Predicción del contenido de humedad en la pollinaza para estimar la producción de bioenergía a través de una red neuronal artificial

Moisture content prediction in poultry litter to estimate bioenergy production using an artificial neural network

J.O. Rico-Contreras*, A.A. Aguilar-Lasserre, J.M. Méndez-Contreras, G. Cid-Chama, G. Alor-Hernández

División de Estudios de Posgrado e Investigación, Instituto Tecnológico de Orizaba, Oriente 9 No. 852 -Col. E. Zapata CP. 94300- Orizaba, Veracruz, México. * Autor para la correspondencia. E-mail: octaviorico@hotmail.com

Resumen

En la industria avícola se identifica un área de oportunidad para la generación de bioenergía empleando la pollinaza, la cual se genera en las granjas de pollos de engorde. La pollinaza puede ser utilizada como biocombustible si se implementa la tecnología apropiada y rentable para su aprovechamiento (digestión anaeróbica, co-digestión anaeróbica o combustión directa).

El adecuado control de variables como temperatura externa, días de estancia, densidad por metro cuadrado, extractores, aspersores, sombreamiento, manejo, cobertura, forro, comedero, bebedero, ventiladores y área, mejoran la calidad de la pollinaza y en consecuencia reducen el contenido de humedad. Estas variables se emplearon para el desarrollo de una red neuronal artificial con el objeto de controlar el sistema que afecta el contenido de humedad en la pollinaza.

Los resultados de la predicción de la red neuronal artificial muestran que las variables que más impactan en el contenido de humedad de la pollinaza son manejo, número de extractores y densidad por metro cuadrado, su control contribuye para mejorar las condiciones de producción de las granjas y reducir el porcentaje de contenido de humedad inferior a 25%.

Mediante simulación Montecarlo se realizó un análisis de riesgo que incluye los resultados de la técnica de red neuronal artificial (RNA), mostrando que la mejor alternativa económica para la generación de bioenergía a partir de pollinaza es la combustión directa.

Palabras clave: bioenergía, pollinaza, poder calorífico, digestión anaeróbica, co-digestión anaeróbica, combustión directa, red neuronal artificial.

Poultry industry identifies an area of opportunity to generate bioenergy by using poultry litter. It is produced at broiler chicken farms for use it as biomassic fuel for to implement the bioenergetic technology most profitable (anaerobic digestion, anaerobic co-digestion, or direct combustion).

The adequate control variables like external temperature (°C), stay days, density per square meter, extractors, foggers, shading, handling, coverage, lining, feeder, watering, fans, area, improving quality of poultry litter and in consequently is reduced the moisture content. These variables are used for the development of artificial neural network (ANN), to control the system that affects the moisture content in the poultry litter.

The results of model artificial intelligence show that the variables that most impact the moisture content of the poultry litter are handling, number of extractors, and density per square meter, control contributes to improving conditions the production of farm and reduce the percentage moisture content of less than 25%.

By using Montecarlo Simulation, it is performed a risk analysis that includes the results of artificial neural network whose best economic alternative is the bioenergy generation through direct combustion.

Keywords: bioenergy, poultry litter, calorific value, anaerobic digestion, anaerobic co-digestion, direct combustion, artificial neural network.

DESCARGAR ARTÍCULO EN FORMATO PDF

Agradecimientos

Referencias

Alvarado-García, A. (2013). Evaluación de alternativas para el aprovechamiento benéfico de los residuos sólidos agroindustriales pollinaza y residuos agrícolas de cosecha de caña (RAC). Tesis de Maestría en Ciencias en Ingeniería Química, Instituto Tecnológico de Orizaba, México.         [ Links ]

Abelha, P., Gulyurtlu, I., Boavida, D., Seabra Barros, J., Cabrita, I., Leahy, J., Kelleher, B., Leahy, M., Henihan, A.M. (2003). Corrigendum to? Combustion of poultry litter in a fluidized bed combustor? Fuel 82, 687-692 and Fuel 83,         [ Links ] 17-18, 2439.         [ Links ]

Carr, L.E. (2002). Personal Communication. Instructor and extension specialist, Biological Resources Engineering, University of Maryland, USA.         [ Links ]

Cheginia G.R., Khazaeia J., Ghobadianb B., Goudarzic A.M. (2008). Prediction of process and product parameters in an orange juice spray dryer using artificial neural networks. Iran Journal of Food Engineering 84, 534-543.         [ Links ]

Chen, S. H., Jakeman, A. J. Norton, J. P. (2008). Artificial Intelligence techniques: An introduction to their use for modelling environmental systems. Mathematics and Computers in Simulation 78, 379-400.         [ Links ]

Collet, S. R. (2012). Nutrition and Wet litter problems in poultry. Animal Feed Science and Technology 173, 65-7.         [ Links ]

Collins, E. (2009). Poultry Litter Management and Carcass Disposal. Fact Sheet No. 10 was developed, Biological Systems Engineering Department, Virginia Tech. Worksheet No. 10 was modified by Eldridge Collins, based on material from the Arkansas Farm*A*Syst package.         [ Links ]

Dávalos, J.Z., Roux, M.V., Jiménez, P. (2002). Evaluation of poultry litter as a feasible fuel. Thermochimica Acta 394, 261-266.         [ Links ]

Díaz-González, L., Hidalgo-Dávila, C.A., Santoyo, E., y Hermosillo-Valádez, J. (2013). Evaluación de técnicas de entrenamiento de redes neuronales para estudios geotermométricos de sistemas geotérmicos. Revista Mexicana de Ingeniería Química 12, 105-120.         [ Links ]

E.P.R. (2012). Proyectos Bioenergéticos Desarrollados. Energy Power Resources.         [ Links ]

Garson, G. D. (1991). Interpreting neural-network connection weights. AI expert 6, 46-51.         [ Links ]

Ghaffari, A., Abdollahi, H., Khoshayand, M. R., Bozchalooi, I. S., Dadgar, A., Rafiee-Tehrani, M. (2006). Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. International Journal of Pharmaceutics 327, 126-138.         [ Links ]

Grimes, J.L., Carter T.A., Godwin J.L. (2006). Use of a litter material made from cotton waste, gypsum, and old newsprint for rearing broiler chickens. Poultry Science 85, 563-568.         [ Links ]

Karaj, Sh., Rehl, T., Leis, H., Muller, J. (2010). Analysis of biomass residues potential for electrical energy generation in Albania. Renewable and Sustainable Energy Reviews 14, 493-499        [ Links ]

Kelleher, B.P., Leahya, J.J., Henihana, A.M, O'Dwyera, T.F., Suttonb, D., Leahyc, M.J. (2002). Advances in poultry litter disposal technology -a review. Bioresource Technology 83, 27-36.         [ Links ]

Lee, P. G. (2000). Process control and artificial intelligence software for aquaculture. Aquacultural Engineering 23, 13-36.         [ Links ]

McKendry, P. (2002-1). Energy production from biomass (part 1): overview of biomass. Bioresource Technology 83, 37-46        [ Links ]

McKendry, P. (2002-2). Energy production from biomass (part 2): conversion technologies?. Bioresource Technology 83, 47-54.         [ Links ]

Martín, J.H., Lefcort, M.D. (2002). An analysis of the feasibility of using broiler litter as a fuel. Fuel and Energy Abstracts 43, 271.         [ Links ]

Méndez-Contreras, J.M., Rendón-Sagardi, J.A. Ruiz-Espinoza, J.E., Alvarado-Lassman, A., and Martínez-Delgadillo, S.A. (2009). Behavior of the mesophilic and thermophilic anaerobic digestion in the stabilization of municipal wastewater sludge (Part 1). Revista Mexicana de Ingeniería Química 8, 283-290.         [ Links ]

Quiroga, G., Castrillón, L., Fernández-Nava, y., Marañon, E. (2010). Physyco-chemical analysis and calorific values of poultry manure. Waste Management 30, 880-884.         [ Links ]

Ruiz-Espinoza, J.E., Méndez-Contreras, J.M., Alvarado-Lassman, A., and Martínez-Delgadillo, S.A. (2012). Effect of low temperature thermal pre-treatment on the solubilization of organic matter, pathogen inactivation and mesophilic anaerobic digestion of poultry sludge. Journal of Environmental Science and Health, Part A: Toxic/Hazardous Substances and Environmental Engineering 47, 1795-802.         [ Links ]

Sablani, S. S., Rahman, M. S. (2003). Using neural networks to predict thermal conductivity of food as a function of moisture content, temperature and apparent porosity. Food Research International 36, 617-623.         [ Links ]

Sacramento-Rivero, J.C., Romero G., Cortés-Rodríguez, E., Pech, E. y Blanco-Rosete, S. (2010) Diagnóstico del desarrollo de biorrefinerías en México. Revista Mexicana de Ingeniería Química 9, 261-283.         [ Links ]

Saidur, R., Abdelaziza, E.A., Demirbas, A., Hossaina, M.S., Mekhilef S. (2011). A review on biomass as a fuel for boilers. Renewable and Sustainable Energy Reviews 15, 2262-2289.         [ Links ]

Serment-Moreno, V., Mujica-Paz, H.,Torres, J.A. and Welti-Chanes, J. (2012). Montecarlo simulation of orange juice pectinmethylesterase (PME) inactivation by combined processes of high hydrostatic Pressure (HHP) and temperature. Revista Mexicana de Ingeniería Química 11, 363-372.         [ Links ]

Serio, M. A. (2003). Pyrolysis processing of animal manure to produce fuel gases. Fuel and Energy Abstracts 44, 232-233        [ Links ]

Sondreal, E.A. Benson, S.A. Hurley, J.P. Mann, M.D. Pavlish, J.H. Swanson, M.L. Weber, G.F., Zygarlicke, C.J., (2001). Review of Advances in combustion Technology and biomass cofiring. Fuel Processing Technology 71, 7-38.         [ Links ]

Taylor, G. (2008). Bioenergy for heat and electricity in the UK: A research atlas and roadmap. Energy Policy 36, 4383-4389.         [ Links ]

UNFCCC. (2012). Clean development mechanism (CMD). United Nations Framework Convention on Climate Change (UNFCCC).         [ Links ]

Whitely, N., Ozao, R., Arriaga, R., C.Yan., Wei-Ping P.(2006). Multi-utilization of chicken litter as biomass source. Part 1: Combustion. Energy & Fuels 20, 2660-2665.         [ Links ]

Zhu S., S. Lee S., Hargrove S.K. y Chen G. (2007). Prediction of combustion efficiency of chicken litter using an artificial neural network approach. Fuel 86, 877-886.         [ Links ]