A study to predict pyrolytic behaviors of refuse-derived fuel (RDF): Artificial neural network application

Özge Çepelioğullar*, İlhan Mutlu, Serdar Yaman, Hanzade Haykiri-Acma

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

59 Citations (Scopus)

Abstract

The present study demonstrates the thermal behaviors of refuse-derived fuel (RDF), a highly-heterogeneous fuel, at high temperature region by bringing experimental and modelling studies together. In the first part, RDF was pyrolyzed in thermal analyzer from room temperature to 900 °C at varying heating rates as well as the evolved gas analysis was monitored by using TG-FTIR-MS. Afterwards, obtained data was used to develop an artificial neural network (ANN) model that can predict thermal behaviors of RDF at a new heating rate without performing any experiments. The temperature and heating rate were selected as input parameters while temperature dependent weight loss was selected as output parameter. The effects of parameters such as neuron number, training number, and the transfer function type on the network performance were investigated in detail to optimize network topology. Optimization studies showed that the best performance was achieved with ANN that had 7-6 neurons trained 25 times with tansig-logsig non-linear function combination. Prediction performance of the optimized ANN was tested by introducing a new experimental dataset. The good agreement between experimental and predicted values revealed that ANN can be a promising tool in pyrolytic behaviors estimation of even heterogeneous fuels such as RDF.

Original languageEnglish
Pages (from-to)84-94
Number of pages11
JournalJournal of Analytical and Applied Pyrolysis
Volume122
DOIs
Publication statusPublished - 1 Nov 2016

Bibliographical note

Publisher Copyright:
© 2016 Elsevier B.V.

Funding

The authors would like to thank The Scientific and Technological Research Council of Turkey for their financial support (TUBITAK 214M403 ) and Istanbul Technical University (ITU)-Scientific Research Project (BAP 39180 ). In addition, Kubilay Atalay, for his valuable contributions to this work, and the assistance of ISTAÇ Co. Compost and Recovery Plant for the provision of RDF as raw material as well as Anadolu University-Carbonaceous Materials Processing Group for their kind assistance in TG-FTIR-MS studies are also acknowledged gratefully by the authors.

FundersFunder number
Scientific Research ProjectBAP 39180
TUBITAK214M403
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu
Istanbul Teknik Üniversitesi

    Keywords

    • Artificial neural network (ANN)
    • Characterization
    • Prediction
    • Pyrolysis
    • RDF
    • TGA

    Fingerprint

    Dive into the research topics of 'A study to predict pyrolytic behaviors of refuse-derived fuel (RDF): Artificial neural network application'. Together they form a unique fingerprint.

    Cite this