Neural Network-Based Prediction and Optimization of Performance in Single Slope Solar Stills Enhanced with Nanoparticles for Improved Water Production
J. Environ. Nanotechnol., Volume 13, No 4 (2024) pp. 489-499
Abstract
This research uses a neural network technique to anticipate and optimize temperature and production factors in a single-slope solar still. In addition to comparable productivity measures and actual and expected temperatures of the glass and water, the experimental dataset contains changes in sun intensity, water depth, and the proportion and type of nanoparticles (TiO2 and CuO). Enhancing knowledge and performance of solar stills, which are essential to sustainable freshwater production, is the goal. Based on input characteristics, a neural network model was developed to forecast water temperature, glass temperature, and productivity. By contrasting expected results with actual measurements, the model's performance was assessed and shown to have good predictive capabilities. The kind and concentration of nanoparticles, as well as sun intensity, had a substantial impact on thermal behaviour and productivity, according to the results. Productivity levels, for example, varied greatly, from as low as 0.3 kg/m²·h with CuO nanoparticles to as high as 2.75 kg/m²·h with TiO2 under some circumstances. The models RNN, LSTM, and CNN were tested, with RNN consistently providing the most accurate predictions across all datasets, particularly for productivity, glass temperature, and water temperature. Along with precise forecasts, optimization methods were used to identify the ideal operating settings for optimum output. This method promotes more effective and environmentally friendly desalination solutions by offering insightful information on solar still design and operation enhancements. Future experimental configurations and practical applications for increased water production may be guided by the results.
Full Text
Reference
Abdullah, A.S., Joseph, A., Kandeal, A.W., Alawee, W.H., Peng, G., Thakur, A.K. and Sharshir, S.W., Application of machine learning modeling in prediction of solar still performance: A comprehensive survey, Results Eng., 21101800 (2024). https://doi.org/10.1016/j.rineng.2024.101800
Abujazar, M.S.S., Fatihah, S., Ibrahim, I.A., Kabeel, A.E. and Sharil, S., Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model, J. Cleaner Prod., 170147–159 (2018). https://doi.org/10.1016/j.jclepro.2017.09.092
Alsaiari, A.O., Moustafa, E.B., Alhumade, H., Abulkhair, H. and Elsheikh, A., A coupled artificial neural network with artificial rabbits optimizer for predicting water productivity of different designs of solar stills, Adv. Eng. Software, 175103315 (2023). https://doi.org/10.1016/j.advengsoft.2022.103315
Alwan, N.T., Ali, B.M., Alomar, O.R., Abdulrazzaq, N.M., Ali, O.M. and Abed, R.M., Performance of solar still units and enhancement techniques: A review investigation, Heliyon, 10(18), e37693 (2024). https://doi.org/10.1016/j.heliyon.2024.e37693
Elsheikh, A.H., Katekar, V.P., Muskens, O.L., Deshmukh, S.S., Elaziz, M.A. and Dabour, S.M., Utilization of LSTM neural network for water production forecasting of a stepped solar still with a corrugated absorber plate, Process Safety Environ. Pro., 148273–282 (2021). https://doi.org/10.1016/j.psep.2020.09.068
Essa, F.A., Abd Elaziz, M. and Elsheikh, A.H., An enhanced productivity prediction model of active solar still using artificial neural network and Harris Hawks optimizer, Appl. Therm. Eng., 170115020 (2020).
https://doi.org/10.1016/j.applthermaleng.2020.115020
Hemmat Esfe, M., Esfandeh, S. and Toghraie, D., Optimization of influential geometrical parameters of single slope solar still equipped with thermoelectric system to achieve maximum desalinated water, Energy Reports, 75257–5268 (2021).
https://doi.org/10.1016/j.egyr.2021.08.106
Mashaly, A.F. and Alazba, A.A., Neural network approach for predicting solar still production using agricultural drainage as a feedwater source, Desalin. Water Treat., 57(59), 28646–28660 (2016).
https://doi.org/10.1080/19443994.2016.1193770
Migaybil, H.H. and Gopaluni, B., A performance neural network model for conventional solar stills via transfer learning, Appl. Energy, 375124118 (2024). https://doi.org/10.1016/j.apenergy.2024.124118
Moustafa, E.B., Hammad, A.H. and Elsheikh, A.H., A new optimized artificial neural network model to predict tubular solar still's thermal efficiency and water yield, Case Stud. Therm. Eng., 30101750 (2022).
https://doi.org/10.1016/j.csite.2021.101750
Mustafa, M. N., Shafie, S., Wahid, M. H. and Sulaiman, Y., Preparation of TiO2 compact layer by heat treatment of electrospun TiO2 composite for dye-sensitized solar cells,Thin Solid Films, 693, 137699, (2020). https://doi.org/10.1016/j.tsf.2019.137699
Nazari, S., Bahiraei, M., Moayedi, H. and Safarzadeh, H., A proper model to predict energy efficiency, exergy efficiency, and water productivity of a solar still via optimized neural network, J. Cleaner Prod., 277123232 (2020). https://doi.org/10.1016/j.jclepro.2020.123232
Senthilkumar, N., Yuvaperiyasamy, M., Deepanraj, B. and Sabari, K., Fuzzy logic-based prediction and parametric optimizing using particle swarm optimization for performance improvement in pyramid solar still, Water Sci. Technol., 90(4), 1321–1337 (2024).
https://doi.org/10.2166/wst.2024.277
Shanmugan, S., Hammoodi, K.A., Eswarlal, T., Selvaraju, P., Bendoukha, S., Barhoumi, N., Mansour, M., Refaey, H.A., Rao, M.C., Mourad, A.H.I., Fujii, M. and Elsheikh, A., A technical appraisal of solar photovoltaic-integrated single slope single basin solar still for simultaneous energy and water generation, Case Stud. Therm. Eng., 54104032 (2024). https://doi.org/10.1016/j.csite.2024.104032
Sharon, H., Reddy, K.S. and Gorjian, S., Parametric investigation and yearround performance of a novel passive multi-chamber vertical solar diffusion still: Energy, exergy and enviro-economic aspects, Solar Energy, 211831–846 (2020). https://doi.org/10.1016/j.solener.2020.10.016
Sharshir, S.W., Elhelow, A., Kabeel, A., Hassanien, A.E., Kabeel, A.E. and Elhosseini, M., Deep neural network prediction of modified stepped double-slope solar still with a cotton wick and cobalt oxide nanofluid, Environ. Sci. Pollut. Res., 29(60), 90632–90655 (2022). https://doi.org/10.1007/s11356-022-21850-2
Victor, W.J.S.D., Somasundaram, D. and Gnanadason, K., Adaptive particle swarm optimization–based deep neural network for productivity enhancement of solar still, Environ. Sci. Pollut. Res., 29(17), 24802–24815 (2022). https://doi.org/10.1007/s11356-021-16840-9
Yuvaperiyasamy, M., Senthilkumar, N. and Deepanraj, B., Experimental and theoretical analysis of solar still with solar pond for enhancing the performance of seawater desalination, Water Reuse, 13(4), 620–633 (2023a). https://doi.org/10.2166/wrd.2023.102
Yuvaperiyasamy, M., Senthilkumar, N. and Deepanraj, B., Experimental investigation on the performance of a pyramid solar still for varying water depth, contaminated water temperature, and addition of circular fins, Int. J. Renew. Energy Dev., 12(6), 1123–1130 (2023). https://doi.org/10.14710/ijred.2023.57327
