Application of an Artificial Neural Network for Moisture Transfer Prediction Considering Shrinkage during Drying of Foodstuffs

Hernández-Pérez, José Alfredo; Alvarado, Miguel Angel Garcia; Trystram, Gilles; Heyd, B.

doi:10.1201/9781420006261.ch12

Cited by 3 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this idea, some research in transport phenomena has been done by applying artificial neural networks (ANN). ANN enables direct modeling of nonlinear processes without requiring a prespecified detailed relationship, as could be the relationship of D eff and the variables studied in a specific mass transport process Examples of the ANN application are the works of Ramesh, Kumar, and Rao (1996) (rehydration of dried rice), Balasubramanian, Panda, and Rao (1996) (drying in fluidized bed), Baroni, Menezes, Adell, and Ribeiro (2003) (modeling cheese salting), and Hernández-Pérez, García- Alvarado, Trystam, and Heyd (2003) (drying with shrinkage of mango and cassava)…”

Section: Application Of Artificial Neural Network In Mass Transfermentioning

confidence: 99%

Transport phenomena in food engineering: basic concepts and advances

Welti‐Chanes

Vergara-Balderas

Bermúdez‐Aguirre

2005

Journal of Food Engineering

View full text Add to dashboard Cite

Section: Application Of Artificial Neural Network In Mass Transfermentioning

confidence: 99%

Transport phenomena in food engineering: basic concepts and advances

Welti‐Chanes

Vergara-Balderas

Bermúdez‐Aguirre

2005

Journal of Food Engineering

View full text Add to dashboard Cite

“…Therefore, the effective models for evaluating the effect of process parameters, optimizing of the drying process, energy integration, and control are necessary (Kumar, Karim, & Joardder, ). The development of mathematical and numerical models to describe the drying processes has been the topic of many research studies for several decades (Hernandez‐Perez, Garcia‐Alvarado, Trystram, & Heyd, ). In the mathematical models, some assumptions are obvious to develop (Kumar et al, ) and numerical models require deep knowledge of the process mechanism, estimation of many experimental parameters and application of advanced calculation methods.…”

Section: Introductionmentioning

confidence: 99%

Drying kinetic and artificial neural network modeling of mushroom drying process in microwave‐hot air dryer

Amin

Behroozi‐Khazaei

Sharifian

2018

J Food Process Engineering

View full text Add to dashboard Cite

Modeling of moisture content variation under variable microwave power in microwave‐hot air dryer is challenging. In this study, one static and one dynamic of ANN were investigated for modeling of whole mushroom drying process. The experiments were done in three levels of hot air temperature (23, 50, and 70 °C), three levels of microwave power density (MPD) (1.5, 2, and 2.5 W/g) and two statuses of microwave power during drying process (constant and variable). The results demonstrated that the two distinct falling rate periods were observed at low MPD with any air temperatures and power density status. The lowest specific energy consumption was found in 23 °C and 2.5 fixed MPD and lowest color deterioration found in 70 °C and 1.5 fixed MPD. The results also showed the 3–6–7–1 structure of dynamic model with 0.2179 RMSE and 0.9914 R values had better results than other structures and would be very suitable in a predictive control system for drying control. Practical applications Volumetric and high efficiency heating are the primary benefit of microwave drying and lot of industries and producers interest to use it. Also, modeling of drying kinetics and evaluating of product quality in each drying method provide valuable information to improve their drawbacks and recommend it for industry. Application of microwave technology in dehydration of mushroom can result in significant improvement in quality and energy consumption. On the other hand investigating a robust ANN model for predicting the moisture content helps to better prediction and control of microwave‐hot air dryer in industrial scale.

show abstract

“…[15] Currently, researchers are investigating how to improve performance of NN due to incorporation of additional predictors. Hernandez-Perez et al [16] showed that shrinkage and air humidity were the most important predictors of moisture content in drying of cassava and mango. Torrecilla et al [17] introduced pressure as an important predictor of drying.…”

Section: Intelligent Computation Of Moisture Content In Shrinkable Bimentioning

confidence: 99%

“…[13][14][15][16][17][18] One of the first applications of NN to drying was a predictive model of moisture content on the basis of three predictors: drying time, air temperature, and air velocity. [13] This three-layer NN was able to manage with nonlinearity, implicitly incorporated in deterministic models.…”

Section: Intelligent Computation Of Moisture Content In Shrinkable Bimentioning

confidence: 99%

Intelligent Computation of Moisture Content in Shrinkable Biomaterials

2007

View full text Add to dashboard Cite

A technique of intelligent computation of moisture content in shrinkable biomaterials from multiple predictors was developed. All measurable predictors were structured in three sets: biomaterial properties (volume, density, porosity, diffusivity); drying conditions (time, air temperature, humidity, velocity, pressure); and drying technologies. Two typical drying models were considered: timedependent (thermodynamical) and time-independent (relational). The relationship between predictors and moisture content was established on the basis of multi-factorial linear regression (MLR) and neural networks (NN). Accuracy of statistical approximation was strongly dependent on drying model and chosen set of predictors. Time-independent models demonstrated better accuracy (MSE ¼ 0.214) than time-dependent models (MSE ¼ 0.254). Redundant predictors did not affect the accuracy and generalization ability of statistical models.Results of NN training and testing showed superior accuracy with respect to statistical models. NN worked perfectly well for any combination of non-correlated predictors, improving accuracy to MSE ¼ 0.01. Elimination of redundant predictors further improved accuracy and generalization ability of NN models.The performance of both models was tested for drying of ginseng roots in the range of temperatures from 38 to 50 C, sizes from 10 to 32 mm, and relative humidity from 12 to 40%. Due to the high accuracy and computational efficiency, NN can be used as online estimator of moisture content in drying process.

show abstract

Application of an Artificial Neural Network for Moisture Transfer Prediction Considering Shrinkage during Drying of Foodstuffs

Cited by 3 publications

References 1 publication

Transport phenomena in food engineering: basic concepts and advances

Transport phenomena in food engineering: basic concepts and advances

Drying kinetic and artificial neural network modeling of mushroom drying process in microwave‐hot air dryer

Intelligent Computation of Moisture Content in Shrinkable Biomaterials

Contact Info

Product

Resources

About