Modelado y predicción basados en redes neuronales del rendimiento de ácido acético en la fermentación de Gluconobacter oxydans utilizando aguas residuales lácteas
DOI:
https://doi.org/10.24054/limentech.v23i2.4359Palabras clave:
Red neuronal artificial (RNA), Gluconobacter oxydans, Ácido acético, Fermentación, Modelado de bioprocesosResumen
El ácido acético (AA) es un valioso bioproducto con amplias aplicaciones industriales en los sectores alimentario, farmacéutico y químico. En este estudio, se empleó Gluconobacter oxydans para la producción de ácido acético utilizando un medio modificado con un 12 % de aguas residuales lácteas como sustrato rentable. Se evaluaron los efectos de la concentración de glucosa, el tiempo de incubación y la temperatura en la producción de ácido acético, y el proceso se modeló mediante una red neuronal artificial (RNA) basada en una arquitectura de perceptrón multicapa (MLP) (estructura 3-2-1). El rendimiento experimental de ácido acético osciló entre 1,01 y 4,68 g/100 mL, valores consistentes con los reportados en la literatura para sistemas de fermentación biológica. El modelo de RNA logró bajos errores de predicción (SSE = 0,756 y 0,187 para entrenamiento y prueba, respectivamente) y demostró una gran capacidad de generalización sin sobreajuste. Los análisis de peso de conexión e importancia relativa revelaron que el tiempo de incubación y la temperatura fueron las variables más influyentes en el rendimiento, mientras que la concentración de glucosa tuvo un efecto secundario. Estos hallazgos confirman la idoneidad de las redes neuronales artificiales (RNA) como herramienta computacional fiable para modelar y optimizar bioprocesos no lineales. La integración de técnicas de aprendizaje automático con la fermentación microbiana puede mejorar la comprensión del proceso y respaldar el desarrollo de estrategias sostenibles de producción de ácido acético a partir de subproductos industriales.
Descargas
Referencias
Agatonovic-Kustrin, S., & Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of Pharmaceutical and Biomedical Analysis, 22(6), 717–727. https://doi.org/10.1016/S0731-7085(99)00272-1
Ameer, K., Bae, S. W., Jo, Y., Lee, H. G., Ameer, A., & Kwon, J. H. (2017). Optimization of microwave-assisted extraction of total extract, stevioside and rebaudioside-A from Stevia rebaudiana (Bertoni) leaves using response surface methodology (RSM) and artificial neural network (ANN) modelling. Food Chemistry, 229, 198–207. https://doi.org/10.1016/j.foodchem.2017.01.121
Arias Palma, G.; Moreano Terán, N.; Silva Paredes, J. (2021). Use of whey in industry. @limentech, Food Science and Technology, 19(1), 36–54. https://doi.org/10.24054/limentech.v19i1.1409
Chai, X., He, D., Li, Y., Niu, D., Xie, T., & Zhao, Y. (2016). A kind of method utilizing changing food waste fermentative production acetic acid. CN103865975B.
Chen, Y., Bai, Y., Li, D., Wang, C., Xu, N., & Hu, Y. (2016). Screening and characterization of ethanol-tolerant and thermotolerant acetic acid bacteria from Chinese vinegar Pei. World Journal of Microbiology and Biotechnology, 32(7), 1–9. https://doi.org/10.1007/s11274-015-1961-8
Cheok, C. Y., Chin, N. L., Yusof, Y. A., Talib, R. A., & Law, C. L. (2012). Optimization of total phenolic content extracted from Garcinia mangostana Linn. hull using response surface methodology versus artificial neural network. Industrial Crops and Products, 40(1), 247–253. https://doi.org/10.1016/j.indcrop.2012.03.019
Cheryan, M., Parekh, S., Shah, M., & Witjitra, K. (1997). Production of acetic acid by Clostridium thermoaceticum. Advances in Applied Microbiology, 43, 1–33. https://doi.org/10.1016/S0065-2164(08)70221-1
Eltawil, M. A., Mohammed, M., & Alqahtani, N. M. (2023). Developing machine learning-based intelligent control system for performance optimization of solar PV-powered refrigerators. Sustainability, 15(8), 6911. https://doi.org/10.3390/su15086911
Es-Sbata, I., Castro, R., Carmona, Y., Zouhair, R., & Durán, E. (2022). Influence of different bacterial inocula and temperature levels on the chemical composition and antioxidant activity of prickly pear vinegar produced by surface culture. Foods, 11(3), 303–323. https://doi.org/10.3390/foods11030303
Fasolo, D., Pippi, B., Meirelles, G., Zorzi, G., Fuentefria, A. M., Poser, G., & Teixeira, H. F. (2020). Topical delivery of antifungal Brazilian red propolis benzophenones-rich extract by means of cationic lipid nanoemulsions optimized by Box–Behnken design. Journal of Drug Delivery Science and Technology, 56, 101573. https://doi.org/10.1016/j.jddst.2020.101573
Fronteras, J. P., Dacera, D. D., Bello, D. D., & Santos, K. J. L. D. (2021). Utilization of pesticide-free Citrus microcarpa and Mangifera indica peels for the production of acetic acid with potential industrial application. Bioresource Technology Reports, 15, 100806. https://doi.org/10.1016/j.biteb.2021.100806
Gong, Y., Hu, Y., Li, D., Liu, Z., Qi, Y., Shi, Y., Bin, T., Wang, A., Wang, C., Wu, Q., & Xu, N. (2019). Immobilized acetic acid fermentation method for improving acetic acid-producing capability of acetic acid bacteria. CN109182399A.
Gullo, M., Caggia, C., De Vero, L., & Giudici, P. (2006). Characterization of acetic acid bacteria in traditional balsamic vinegar. International Journal of Food Microbiology, 106(2), 209–212. https://doi.org/10.1016/j.ijfoodmicro.2005.06.024
Iida, A. (2013). Gene associated with foam formation of acetic acid bacterium, acetic acid bacterium bred by modifying the gene and method for producing vinegar using the acetic acid bacterium. U.S. Patent 8,389,265.
Ishtiaq, M., Tariq, H. M. R., Reddy, D. Y. C., Kang, S.-G., & Reddy, N. G. S. (2025). Prediction of creep rupture life of 5Cr-0.5Mo steel using machine learning models. Metals, 15(2), 288. https://doi.org/10.3390/met15020288
Ishtiaq, M., Tiwari, S., Panigrahi, B. B., Seol, J. B., & Reddy, N. S. (2024). Neural network-based modeling of the interplay between composition, service temperature, and thermal conductivity in steels for engineering applications. International Journal of Thermophysics, 45, 137. https://doi.org/10.1007/s10765-024-03308-y
Joung, K. C. (2019). Onion vinegar and its preparation method. KR20190007329A.
Kalck, P., Le Berre, C., & Serp, P. (2020). Recent advances in the methanol carbonylation reaction into acetic acid. Coordination Chemistry Reviews, 402, 213078. https://doi.org/10.1016/j.ccr.2019.213078
Lu, S. F., Lee, F. L., & Chen, H. K. (2000). Thermotolerant and high acetic acid-producing Acetobacter bacterium. U.S. Patent 6,096,528.
Otero-Pérez, Tahíz C.; Mantilla-Escalante, Diana; Manjarrez-Machacón, Oscar D.; Carrascal, Juan J. (2024). Optimization of the Traditional and Bioactive Properties of Bee Pollen: A Comprehensive Review of Fermentation Processes. (2024). @limentech Magazine, Food Science and Technology. Print ISSN 1692-7125 -Electronic ISSN 2711-3035. Volume 22 No. 2. Pp: 257–280. https://doi.org/10.24054/limentech.v22i2.3656
Pal, P., & Nayak, J. (2016). Acetic acid production and purification: Critical review towards process intensification. Separation & Purification Reviews, 46(1), 44–61. https://doi.org/10.1080/15422119.2016.1185017
Pérez-Gomariz, M., López-Gómez, A., & Cerdán-Cartagena, F. (2023). Artificial neural networks as artificial intelligence technique for energy saving in refrigeration systems—a review. Clean Technologies, 5(1), 116–136. https://doi.org/10.3390/cleantechnol5010007
Ripley, B. D. (2007). Pattern recognition and neural networks. Cambridge University Press.
Sharafi, S. M., Rasooli, I., & Beheshti-Maal, K. (2010). Isolation, characterization, and optimization of indigenous acetic acid bacteria and evaluation of their preservation methods. Iranian Journal of Microbiology, 2(1), 38–45. https://pubmed.ncbi.nlm.nih.gov/22347549/
Tarón-Dunoyer, Arnulfo; Barros-Portnoy, Israel; Mercado-Camargo, Jairo. (2022). Characterization of fatty acids and total phenols with antioxidant activity in peach seeds (Prunus persica). @limentech Journal, Food Science and Technology. Print ISSN 1692-7125 - Electronic ISSN 2711-3035. Volume 20 No. 1. Pp: 77–91. https://doi.org/10.24054/limentech.v20i1.1667
Upadhyay, A., Kovalev, A., Zhuravleva, E., Pareek, N., & Vivekanand, V. (2023). Enhanced production of acetic acid through bioprocess optimization employing response surface methodology and artificial neural network. Bioresource Technology, 376, 128930. https://doi.org/10.1016/j.biortech.2023.128930
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2025 Revista @Limentech Ciencia y Tecnología Alimentaria
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
