An enhanced productivity prediction model of active solar still using artificial neural network and Harris Hawks optimizer. (April 2020)

• Record Type: Journal Article
• Authors: Essa, F.A.; Abd Elaziz, Mohamed; Elsheikh, Ammar H.
• Is Part Of: Applied thermal engineering. Volume 170(2020)
• Publication Date: 2020-04
• Subjects: Solar still -- Artificial neural network -- Desalination -- Solar still condenser -- Productivity optimization; ANN Artificial neural network -- COV Coefficient of variance -- CRM Coefficient of residual mass -- EC Efficiency coefficient -- FFNNs Feedforward neural networks -- HHO Harris Hawks optimizer -- MAE Mean absolute error -- MLP Multilayer perceptron -- MRE Mean relative error -- OI Overall index of model performance -- R Regression -- R2 Coefficient of determination -- RMSE Root mean square error -- SVM Support vector machine; Heat engineering -- Periodicals; Heating -- Equipment and supplies -- Periodicals; Periodicals; 621.40205
• DOI: 10.1016/j.applthermaleng.2020.115020
• Languages: English
• ISSNs: 1359-4311

Abstract

Graphical abstract: Highlights: Performance of passive still, active still, and condenser is studied. Distilling systems are modeled by different artificial intelligence-based models. Accumulated productivity of active still is improved by 53.21%. Artificial neural network unified with Harris Hawks optimizer is the best model. In the best model, R 2 is 0.97 and 0.98 for active and passive stills, respectively. Abstract: In this paper, a new productivity prediction model of active solar still was developed depending on improving the performance of the traditional artificial neural networks using Harris Hawks Optimizer. This optimizer simulates the behavior of Harris Hawks to catch their prey, and this method is used to determine the optimal parameters of artificial neural networks. The proposed model, called Harris Hawks Optimizer – artificial neural network, is compared with two other models named support vector machine and traditional artificial neural network, in addition to the experimental-based behavior of the solar still. The models were applied to predict the yield of three different distillation systems, namely, passive solar still, active solar still, and active solar still integrated with a condenser. Experimentally, the productivity of the active distiller integrated with the condenser was increased by 53.21% at a fan speed of 1350 rpm. The performance of the models was assessed using different statistical criteria such as root mean square error, coefficient of determination, and others. Among the three models, Harris Hawks Optimizer – artificial neural network had the best accuracy in predicting the solar still yield compared with the real experimental results.