Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models

Biomass solid waste (BSW) generation in Malaysia is rapidly increasing as a result of nation’s industrialization, urbanization, and population growth. Thermochemical conversion of BSW to produce energy is not straightforward due to fuel’s high moisture content, low heating value, and poor grindabili...

Full description

Bibliographic Details
Main Authors: Bagheri, Milad, Ibrahim, Zelina Zaiton, Abd Manaf, Latifah, Akhir, Mohd Fadzil, Wan Talaat, Wan Izatul Asma
Format: Article
Published: UKM Press 2022
Online Access:http://psasir.upm.edu.my/id/eprint/103200/
_version_ 1848863959712530432
author Bagheri, Milad
Ibrahim, Zelina Zaiton
Abd Manaf, Latifah
Akhir, Mohd Fadzil
Wan Talaat, Wan Izatul Asma
author_facet Bagheri, Milad
Ibrahim, Zelina Zaiton
Abd Manaf, Latifah
Akhir, Mohd Fadzil
Wan Talaat, Wan Izatul Asma
author_sort Bagheri, Milad
building UPM Institutional Repository
collection Online Access
description Biomass solid waste (BSW) generation in Malaysia is rapidly increasing as a result of nation’s industrialization, urbanization, and population growth. Thermochemical conversion of BSW to produce energy is not straightforward due to fuel’s high moisture content, low heating value, and poor grindability. Accessing different combinatorial scheme of BSW may help to mitigate above-mentioned issues while maintaining attractively high energy outputs. In this work, calorific values and ultimate analyses of a wide variety of BSW reported in literature were compiled. Based on the collected data, two empirical correlations to predict high heating value (HHV) of BSW were developed using a multiple regression method. The developed correlations were (i) HHV = 908.37C + 2942.94H + 4439.73S + 518.92O − 63558.52(municipal solid waste) and (ii) HHV = 382.62C − 368.16H + 2788.24S − 37.83O + 926.26(biomass/biochar) where, C, H, O, N, and S represent biomass content in a form of elemental carbon, hydrogen, oxygen, nitrogen, and sulfur, respectively. The accuracies of the correlations were verified by comparing the predicted values with those experimentally determined. Thermogravimetric analysis was used to analyze BSW combustion behavior and retrieve important combustion parameters. The best-fit correlations obtained in this work had R2 values of 0.98 (MAPE of 3.2%) and 0.92 (MAPE of 7.1%) for municipal solid waste and biomass/biochar samples, respectively. Moreover, the correlations were fairly accurate in predicting HHV of different BSW combination with prediction error of less than 15%. The correlations developed in this work could be instrumental for a precise determination of different combination of solid biomass.
first_indexed 2025-11-15T13:41:12Z
format Article
id upm-103200
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T13:41:12Z
publishDate 2022
publisher UKM Press
recordtype eprints
repository_type Digital Repository
spelling upm-1032002023-11-23T04:28:04Z http://psasir.upm.edu.my/id/eprint/103200/ Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models Bagheri, Milad Ibrahim, Zelina Zaiton Abd Manaf, Latifah Akhir, Mohd Fadzil Wan Talaat, Wan Izatul Asma Biomass solid waste (BSW) generation in Malaysia is rapidly increasing as a result of nation’s industrialization, urbanization, and population growth. Thermochemical conversion of BSW to produce energy is not straightforward due to fuel’s high moisture content, low heating value, and poor grindability. Accessing different combinatorial scheme of BSW may help to mitigate above-mentioned issues while maintaining attractively high energy outputs. In this work, calorific values and ultimate analyses of a wide variety of BSW reported in literature were compiled. Based on the collected data, two empirical correlations to predict high heating value (HHV) of BSW were developed using a multiple regression method. The developed correlations were (i) HHV = 908.37C + 2942.94H + 4439.73S + 518.92O − 63558.52(municipal solid waste) and (ii) HHV = 382.62C − 368.16H + 2788.24S − 37.83O + 926.26(biomass/biochar) where, C, H, O, N, and S represent biomass content in a form of elemental carbon, hydrogen, oxygen, nitrogen, and sulfur, respectively. The accuracies of the correlations were verified by comparing the predicted values with those experimentally determined. Thermogravimetric analysis was used to analyze BSW combustion behavior and retrieve important combustion parameters. The best-fit correlations obtained in this work had R2 values of 0.98 (MAPE of 3.2%) and 0.92 (MAPE of 7.1%) for municipal solid waste and biomass/biochar samples, respectively. Moreover, the correlations were fairly accurate in predicting HHV of different BSW combination with prediction error of less than 15%. The correlations developed in this work could be instrumental for a precise determination of different combination of solid biomass. UKM Press 2022 Article PeerReviewed Bagheri, Milad and Ibrahim, Zelina Zaiton and Abd Manaf, Latifah and Akhir, Mohd Fadzil and Wan Talaat, Wan Izatul Asma (2022) Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models. Sains Malaysiana, 51 (7). 2003 - 2012. ISSN 0126-6039 https://www.ukm.my/jsm/english_journals/vol51num7_2022/contentsVol51num7_2022.html 10.17576/jsm-2022-5107-05
spellingShingle Bagheri, Milad
Ibrahim, Zelina Zaiton
Abd Manaf, Latifah
Akhir, Mohd Fadzil
Wan Talaat, Wan Izatul Asma
Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title_full Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title_fullStr Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title_full_unstemmed Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title_short Simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
title_sort simulation and analysis of sea-level change from tide gauge station by using artificial neural network models
url http://psasir.upm.edu.my/id/eprint/103200/
http://psasir.upm.edu.my/id/eprint/103200/
http://psasir.upm.edu.my/id/eprint/103200/