Artificial neural network for prediction of dielectric properties relevant to microwave processing of fruit juice

Abstract

Dielectric properties are fundamental parameters to determine the heating behavior of food products using microwaves. Determining and modeling these properties as a function of process conditions and product composition is required to be implemented in Multiphysics modeling, in which heat transfer and electromagnetic aspects are solved, allowing the characterizing and optimization of microwave processing. This work evaluates the dielectric properties of model fruit juice solutions at concentrations ranging from 5 to 65°Brix. Measurements were carried out at frequencies between 200 and 3,000 MHz in the temperature range of 20–80 °C. The results show that the dielectric properties are non‐linearly influenced by temperature, frequency and sugar content. A comparison between the dielectric properties of model solutions and of real juices was performed, and similarities were found. Furthermore, based on Artificial Neural Networks, the modeling and prediction of the dielectric properties at different conditions were achieved. Practical applications In search of food processes that cause a minimum damage to the original organoleptic characteristics of the product, the use of microwaves is considered as a promising alternative to conventional thermal treatment. Microwave heating can offer rapid volumetric heating, shorter processing time, and lower surface temperature, resulting in better sensorial and nutritional qualities. Knowledge of dielectric properties is fundamental to study the response of the food material to the electromagnetic field and to determine the heating pattern. The need for dielectric properties data is even more evident during microwave process development and optimization using Multiphysics modeling. Therefore, the results presented in this work can be useful for further studies involving the design of microwave processing of fruit juices.

Effect of temperature and moisture contents on dielectric properties at 2.45 GHz of fruit and vegetable processing by-products

“…According to other studies, sugar could not be detected in the chemical analysis of SCG as it is commonly extracted through the coffee brewing process. 24,25 However, the sugar content was found to be the most signicant component to model dielectric properties in products such as grapes or juices; 26,27 thus, the absence of it in SCG could diminish the dielectric constant values.…”

Dielectric Properties of Foods

“…For an appropriate and uniform pasteurization process, it is crucial selecting of frequency ranges. In previous studies, it was revealed that dielectric constants of liquid foods decreased as frequency and temperature increased (Nelson and Trabelsi, 2012;Siguemoto and Gut, 2016;Franco et al, 2017;Kubo et al, 2018;Gonzalez-Monroy et al, 2018;Sobreiro et al, 2018;Kumar and Shrivasta, 2019). The effects of applied frequency and temperature on loss factor values, may vary (Table 7).…”

“…Moreover, the sugar content of liquid foods is another important factor in dielectric properties. It was indicated that as Brix increases, although dielectric constant and penetration depth decrease, loss factor increases (Siguemoto and Gut, 2016;Franco et al, 2017;Kubo et al, 2018;Sobreiro et al, 2018;Kumar and Shrivasta, 2019).…”

Procédés de chauffage par micro-ondes : approches expérimentales et numériques des interactions avec les produits alimentaires

“…Dans ce cas, la dégradation de l'énergie de l'onde électromagnétique en chaleur est due à la conductivité électrique des ions présents dans les matrices. A l'inverse, à la fréquence de 2450 MHz, les mécanismes lies à la rotation dipolaire des molécules sont majoritaires (Kubo et al, 2018a).…”