Determination and Evaluation of the Pyrolysis Temperature for the Cogeneration Process in Downdraft Gasification with the Use of Artificial Neural Networks (ANN).

In the present study, the control of the pyrolysis temperature was carried out in a gasification process of eucalyptus wood, its prediction is made based on the operating parameters of the reactor to ensure the obtaining of a synthesis gas with the required quality. The results obtained from the mat...

Descripción completa

Detalles Bibliográficos
Autores: Gutierrez Gualotuña, Eduardo Roberto, Solis Cornejo, Edison, Llamatumbi Pinán, German
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:Perú
Institución:Universidad Nacional Santiago Antúnez de Mayolo
Repositorio:Revistas - Universidad Nacional Santiago Antunez de Mayolo
Idioma:español
OAI Identifier:oai:ojs.pkp.sfu.ca:article/802
Acceso en línea:http://revistas.unasam.edu.pe/index.php/Aporte_Santiaguino/article/view/802
Access Level:acceso abierto
Palabra clave:gasificación; biomasa; predicción; temperatura de pirólisis; redes neuronales.
gasification; biomass; prediction; pyrolysis temperature; neural networks.
Descripción
Sumario:In the present study, the control of the pyrolysis temperature was carried out in a gasification process of eucalyptus wood, its prediction is made based on the operating parameters of the reactor to ensure the obtaining of a synthesis gas with the required quality. The results obtained from the mathematical modeling for the prediction of the pyrolysis temperature with the use of artificial intelligence techniques and the development of artificial neural networks are shown, with experimental data of the process. For this reason, an experimental statistical design of type 3n was implemented, with two additional replications, by means of which the training of an artificial neural network capable of predicting the pyrolysis temperature in a downdraft type gasifier with cogeneration was carried out. The prediction of the pyrolysis temperature has an error of 4.6 oC and an adjustment of 93.71%, adequate values ​​for this working parameter.