Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model

Mohammed Shadi S. Abujazar, Fatihah Suja`, Ibrahim Anwar Ibrahim, A. E. Kabeel, Suraya Sharil

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

This paper presents a cascaded forward neural network model for predicting the productivity of a developed inclined stepped solar still system. The actual recorded data of the developed inclined stepped solar still system is used to develop the proposed model. The results of the predicted productivity are compared with that obtained from regression and linear models. In this study, three statistical error terms are used to evaluate the proposed model: root mean square error (RMSE), mean absolute percentage error (MAPE) and mean bias error (MBE). The results show that the proposedcascaded forward neural network (CFNN) model more accurately predicts the productivity of the system than the other modelsmentioned. The RMSE, MAPE and MBE values of the proposed model are 22.48%, 18.51% and −26.46%, respectively. Therefore, the CFNN model provides benefits for modelling the solar still.

Original languageEnglish
Pages (from-to)147-159
Number of pages13
JournalJournal of Cleaner Production
Volume170
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Solar system
solar system
Productivity
Neural networks
productivity
modeling
Mean square error
Network model
Modeling

Keywords

  • ANN
  • Modelling
  • Performance evaluation
  • Prediction
  • Productivity
  • Solar desalination
  • Solar still

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Environmental Science(all)
  • Strategy and Management
  • Industrial and Manufacturing Engineering

Cite this

Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model. / Abujazar, Mohammed Shadi S.; Suja`, Fatihah; Ibrahim, Ibrahim Anwar; Kabeel, A. E.; Sharil, Suraya.

In: Journal of Cleaner Production, Vol. 170, 01.01.2018, p. 147-159.

Research output: Contribution to journalArticle

@article{af17df4c2a8842388ca00ec536e9f09f,
title = "Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model",
abstract = "This paper presents a cascaded forward neural network model for predicting the productivity of a developed inclined stepped solar still system. The actual recorded data of the developed inclined stepped solar still system is used to develop the proposed model. The results of the predicted productivity are compared with that obtained from regression and linear models. In this study, three statistical error terms are used to evaluate the proposed model: root mean square error (RMSE), mean absolute percentage error (MAPE) and mean bias error (MBE). The results show that the proposedcascaded forward neural network (CFNN) model more accurately predicts the productivity of the system than the other modelsmentioned. The RMSE, MAPE and MBE values of the proposed model are 22.48{\%}, 18.51{\%} and −26.46{\%}, respectively. Therefore, the CFNN model provides benefits for modelling the solar still.",
keywords = "ANN, Modelling, Performance evaluation, Prediction, Productivity, Solar desalination, Solar still",
author = "Abujazar, {Mohammed Shadi S.} and Fatihah Suja` and Ibrahim, {Ibrahim Anwar} and Kabeel, {A. E.} and Suraya Sharil",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.jclepro.2017.09.092",
language = "English",
volume = "170",
pages = "147--159",
journal = "Journal of Cleaner Production",
issn = "0959-6526",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Productivity modelling of a developed inclined stepped solar still system based on actual performance and using a cascaded forward neural network model

AU - Abujazar, Mohammed Shadi S.

AU - Suja`, Fatihah

AU - Ibrahim, Ibrahim Anwar

AU - Kabeel, A. E.

AU - Sharil, Suraya

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper presents a cascaded forward neural network model for predicting the productivity of a developed inclined stepped solar still system. The actual recorded data of the developed inclined stepped solar still system is used to develop the proposed model. The results of the predicted productivity are compared with that obtained from regression and linear models. In this study, three statistical error terms are used to evaluate the proposed model: root mean square error (RMSE), mean absolute percentage error (MAPE) and mean bias error (MBE). The results show that the proposedcascaded forward neural network (CFNN) model more accurately predicts the productivity of the system than the other modelsmentioned. The RMSE, MAPE and MBE values of the proposed model are 22.48%, 18.51% and −26.46%, respectively. Therefore, the CFNN model provides benefits for modelling the solar still.

AB - This paper presents a cascaded forward neural network model for predicting the productivity of a developed inclined stepped solar still system. The actual recorded data of the developed inclined stepped solar still system is used to develop the proposed model. The results of the predicted productivity are compared with that obtained from regression and linear models. In this study, three statistical error terms are used to evaluate the proposed model: root mean square error (RMSE), mean absolute percentage error (MAPE) and mean bias error (MBE). The results show that the proposedcascaded forward neural network (CFNN) model more accurately predicts the productivity of the system than the other modelsmentioned. The RMSE, MAPE and MBE values of the proposed model are 22.48%, 18.51% and −26.46%, respectively. Therefore, the CFNN model provides benefits for modelling the solar still.

KW - ANN

KW - Modelling

KW - Performance evaluation

KW - Prediction

KW - Productivity

KW - Solar desalination

KW - Solar still

UR - http://www.scopus.com/inward/record.url?scp=85031932663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031932663&partnerID=8YFLogxK

U2 - 10.1016/j.jclepro.2017.09.092

DO - 10.1016/j.jclepro.2017.09.092

M3 - Article

AN - SCOPUS:85031932663

VL - 170

SP - 147

EP - 159

JO - Journal of Cleaner Production

JF - Journal of Cleaner Production

SN - 0959-6526

ER -