org/10.1007/s42452-019-0364-0.Search in Google Scholar
10. Oladipo, B, Betiku, B. Process optimization of solvent extraction of seed oil from moringa oleifera: an appraisal of quantitative and qualitative process variables on oil quality. Biocatal Agric Biotechnol 2019;20:1–12. https://doi.org/10.1016/j.bcab.2019.101187.Search in Google Scholar
11. Otoikhian, S, Aluyor, E, Audu, T. Mechanical extraction and fuel properties evaluation of Hura crepitans seed oil. Chem Technol Ind J 2016;11:1–11.Search in Google Scholar
12. Oloyede, G, Adaramoye, O, Olatinwo, M. Chemical constituents of sandbox tree (Hura crepitans Linn.) and anti-hepatotoxic activity of the leaves and stem bark extracts. In: 39th CSN annual international conference, workshop and exhibition. Port Harcourt, Nigeria: Rivers State University of Science and Technology; 2016.10.7727/wimj.2015.247Search in Google Scholar
13. Medi, B, Asadbeigi, A. Application of GA-optimized NNARX controller to nonlinear chemical and biochemical processes. Heliyon 2021;7:1–11. https://doi.org/10.1016/j.heliyon.2021.e07846.Search in Google Scholar PubMed PubMed Central
14. Alimohammedi, H, Alagoz, B, Tepljakov, A, Vassiljeva, K, Pentlenkov, E. A NARX model reference adaptive control scheme: improved disturbance rejection fractional-order PID control of an experimental magnetic levitation system. Algorithms 2020;13:1–27. https://doi.org/10.3390/a13080201.Search in Google Scholar
15. Jain, V, Sambi, S, Kumar, S, Kumar, B, Kumar, S. Modeling of a UASB reactor by NARX networks for biogas production. Chem Prod Process Model 2015;10:113–21. https://doi.org/10.1515/cppm-2014-0035.Search in Google Scholar
16. Boussaada, Z, Curea, O, Remaci, A, Camblong, H, Bellaaj, N. A nonlinear autoregressive exogenous (NARX) neural network model for the prediction of the daily direct solar radiation. Energies 2018;11:1–21. https://doi.org/10.3390/en11030620.Search in Google Scholar
17. Cococcioni, M, D’Andrea, E, Lazzerini, B. One day-ahead forecasting of energy production in solar photovoltaic installations: an empirical study. Intell Decis Technol 2012;6:197–210. https://doi.org/10.3233/IDT-2012-0136.Search in Google Scholar
18. Chetouani, Y. Using ARX and NARX approaches for modeling and prediction of the process behaviour: application to a reactor-exchanger. Asia Pac J Chem Eng 2008;3:597–605. https://doi.org/10.1002/apj.118.Search in Google Scholar
19. Gaya, M, Wahab, NA, Sam, Y, Samsudin, S, Jamaludin, I. Comparison of NARX neural network and classical modelling approaches. Appl Mech Mater 2014;554:360–5. https://doi.org/10.4028/www.scientific.net/AMM.554.360.Search in Google Scholar
20. Li, P, Hua, P, Gui, D, Niu, J, Pei, P, Zhang, J, et al.. A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal prediction. Sci Rep 2020;10:1–15. https://doi.org/10.1038/s41598-020-70438-8.Search in Google Scholar PubMed PubMed Central
21. Chisa, O, Amine, J, Alim, A, Shakarau, L, Ogbobame, I, Adidauki, S. Effects of parameters on solvent extraction of oil from sandbox (Hura crepitans) seed oil using 24 factorial design. Int J Energy Environ 2021;15:48–55. https://doi.org/10.46300/91012.2021.15.9.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- MSP designing with optimal fractional PI–PD controller for IPTD processes
- A novel nonlinear sliding mode observer to estimate biomass for lactic acid production
- pH prediction for a semi-batch cream cheese fermentation using a grey-box model
- Modeling of carbon dioxide and hydrogen sulfide pollutants absorption in wetted-wire columns with alkanolamines
- Pharmaceutical wastewater treatment using TiO2 nanosheets deposited by cobalt co-catalyst as hybrid photocatalysts: combined experimental study and artificial intelligence modeling
- Numerical simulation of fluid flow mixing in flow-focusing microfluidic devices
- A nonlinear autoregressive exogenous neural network (NARX-NN) model for the prediction of solvent-based oil extraction from Hura crepitans seeds
- Intensification of thorium biosorption onto protonated orange peel using the response surface methodology
- Investigating the energy, environmental, and economic challenges and opportunities associated with steam sterilisation autoclaves
- Short Communication
- Molecular dynamics simulations of water-ethanol droplet on silicon surface
Articles in the same Issue
- Frontmatter
- Research Articles
- MSP designing with optimal fractional PI–PD controller for IPTD processes
- A novel nonlinear sliding mode observer to estimate biomass for lactic acid production
- pH prediction for a semi-batch cream cheese fermentation using a grey-box model
- Modeling of carbon dioxide and hydrogen sulfide pollutants absorption in wetted-wire columns with alkanolamines
- Pharmaceutical wastewater treatment using TiO2 nanosheets deposited by cobalt co-catalyst as hybrid photocatalysts: combined experimental study and artificial intelligence modeling
- Numerical simulation of fluid flow mixing in flow-focusing microfluidic devices
- A nonlinear autoregressive exogenous neural network (NARX-NN) model for the prediction of solvent-based oil extraction from Hura crepitans seeds
- Intensification of thorium biosorption onto protonated orange peel using the response surface methodology
- Investigating the energy, environmental, and economic challenges and opportunities associated with steam sterilisation autoclaves
- Short Communication
- Molecular dynamics simulations of water-ethanol droplet on silicon surface
