Citation:

Halimi Soufiane, Benmoussa Ahmed, Soualah Mondir, Amira Mohammed Toufik, 2024. Optimizing Water Productivity in a Passive Solar Still via Advanced Deep Neural Networks Technique, ESP Journal of Engineering & Technology Advancements  4(2): 19-27.

Abstract:

In the quest for sustainable water purification methods, passive solar distillation systems stand out for their ability to desalinate brackish water efficiently. This research focuses on enhancing the efficacy of such systems across varied sectors, including residential, agricultural, and industrial domains. Key variables such as solar radiation, ambient conditions, wind velocity, and design parameters play pivotal roles in the operational efficiency of solar stills. Leveraging advanced machine learning methodologies, the study introduces an innovative approach using Deep Neural Networks, particularly focusing on the Multilayer Perceptron (MLP) architecture, to refine predictions of system yield. A comparative analysis of various hyperparameter tuning strategies reveals the superior performance of the Particle Swarm Optimization (PSO) technique in conjunction with the MLP model. This synergistic PSO-MLP framework, especially when integrated with a specific solar collector design, demonstrated notable achievements, evidenced by a Coefficient of Determination (COD) of 0.98167 and a Mean Squared Error (MSE) of 0.00006. The findings underscore the significant impact of employing advanced computational strategies to predict and enhance the functionality of solar distillation systems, setting a benchmark for future research in sustainable water purification technologies.

References:

[1] U. Nations, International Decade for Action on Water for Sustainable Development, 2018–2028, in, United Nations New York, NY, USA, 2016.
[2] G. Angappan, S. Pandiaraj, H. Panchal, T. Kathiresan, D. Ather, C. Dutta, et al., An extensive review of performance enhancement techniques for pyramid solar still for solar thermal applications, Desalination, 532 (2022) 115692, https://doi.org/https://doi.org/10.1016/j.desal.2022.115692.
[3] K.A. Hammoodi, H.A. Dhahad, W.H. Alawee, Z.M. Omara, A detailed review of the factors impacting pyramid type solar still performance, Alexandria Engineering Journal, 66 (2023) 123-154, https://doi.org/https://doi.org/10.1016/j.aej.2022.12.006.
[4] M.E. Hadi Attia, A.K. Hussein, G. Radhakrishnan, S. Vaithilingam, O. Younis, N. Akkurt, Energy, exergy and cost analysis of different hemispherical solar distillers: A comparative study, Solar Energy Materials and Solar Cells, 252 (2023) 112187, https://doi.org/https://doi.org/10.1016/j.solmat.2023.112187.
[5] L.D. Jathar, S. Ganesan, K. Shahapurkar, M.E.M. Soudagar, M.A. Mujtaba, A.E. Anqi, et al., Effect of various factors and diverse approaches to enhance the performance of solar stills: a comprehensive review, Journal of Thermal Analysis and Calorimetry, 147 (2022) 4491-4522, https://doi.org/10.1007/s10973-021-10826-y.
[6] F.A. Essa, W.H. Alawee, S.A. Mohammed, A.S. Abdullah, Z.M. Omara, Enhancement of pyramid solar distiller performance using reflectors, cooling cycle, and dangled cords of wicks, Desalination, 506 (2021) 115019, https://doi.org/https://doi.org/10.1016/j.desal.2021.115019.
[7] S.K. S, U.M. S.D, M. M, V. Nagaraju, B. Yakkala, D. Vinod, et al., Effect of energy storage material on a triangular pyramid solar still operating with constant water depth, Energy Reports, 8 (2022) 652-658, https://doi.org/https://doi.org/10.1016/j.egyr.2022.10.203.
[8] K.V. Modi, K.H. Nayi, Efficacy of forced condensation and forced evaporation with thermal energy storage material on square pyramid solar still, Renewable Energy, 153 (2020) 1307-1319, https://doi.org/https://doi.org/10.1016/j.renene.2020.02.095.
[9] A.E. Kabeel, W.M. El-Maghlany, M. Abdelgaied, M.M. Abdel-Aziz, Performance enhancement of pyramid- shaped solar stills using hollow circular fins and phase change materials, Journal of Energy Storage, 31 (2020) 101610, https://doi.org/https://doi.org/10.1016/j.est.2020.101610.
[10] A. Prakash, R. Jayaprakash, Performance evaluation of stepped multiple basin pyramid solar still, Materials Today: Proceedings, 45 (2021) 1950-1956, https://doi.org/https://doi.org/10.1016/j.matpr.2020.09.227.
[11] N.Y.Y. Emran, A. Ahsan, E.H.H. Al-Qadami, M.M. El-Sergany, M. Shafiquzzaman, M. Imteaz, et al., Efficiency of a triangular solar still integrated with external PVC pipe solar heater and internal separated condenser, Sustainable Energy Technologies and Assessments, 52 (2022) 102258, https://doi.org/https://doi.org/10.1016/j.seta.2022.102258.
[12] H.R. Goshayeshi, I. Chaer, M. Yebiyo, H.F. Öztop, Experimental investigation on semicircular, triangular and rectangular shaped absorber of solar still with nano-based PCM, Journal of Thermal Analysis and Calorimetry, 147 (2022) 3427-3439, https://doi.org/10.1007/s10973-021-10728-z.
[13] A.O. Alsaiari, E.B. Moustafa, H. Alhumade, H. Abulkhair, A. Elsheikh, A coupled artificial neural network with artificial rabbits optimizer for predicting water productivity of different designs of solar stills, Advances in Engineering Software, 175 (2023) 103315, https://doi.org/https://doi.org/10.1016/j.advengsoft.2022.103315.
[14] W.J.S.D. Victor, D. Somasundaram, K. Gnanadason, Adaptive particle swarm optimization–based deep neural network for productivity enhancement of solar still, Environmental Science and Pollution Research, 29 (2022) 24802-24815, https://doi.org/10.1007/s11356-021-16840-9.
[15] H. Salem, A.E. Kabeel, E.M.S. El-Said, O.M. Elzeki, Predictive modelling for solar power-driven hybrid desalination system using artificial neural network regression with Adam optimization, Desalination, 522 (2022) 115411, https://doi.org/https://doi.org/10.1016/j.desal.2021.115411.
[16] A.H. Elsheikh, E.M.S. El-Said, M. Abd Elaziz, M. Fujii, H.R. El-Tahan, Water distillation tower: Experimental investigation, economic assessment, and performance prediction using optimized machine- learning model, Journal of Cleaner Production, 388 (2023) 135896, https://doi.org/https://doi.org/10.1016/j.jclepro.2023.135896.
[17] A.H. Elsheikh, H. Panchal, M. Ahmadein, A.O. Mosleh, K.K. Sadasivuni, N.A. Alsaleh, Productivity forecasting of solar distiller integrated with evacuated tubes and external condenser using artificial intelligence model and moth-flame optimizer, Case Studies in Thermal Engineering, 28 (2021) 101671, https://doi.org/https://doi.org/10.1016/j.csite.2021.101671.
[18] M. Chelgham, M.M. Belhadj, F. Chelgham, Y. Marif, A. Ouakkaf, H. Bouguettaia, Experimental Investigation of a Single-Slope Basin Still with a Built-in Additional Flat-Plate Solar Air Collector, Applied Solar Energy, 58 (2022) 250-258, https://doi.org/10.3103/S0003701X22020049.
[19] Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature, 521 (2015) 436-444, https://doi.org/10.1038/nature14539.
[20] J. Kennedy, R. Eberhart, Particle swarm optimization, in: Proceedings of ICNN'95 - International Conference on Neural Networks (Vol. 4, pp. 1942-1948). 1995, pp. Vol. 4, pp. 1942-1948.
[21] Y. Shi, R. Eberhart, A modified particle swarm optimizer, in: 1998 IEEE international conference on evolutionary computation proceedings. IEEE world congress on computational intelligence (Cat. No. 98TH8360) (pp. 69-73). IEEE, 1998, pp. 69-73.
[22] M. Clerc, J. Kennedy, The particle swarm - explosion, stability, and convergence in a multidimensional complex space, IEEE Transactions on Evolutionary Computation, 6 (2002) 58-73, https://doi.org/10.1109/4235.985692.
[23] A. Géron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly Media, Inc., 2022.
[24] E. Brochu, V.M. Cora, N.d. Freitas, A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning, ArXiv, abs/1012.2599 (2010).
[25] B. Shahriari, K. Swersky, Z. Wang, R.P. Adams, N.d. Freitas, Taking the Human Out of the Loop: A Review of Bayesian Optimization, Proceedings of the IEEE, 104 (2016) 148-175, https://doi.org/10.1109/JPROC.2015.2494218.
[26] J. Snoek, H. Larochelle, R.P. Adams, Practical Bayesian Optimization of Machine Learning Algorithms, in: Advances in Neural Information Processing Systems, 2012.
[27] J. Bergstra, Y. Bengio, Random Search for Hyper-Parameter Optimization, Journal of Machine Learning Research, 13 (2012) 281-305.
[28] J. Bergstra, D. Yamins, D. Cox, Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures, in: D. Sanjoy, M. David, (Eds.), Proceedings of the 30th International Conference on Machine Learning (pp. 115-123). PMLR, 2013, pp. 115--123.
[29] L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar, Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization, Journal of Machine Learning Research, 18 (2018) 1-52.
[30] J. Bergstra, R. Bardenet, Y. Bengio, B. Kégl, Algorithms for Hyper-Parameter Optimization, in: Advances in Neural Information Processing Systems, Curran Associates, Inc., 2011.
[31] N.Y. Mohamed, A.S. Mahmoud, Heptachlor Epoxide -Pesticide- Removal from Aqueous Solutions Using Nano Zero Valent Iron: Operating Conditions, Response Surface Methodology, and Artificial Intelligence Neural Networks, Solid State Phenomena, 342 (2023) 51-66, https://doi.org/10.4028/p-40bl00.
[32] S.A.A. Akkar, S.A.M. Mohammed, Design of Intelligent Network to Predicate Phenol Removal from Waste Water by Emulsion Liquid Membrane, Materials Science Forum, 1021 (2021) 115-128, https://doi.org/10.4028/www.scientific.net/MSF.1021.115.
[33] N. Zouli, Design of solar power-based hybrid desalination predictive method using optimized neural network, Desalination, 566 (2023) 116854, https://doi.org/https://doi.org/10.1016/j.desal.2023.116854.
[34] Y. Wang, A.W. Kandeal, A. Swidan, S.W. Sharshir, G.B. Abdelaziz, M.A. Halim, et al., Prediction of tubular solar still performance by machine learning integrated with Bayesian optimization algorithm, Applied Thermal Engineering, 184 (2021) 116233, https://doi.org/https://doi.org/10.1016/j.applthermaleng.2020.116233.
[35] E.B. Moustafa, A.H. Hammad, A.H. Elsheikh, A new optimized artificial neural network model to predict thermal efficiency and water yield of tubular solar still, Case Studies in Thermal Engineering, 30 (2022) 101750, https://doi.org/https://doi.org/10.1016/j.csite.2021.101750.

Keywords:

Deep Neural Networks (DNN), Multilayer Perceptron (MLP), Particle Swarm Optimization, Solar Distillation, Water Purification.