Opin vísindi

Artificial neural network integrated with thermodynamic equilibrium modeling of downdraft biomass gasification-power production plant

Artificial neural network integrated with thermodynamic equilibrium modeling of downdraft biomass gasification-power production plant


Title: Artificial neural network integrated with thermodynamic equilibrium modeling of downdraft biomass gasification-power production plant
Author: Safarian, Sahar   orcid.org/0000-0002-0409-007X
Ebrahimi Saryazdi, Seyed Mohammad
Unnthorsson, Runar   orcid.org/0000-0002-1960-0263
Richter, Christiaan   orcid.org/0000-0002-6563-4923
Date: 2020-12
Language: English
Scope: 118800
University/Institute: Háskóli Íslands
University of Iceland
School: Verkfræði- og náttúruvísindasvið (HÍ)
School of Engineering and Natural Sciences (UI)
Department: Iðnaðarverkfræði-, vélaverkfræði- og tölvunarfræðideild (HÍ)
Faculty of Industrial Eng., Mechanical Eng. and Computer Science (UI)
Series: Energy;213
ISSN: 0360-5442
DOI: https://doi.org/10.1016/j.energy.2020.118800
Subject: Biomass gasification; Artificial neural network; Power production; Downdraft; Simulation; Lífmassi; Lífrænn úrgangur; Tauganet; Líkön; Orkugjafar
URI: https://hdl.handle.net/20.500.11815/2084

Show full item record

Citation:

Safarian, S., Ebrahimi Saryazdi, S. M., Unnthorsson, R., & Richter, C. (2020). Artificial neural network integrated with thermodynamic equilibrium modeling of downdraft biomass gasification-power production plant. Energy, 213, 118800. doi:https://doi.org/10.1016/j.energy.2020.118800

Abstract:

This study is a novel attempt in developing of an Artificial neural network (ANN) model integrated with a thermodynamic equilibrium approach for downdraft biomass gasification integrated power generation unit. The objective of the study is to predict the net output power from the systems derived from various kinds of biomass feedstocks under atmospheric pressure and various operating conditions. The input parameters used in the models are elemental analysis compositions (C, O, H, N and S), proximate analysis compositions (moisture, ash, volatile material and fixed carbon) and operating parameters (gasifier temperature and air to fuel ratio). The architecture of the model consisted of one input, one hidden and one output layer. 1032 simulated data from 86 different types of biomasses in various operating conditions were used to train the ANN. The developed ANN shows agreement with simulated data with absolute fraction of variance (R2) higher than 0.999 in the case of product power. Moreover, the relative influence of biomass characteristics and some specific operating parameters on output power are determined. Finally, to have a more detailed assessment, the variations of all input variables with respect to carbon content are compared and analyzed together. The suggested integrated ANN based model can be applied as a very useful tool for optimization and control of the process through the downdraft biomass gasification integrated with power generation unit.

Description:

Post-print (lokagerð höfundar)

Rights:

CC BY-NC-ND

Files in this item

This item appears in the following Collection(s)