An integrated framework of data-driven, metaheuristic, and mechanistic modeling approach for biomass pyrolysis

Zahid Ullah; Muzammil Khan; Salman Raza Naqvi; Muhammad Nouman Aslam Khan; Wasif Farooq; Muhammad Waqas Anjum; Muhammad Waqas Yaqub; Hamad AlMohamadi; Fares Almomani

doi:10.1016/j.psep.2022.04.013

An integrated framework of data-driven, metaheuristic, and mechanistic modeling approach for biomass pyrolysis

Zahid Ullah, Muzammil Khan, Salman Raza Naqvi^*, Muhammad Nouman Aslam Khan, Wasif Farooq, Muhammad Waqas Anjum, Muhammad Waqas Yaqub, Hamad AlMohamadi, Fares Almomani

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

This study presents an integrated hybrid framework of data-driven (cascade forward neural network (CFNN)), metaheuristic (artificial bee colony (ABC)), and a mechanistic modeling (Aspen simulation) approach for the biomass pyrolysis process for bio-oil production. We applied CFNN and an ABC to predict and optimize bio-oil yield. The CFNN model achieved high prediction performance with a correlation coefficient value of 0.95 and a root mean squared error value of 0.39. Furthermore, the CFNN-ABC derived optimum parameters were then validated using a mechanistic model of the pyrolysis process. The CFNN and Aspen simulation results were following the experimental results, with an average deviation of 5%. The feature importance showed that the internal information about biomass was more relevant than external factors for bio-oil yield. The partial dependence plots were developed to know the insights into the biomass pyrolysis process. This study presents a modeling and simulation platform for bio-oil production that can increase the waste-to-energy process and can be helpful for academia.

Original language	English
Pages (from-to)	337-345
Number of pages	9
Journal	Process Safety and Environmental Protection
Volume	162
DOIs	https://doi.org/10.1016/j.psep.2022.04.013
State	Published - Jun 2022

Bibliographical note

Funding Information:
The corresponding author would like to acknowledge Pakistan Science Foundation (grant number: PSF/CRP/C-NUST/T-Helix (47) ) for financial support and National University of Sciences & Technology for technical support.

Publisher Copyright:
© 2022 The Institution of Chemical Engineers

Keywords

Artificial bee colony
Aspen plus
Bioenergy
Biomass
Cascade neural network
Machine learning

ASJC Scopus subject areas

Environmental Engineering
Environmental Chemistry
Chemical Engineering (all)
Safety, Risk, Reliability and Quality

Access to Document

10.1016/j.psep.2022.04.013

Cite this

@article{3cd9236156ac4c6ba8797dd1b8c9aad3,

title = "An integrated framework of data-driven, metaheuristic, and mechanistic modeling approach for biomass pyrolysis",

abstract = "This study presents an integrated hybrid framework of data-driven (cascade forward neural network (CFNN)), metaheuristic (artificial bee colony (ABC)), and a mechanistic modeling (Aspen simulation) approach for the biomass pyrolysis process for bio-oil production. We applied CFNN and an ABC to predict and optimize bio-oil yield. The CFNN model achieved high prediction performance with a correlation coefficient value of 0.95 and a root mean squared error value of 0.39. Furthermore, the CFNN-ABC derived optimum parameters were then validated using a mechanistic model of the pyrolysis process. The CFNN and Aspen simulation results were following the experimental results, with an average deviation of 5%. The feature importance showed that the internal information about biomass was more relevant than external factors for bio-oil yield. The partial dependence plots were developed to know the insights into the biomass pyrolysis process. This study presents a modeling and simulation platform for bio-oil production that can increase the waste-to-energy process and can be helpful for academia.",

keywords = "Artificial bee colony, Aspen plus, Bioenergy, Biomass, Cascade neural network, Machine learning",

author = "Zahid Ullah and Muzammil Khan and Naqvi, {Salman Raza} and Khan, {Muhammad Nouman Aslam} and Wasif Farooq and Anjum, {Muhammad Waqas} and Yaqub, {Muhammad Waqas} and Hamad AlMohamadi and Fares Almomani",

note = "Funding Information: The corresponding author would like to acknowledge Pakistan Science Foundation (grant number: PSF/CRP/C-NUST/T-Helix (47) ) for financial support and National University of Sciences & Technology for technical support. Publisher Copyright: {\textcopyright} 2022 The Institution of Chemical Engineers",

year = "2022",

month = jun,

doi = "10.1016/j.psep.2022.04.013",

language = "English",

volume = "162",

pages = "337--345",

journal = "Process Safety and Environmental Protection",

issn = "0957-5820",

publisher = "Institution of Chemical Engineers",

}

TY - JOUR

T1 - An integrated framework of data-driven, metaheuristic, and mechanistic modeling approach for biomass pyrolysis

AU - Ullah, Zahid

AU - Khan, Muzammil

AU - Naqvi, Salman Raza

AU - Khan, Muhammad Nouman Aslam

AU - Farooq, Wasif

AU - Anjum, Muhammad Waqas

AU - Yaqub, Muhammad Waqas

AU - AlMohamadi, Hamad

AU - Almomani, Fares

N1 - Funding Information: The corresponding author would like to acknowledge Pakistan Science Foundation (grant number: PSF/CRP/C-NUST/T-Helix (47) ) for financial support and National University of Sciences & Technology for technical support. Publisher Copyright: © 2022 The Institution of Chemical Engineers

PY - 2022/6

Y1 - 2022/6

N2 - This study presents an integrated hybrid framework of data-driven (cascade forward neural network (CFNN)), metaheuristic (artificial bee colony (ABC)), and a mechanistic modeling (Aspen simulation) approach for the biomass pyrolysis process for bio-oil production. We applied CFNN and an ABC to predict and optimize bio-oil yield. The CFNN model achieved high prediction performance with a correlation coefficient value of 0.95 and a root mean squared error value of 0.39. Furthermore, the CFNN-ABC derived optimum parameters were then validated using a mechanistic model of the pyrolysis process. The CFNN and Aspen simulation results were following the experimental results, with an average deviation of 5%. The feature importance showed that the internal information about biomass was more relevant than external factors for bio-oil yield. The partial dependence plots were developed to know the insights into the biomass pyrolysis process. This study presents a modeling and simulation platform for bio-oil production that can increase the waste-to-energy process and can be helpful for academia.

AB - This study presents an integrated hybrid framework of data-driven (cascade forward neural network (CFNN)), metaheuristic (artificial bee colony (ABC)), and a mechanistic modeling (Aspen simulation) approach for the biomass pyrolysis process for bio-oil production. We applied CFNN and an ABC to predict and optimize bio-oil yield. The CFNN model achieved high prediction performance with a correlation coefficient value of 0.95 and a root mean squared error value of 0.39. Furthermore, the CFNN-ABC derived optimum parameters were then validated using a mechanistic model of the pyrolysis process. The CFNN and Aspen simulation results were following the experimental results, with an average deviation of 5%. The feature importance showed that the internal information about biomass was more relevant than external factors for bio-oil yield. The partial dependence plots were developed to know the insights into the biomass pyrolysis process. This study presents a modeling and simulation platform for bio-oil production that can increase the waste-to-energy process and can be helpful for academia.

KW - Artificial bee colony

KW - Aspen plus

KW - Bioenergy

KW - Biomass

KW - Cascade neural network

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85128319138&partnerID=8YFLogxK

U2 - 10.1016/j.psep.2022.04.013

DO - 10.1016/j.psep.2022.04.013

M3 - Article

AN - SCOPUS:85128319138

SN - 0957-5820

VL - 162

SP - 337

EP - 345

JO - Process Safety and Environmental Protection

JF - Process Safety and Environmental Protection

ER -

An integrated framework of data-driven, metaheuristic, and mechanistic modeling approach for biomass pyrolysis

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this