Neural networks for the heat and mass transfer prediction during drying of cassava and mango

Hernández-Pérez, José Alfredo; Garcı́a-Alvarado, M.A.; Trystram, Gilles; Heyd, B.

doi:10.1016/j.ifset.2003.10.004

Cited by 131 publications

(78 citation statements)

References 21 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The R results are very similar to those in the references consulted, which range from 0.90 to 0.99 in the training process (Myhara et al, 1998;Hernández-Pérez et al, 2004;Peng et al, 2007;Diamantopoulou, 2005;Avramidis and Iliadis, 2005a).…”

Section: Resultssupporting

confidence: 82%

“…For the network a feedforward multilayer percepton was used, trained by means of the backpropagation algorithm, one of the most commonly used algorithms in the references consulted (Krauss et al, 1997;Drake and Packianather, 1998;Myhara and Sablani, 2001;Panchariya et al, 2002;Nordmark, 2002;Avramidis and Iliadis, 2005a;Hernández-Pérez et al, 2004;Diamantopoulou, 2005;Singh et al, 2007;Peng et al, 2007).…”

Section: Methodsmentioning

confidence: 99%

“…The transfer function used was a variant of the hyperbolic tangent (Myhara and Sablani, 2001;Hernández-Pérez et al, 2004;Diamantopoulou, 2005), more specifically the hyperbolic tangent sigmoid transfer function (tansig) (Krauss et al, 1997;Demuth et al, 2002) [Eq. 7], which achieves the output much faster and is mathematically equivalent, improving the functioning of the network (Demuth et al, 2002).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model

Fernández¹,

Esteban²,

Palacios³

et al. 2008

For. syst.

View full text Add to dashboard Cite

The physical properties (specific gravity, moisture content, thickness swelling and water absorption) and mechanical properties (internal bond strength, bending strength and modulus of elasticity) were determined on 93 Spanish-manufactured standard particleboards of different thicknesses selected randomly at the end of the production process. The testing methods of the corresponding European standards (EN) were used, except in the case of the thickness swelling and absorption tests, for which the Spanish UNE standard was used. The thickness and the values obtained for the physical properties were entered into an artificial neural network in order to predict the mechanical properties of the board. The fit was compared with the usual multivariate regression models. The use of a neural network made it possible to obtain the values of bending strength, modulus of elasticity and internal bond strength of the boards utilizing the known data, not only of thickness, moisture content and specific gravity, but also of thickness swelling and water absorption. The neural network proposed is much better adapted to the observed values than any of the multivariate regression models obtained.Key words: wood-based panels, physico-mechanical properties, ANN, regression fit, predictive model. ResumenPredicción de propiedades mecánicas del tablero de partículas estándar mediante una red neuronal artificial y comparación con un modelo de regresión multivariante Se han determinado las propiedades físicas (densidad, humedad, hinchazón en espesor y absorción de agua) y mecánicas (tracción perpendicular a las caras, resistencia a flexión y módulo de elasticidad) de 93 tableros de partículas estándar de diferentes espesores, de fabricación española, elegidos aleatoriamente a la salida del proceso de producción, utilizando los métodos de ensayo recogidos en las normas EN correspondientes, excepto en los ensayos de hinchazón y absorción que se ha utilizado norma UNE (española). El espesor y los valores obtenidos de las propiedades físicas han sido introducidos en una red neuronal artificial (RNA) para predecir las propiedades mecánicas del tablero. El ajuste se ha comparado con los habituales modelos de regresión multivariante. La utilización de una red neuronal ha permitido obtener los valores de resistencia a flexión, módulo de elasticidad y resistencia a la tracción perpendicular a las caras de los tableros de partículas a través de los datos conocidos, no sólo de espesor, humedad y densidad sino también de hinchazón en espesor y absorción de agua. La red neuronal propuesta tiene una adecuación a los valores experimentales muy superior a cualquiera de los modelos de regresión multivariante obtenidos.Palabras clave: tableros derivados de la madera, propiedades físico-mecánicas, RNA, ajuste por regresión, modelo predictivo.

show abstract

Section: Resultssupporting

confidence: 82%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model

Fernández¹,

Esteban²,

Palacios³

et al. 2008

For. syst.

View full text Add to dashboard Cite

show abstract

“…A predictive model for heat and mass transfer using ANN was proposed in order to obtain on-line predictions of temperature and moisture kinetics during the drying of mango [27]. The model takes into account shrinkage of the product as a function of moisture content.…”

Section: S Mangomentioning

confidence: 99%

Artificial Neural Networks in Fruits: A Comprehensive Review

Goyal¹

2014

IJIGSP

View full text Add to dashboard Cite

Abstract-This review discusses the application of artificial neural networks (ANN) modeling in fruits. It covers all fruits in which ANN modeling has been applied. ANN is quite a new and easy computational modeling approach used for prediction, which has become popular and accepted by food industry, researchers, scientists and students. ANNs have been applied in almost every field of science and technology, viz., speech synthesis & recognition, pattern classification, adaptive interfaces between humans & complex physical systems, clustering, function approximation, image data compression, non-linear system modeling, associative memory, combinatorial optimization, control and several others, as they have proved valuable tools for obtaining the required output. ANN provides an exciting alternative method for solving a variety of problems in different areas of science and engineering. The aim of this communication is to discover the recent advances of ANN technology implemented in fruits, and discuss the critical role that ANN plays in predictive modelling.

show abstract

“…This phenomenon has been modeled with different levels of complexity. ANNs permit an adequate and precise prediction of the drying process in industrial applications and have been extensively studied by many researchers (Raisul Islam et al 2003;Hernandez-Perez et al 2004;Martynenko and Yang 2006;Kerdpiboon et al 2006;Erenturk and Erenturk 2007;Liu et al 2007;Ochoa-Martinez and Ayala-Aponte 2007;Ceylan and Aktas 2008;Lertworasirikul and Tipsuwan 2008;Youssefi et al 2009;Shafafi Zenoozian and Devahastin 2009;Omid et al 2009;Topuz 2010).…”

Section: Introductionmentioning

confidence: 99%

Prediction of carrot cubes drying kinetics during fluidized bed drying by artificial neural network

2010

View full text Add to dashboard Cite

This article presents static and recurrent artificial neural networks (ANNs) to predict the drying kinetics of carrot cubes during fluidized bed drying. Experiments were performed on square−cubed carrot with dimensions of 4, 7 and 10 mm, air temperatures of 50, 60 and 70°C and bed depths of 3, 6 and 9 cm. Initially, static ANN was used to correlate the outputs (moisture ratio and drying rate) to the four exogenous inputs (drying time, drying air temperature, carrot cubes size, and bed depth). In the recurrent ANNs, in addition to the four exogenous inputs, two state input and output (moisture ratio or drying rate) were applied. A number of hidden neurons and training epoch were investigated in this study. The dying kinetics was predicted with R 2 values of greater than 0.94 and 0.96 using static and recurrent ANNs, receptively.

show abstract

Neural networks for the heat and mass transfer prediction during drying of cassava and mango

Cited by 131 publications

References 21 publications

Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model

Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model

Artificial Neural Networks in Fruits: A Comprehensive Review

Prediction of carrot cubes drying kinetics during fluidized bed drying by artificial neural network

Contact Info

Product

Resources

About