TY - JOUR
T1 - Artificial neural network simulation of the condenser of seawater greenhouse in Oman
AU - Al-Ismaili, Abdulrahim M.
AU - Ramli, Nasser Mohamed
AU - Azlan Hussain, Mohd
AU - Rahman, M. Shafiur
N1 - Publisher Copyright:
© 2019, © 2019 Taylor & Francis Group, LLC.
PY - 2019
Y1 - 2019
N2 - The prediction of freshwater production from the condenser of an agricultural seawater greenhouse is important for designing the greenhouse process. Two models, namely, Artificial Neural Network and multilinear regression (denoted as ANN and RA, respectively), were developed and tested to predict the freshwater production rate considering ambient solar intensity, condenser inlet moist-air temperature, humidity ratio and mass flowrate, and inlet coolant temperature. Statistical analysis indicated that all parameters significantly affected the prediction (p < 0.05). The accuracy of the ANN and RA models was then compared to two models previously developed by Yetilmezsoy and Abdul-Wahab and Al-Ismaili et al. (denoted as Yetilmezsoy model and Al-Ismaili model, respectively). The ANN model showed the best prediction when seven statistical criteria were considered. The Pearson correlations for ANN, RA, Yetilmezsoy, and Al-Ismaili models were observed as 1.00, 0.98, 0.88, and 0.96, respectively, while mean absolute percentage errors (MAPE) were 17.84, 79.72, 63.24, and 80.50%, respectively. Hence it could be recommended to use ANN model for the prediction of freshwater production rate, however other three simple models could also be used with lower accuracy in the cases of unavailability of the ANN model.
AB - The prediction of freshwater production from the condenser of an agricultural seawater greenhouse is important for designing the greenhouse process. Two models, namely, Artificial Neural Network and multilinear regression (denoted as ANN and RA, respectively), were developed and tested to predict the freshwater production rate considering ambient solar intensity, condenser inlet moist-air temperature, humidity ratio and mass flowrate, and inlet coolant temperature. Statistical analysis indicated that all parameters significantly affected the prediction (p < 0.05). The accuracy of the ANN and RA models was then compared to two models previously developed by Yetilmezsoy and Abdul-Wahab and Al-Ismaili et al. (denoted as Yetilmezsoy model and Al-Ismaili model, respectively). The ANN model showed the best prediction when seven statistical criteria were considered. The Pearson correlations for ANN, RA, Yetilmezsoy, and Al-Ismaili models were observed as 1.00, 0.98, 0.88, and 0.96, respectively, while mean absolute percentage errors (MAPE) were 17.84, 79.72, 63.24, and 80.50%, respectively. Hence it could be recommended to use ANN model for the prediction of freshwater production rate, however other three simple models could also be used with lower accuracy in the cases of unavailability of the ANN model.
KW - Artificial Neural Network
KW - Condenser
KW - Regression analysis
KW - Seawater greenhouse
UR - http://www.scopus.com/inward/record.url?scp=85064008302&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064008302&partnerID=8YFLogxK
U2 - 10.1080/00986445.2018.1539710
DO - 10.1080/00986445.2018.1539710
M3 - Article
AN - SCOPUS:85064008302
SN - 0098-6445
VL - 206
SP - 967
EP - 985
JO - Chemical Engineering Communications
JF - Chemical Engineering Communications
IS - 8
ER -