Artificial neural network techniques to predict the moisture ratio content during hot air drying and vacuum drying of Radix isatidis extract

Background:To predict the moisture ratio of Radix isatidis extract during drying.Methods:Artificial neural networks were designed using the MATLAB neural network toolbox to produce a moisture ratio prediction model of Radix isatidis extract during hot air drying and vacuum drying,where regression values and mean squared error were used as evaluation indexes to optimize the number of hidden layer nodes and determine the topological structure of artificial neural networks model.In addition,the drying curves for the different drying parameters were analyzed.Results:The optimal topological structure of the moisture ratio prediction model for hot air drying and vacuum drying of Radix isatidis extract were“4-9-1”and“5-9-1”respectively,and the regression values between the predicted value and the experimental value is close to 1.This indicates that it has a high prediction accuracy.The moisture ratio gradually decreases with an increase in the drying time,reducing the loading,initial moisture content,increasing the temperature,and pressure can shorten the drying time and improve the drying efficiency.Conclusion:Artificial neural networks technology has the advantages of rapid and accurate prediction,and can provide a theoretical basis and technical support for online prediction during the drying process of the extract.

A valid evaluation method for UPLC fingerprint analysis and moisture ratio prediction model:application to microwave vacuum drying of Radix isatidis extract

Background:Drying is a necessary component of traditional Chinese medicine extracts.The heating principle of microwave vacuum drying is different from that of the conventional heat method.However,at present,there is paucity of information on the drying process of traditional Chinese medicine extract by microwave vacuum drying,and the results of such process are unclear.Methods:To study the dynamic changes in the chemical characteristics of microwave vacuum drying under different drying conditions,ultrahigh-performance liquid chromatography fingerprint profiles were established using Radix isatidis extract as a model drug and analyzed using similarity analysis,partial least squares-discriminant analysis,and semi-quantitative analysis.In addition,a backpropagation artificial neural network model was developed to predict the moisture ratio of the drying process.Results:Qualitative results showed that the similarity between different drying conditions was greater than 0.95,and 2 amino acid components(peaks 5 and 6)affected by process fluctuations were screened out.The quantitative results showed that the mass concentration of component 1 fluctuated after drying,while that of component 2 increased.The optimal backpropagation artificial neural network model structure used to predict the moisture ratio was 5-4-1,with regression and mean squared error values of 0.996 and 0.0003,respectively,after training,which were well fitted and had a strong approximation ability.Conclusion:Upon comparison of fingerprints and the evaluation of statistical methods,common components of Radix isatidis extract had little variation under different drying conditions,and the selected components provided a reference for the establishment of process evaluation indexes.The establishment of backpropagation artificial neural network provides a theoretical basis for the application of microwave vacuum drying technology and online monitoring of moisture ratio.

Modeling and optimization for prediction of moisture content,drying rates and moisture ratio

There were needs to develop some preservation technique to enhance the shelf life of Paneer because it is highly perishable in nature at ambient conditions.Drying can be one of the methods to increase shelf life of paneer.This study was undertaken to dry 1.5 cm3 paneer at 62,72 and 82℃temperatures and 10,14 and 18 kPa absolute pressures with superheated steam.Moisture content,drying rate and moisture ratio data were generated by conducting the experiments in low pressure superheated steam dryer.These data were used to develop Artificial Neural Network(ANN)models.Optimized ANN models were developed for rapid and more accurate prediction of moisture content with two hidden layers and seven nurons having R20.9991,drying rate with two hidden layers and nine nurons having R20.9846 and moisture ratio with two hidden layers and seven nurons having R20.9991 in drying,based on two hidden layers and one to nine neurons in each hidden layer.Measured values of moisture content,drying rate and moisture ratio were predicted with an R^(2)>0.98.System equation has been developed to predict moisture content,drying rate and moisture ratio at any given conditions.

Determination of Natural Logarithm of Diffusion Coefficient and Activation Energy of Thin Layer Drying Process of Ginger Rhizome Slices

This study is an extension of the previous work done with ARS-680 Environmental Chamber. Drying is a complex operation that demands much energy and time. Drying is essentially important for preservation of ginger rhizome. Drying of ginger was modeled, and then the effective diffusion coefficient and activation energy were determined. For this purpose, the experiments were done at six levels of varied temperatures: 10°C, 20°C, 30°C, 40°C, 50°C and 60°C. The values of effective diffusion coefficients obtained in this work for the variously treated ginger rhizomes closely agreed with the average effective diffusion coefficients of other notable authors who determined the drying kinetics and convective heat transfer coefficients of ginger slices.

Drying characteristics,kinetics model and effective moisture diffusivity of vacuum far-infrared dried Rehmanniae

Vacuum far-infrared radiation(VFIR)drying has recently received many attentions because of its effective and successful applications in drying some agricultural products.The VFIR drying of Radix Rehmanniae was conducted and Weibull distribution function was applied to fit the drying kinetics in this study.The results showed that the increase of radiation heater temperature and the decrease of chamber pressure could reduce drying time obviously.Compared with single diffusion equation,Weibull distribution function had higher precision to fit the drying curves of VFIR drying of Rehmanniae.The effective moisture diffusivity(Deff)increased with the increase of heater temperature and the decrease of pressure.Scanning electron telescope(SEM)analysis showed that more porous surface could be observed after VFIR drying,which is beneficial to enhance moisture diffusivity and drying rate as well.

Analyzing drying characteristics and modeling of thin layers of peppermint leaves under hot-air and infrared treatments

The drying kinetics of peppermint leaves was studied to determine the best drying method for them.Two drying methods include hot-air and infrared techniques,were employed.Three different temperatures(30,40,50℃)and air velocities(0.5,1,1.5 m/s)were selected for the hot-air drying process.Three levels of infrared intensity(1500,3000,4500 W/m^2),emitter-sample distance(10,15,20 cm)and air speed(0.5,1,1.5 m/s)were used for the infrared drying technique.According to the results,drying had a falling rate over time.Drying kinetics of peppermint leaves was explained and compared using three mathematical models.To determine coefficients of these models,non-linear regression analysis was used.The models were evaluated in terms of reduced chi-square(χ^2),root mean square error(RMSE)and coefficient of determination(R^2)values of experimental and predicted moisture ratios.Statistical analyses indicated that the model with the best fitness in explaining the drying behavior of peppermint samples was the Logarithmic model for hot-air drying and Midilli model for infrared drying.Moisture transfer in peppermint leaves was also described using Fick’s diffusion model.The lowest effective moisture diffusivity(1.096×10^-11m^2/s)occurred during hot-air drying at 30℃ using 0.5 m/s,whereas its highest value(5.928×10^-11m^2/s)belonged to infrared drying using 4500 W/m^2 infrared intensity,0.5 m/s airflow velocity and 10 cm emitter-sample distance.The activation energy for infrared and hot-air drying were ranged from 0.206 to 0.439 W/g,and from 21.476 to 27.784 kJ/mol,respectively.

Color changes and drying kinetics modeling of basil seed mucilage during infrared drying process

The physicochemical properties and color of dried seed mucilage (gums) depend on thecondition and method of drying. So, in this study, the effects of infrared (IR) dryer systemparameters such as IR power (150, 250, and 375 W), distance of mucilage from lamp surface(4, 8, and 12 cm), mucilage thickness (0.5, 1.0, and 1.5 cm) on drying kinetics and colorindexes (L*a*b*) of basil seed mucilage (BSM) were examined in an IR dryer system. IR dry-ing kinetic of BSM was modeled using mathematical approach. Thus, experimental mois-ture ratio data were fitted to 8 various empirical models. It was found that Page model hasthe best fit to show the kinetic behavior and acceptably described the IR drying behavior ofBSM with the highest correlation coefficient values and the lowest standard error values.The average effective moisture diffusivity (Deff) increased from 1.69×10^(-9)to 9.21×10^(-9)m^(2)/s with increasing lamp power from 150 W to 375 W, while it was decreased from7.93×10^(-9)to 2.65×10^(-9)m^(2)/s and 7.81×10^(-9)to 1.82×10^(-9)m^(2)/s with increasing the dis-tance of mucilage from 4 to 12 cm and the reduction of mucilage thickness from 1.5 to0.5 cm, respectively. The increasing in IR radiation power has a positive influence on thelightness (increasing L* index) of dried BSM and it reduced color changes index (DE) from13.04 to 11.51. The results showed that IR drying method has great industrial potential insaving processing time as well as energy with better maintenance of color and quality ofdried BSM.

Investigation of the structural changes of cocoa bean (with and without seed coat) during convective drying

The influence of seed coat on the behaviour of heterogeneous structure of cocoa bean(frosteros sp.)during convective drying with tempering period was investigated in an isothermal condition.It was found that the removal rate of moisture and air diffusion between the cocoa kernel and seed coat is not the same especially at the temperature of 55℃and initial drying time for all temperatures used.When the drying temperature increased to 70℃and 81℃,the cocoa kernel and the seed coat shrinks simultaneously,indicating that the rate of moisture and air removal from the kernel through the seed coat are the same.Change in sphericity of the bean was more pronounced at the temperature of 55℃for the seeds with seed coat while for all other drying conditions it remains fairly constant after one-hour drying.