Artificial neural network and mathematical modeling comparative analysis of nonisothermal diffusion of moisture in wood

The objective of this study was to develop an optimum artificial neural network (ANN) capable of predicting the direction and magnitude of the moisture flux through wood under nonisothermal steady-state diffusion. A comparison between experimental measurements and the predicted values of three mathematical models reported in the literature and of the proposed neural network is presented and discussed. When developing the ANN model, several configurations were evaluated. The optimal ANN model was found to be a network with six neurons in one hidden layer. This well-trained network correlated the forecasted to the experimental data with low-level errors compared to previously developed models and also predicted the flux-reversal phenomenon thus confirming that ANN modeling has a much better predictive performance. It was also shown that the numbers of the training data were linked to the performance of the network during estimation. However, the powerful predictive capacity of this modeling method was still supported although a limited experimental data set was trained.     

超声作用对葡萄汁膜过滤工艺的影响

将超声波技术应用于葡萄汁的超滤膜过滤过程,研究了超滤膜孔径、跨膜压力、超声功率、超声频率等因素对超滤膜通量的影响,结果表明:采用200目滤布的板框过滤使后续的超滤过滤有较大的膜通量.超声波作用下,适宜的葡萄汁超滤膜工艺参数为:跨膜压力0.25 MPa、膜滤温度50℃、超声功率200W和频率40kHz.同无超声波作用相比...     

Developing a hybrid artificial neural network-genetic algorithm model to predict resilient modulus of polypropylene/polyester fiber-reinforced asphalt concrete

Up to now various kinds of fibers are used to improve the hot mix asphalt (HMA) performance, but a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, in this paper, the resilient modulus of the modified HMA samples using polypropylene and polyester fibers (hybrid and single modes) was evaluated and modeled by regression method and artificial neural network (ANN). As ANN includes different parameters such as the number of neurons in hidden layer influenced on the prediction accuracy, genetic algorithm (GA) was used to optimize the ANN parameters. Also, GA parameters were optimized using the trial and error method such as the population size. The obtained results indicated that the optimized ANN with two hidden layers and two neurons in each hidden layer can predict the resilient modulus of fiber-reinforced HMA with high accuracy (correlation coefficient: .96).     

Modeling Thermal Conductivity of Iranian Flat Bread Using Artificial Neural Networks

The objective of this work was to develop Artificial Neural Network (ANN) based thermal conductivity (K) prediction model for Iranian flat breads. Experimental data needed for ANN models were obtained from a pilot-scale set-up. Breads were made from three different cultivars of wheat and were baked in an eclectic oven at three different baking temperatures (232°C, 249°C and 260°C). A data set of 205 conditions was used for developing ANN and empirical models. To model K using ANN, 16 different MLP (multilayer perceptron) configurations ranging from one to two hidden layers of neurons were investigated and their prediction performances were evaluated. The (4-3-5-1)-MLP network, that is a network having two hidden layers, with three neurons in its first hidden layer and five neurons in its second hidden layer, had the best results in predicting the thermal conductivity of flat bread. For this network, R², MRE, MAE and SE were 0.988, 0.6323, 1.66×10^{? 3}, and 8.56×10^?4, respectively. Overall, ANN models (with R² ≥ 0.95) performed superior than the empirical model (with R² = 0. 870).     

Assessing performance of skim milk ultrafiltration by using technical parameters

In the present study a mathematical model has been applied to interpret the permeate flux decay that occurs during the process of concentrating skim milk by ultrafiltration using a commercial membrane module. The effects on membrane fouling of two operational variables, temperature and transmembrane pressure, have been studied using technical parameters. An energy analysis has demonstrated that the major energy consumption takes place in the thermal process and not in the mechanical pumping of the fluid. In addition, higher increments in permeate volume can be achieved by increasing transmembrane pressure, not temperature. The mathematical analysis presented here permits the evaluation of optimum values of the engineering parameters necessary to design and operate skim milk ultrafiltration units.     

Modeling of acrylamide formation and browning ratio in potato chips by artificial neural network

The artificial neural network (ANN) modeling approach was used to predict acrylamide formation and browning ratio (%) in potato chips as influenced by time x temperature covariants. A series of feed-forward type network models with back-propagation training algorithm were developed. Among various network configurations, 4-5-3-2 configuration was found as the best performing network topology. Four neurons in the input layer were reflecting the asparagine concentration, glucose concentration, frying temperature, and frying time. The output layer had two neurons representing acrylamide concentration and browning ratio of potato chips. The ANN modeling approach was shown to successfully predict acrylamide concentration (R = 0.992) and browning ratio (R = 0.997) of potato chips during frying at different temperatures in time-dependent manner for potatoes having different concentrations of asparagine and glucose. It was concluded that ANN modeling is a useful predictive tool which considers only the input and output variables rather than the complex chemistry.     

Hollow Fiber Ultrafiltration of Maple Sap: A Performance Study

In an attempt to develop new products from maple sap, membrane technology was used to fractionate and concentrate macromolecular components (10,000 daltons or larger). Permeate fluxes increased with transmembrane pressure, reaching a maximum at 190–200 kPa, at 8–10°C. The flux profiles were similar to those of protein solutions and fruit juices. This method of clarification was successfully applied to obtain a clear “cold sterilized” sap. Application of ultrafiltration to maple farms or industries are discussed.     

Membrane processing of fruit juices and beverages: a review

Membrane technology for the processing of fruit juices and beverages has been applied mainly for clarification using ultrafiltration and microfiltration, and for concentration using reverse osmosis. The effects of product preparation, membrane selection, and operating parameters are important factors influencing filtration rate and product quality. Technological advances related to the development of new membranes, improvement in process engineering, and better understanding of fruit beverage constituents have expanded the range of membrane separation processes. Developments in novel membrane processes, including electrodialysis and pervaporation, increased the array of applications in combination with other technologies for alternate uses in fruit juices and beverages.     

Prediction of mass transfer kinetics during osmotic dehydration of apples using neural networks

An artificial neural network (ANN) model was developed for the prediction of water loss (WL) and solid gain (SG) in osmotic dehydration of apple cylinders using a wide variety of data from the literature to make it more general. This model mathematically correlates six processing variables (temperature and concentration of osmotic solution, immersion time, surface area, solution to fruit mass ratio and agitation level) with WL and SG. The optimal ANN consisted of one hidden layer with four neurons. This model was able to predict WL and SG in a wide range of processing variables with a mean square error of 13.9 and 4.4, and regression coefficient of 0.96 and 0.89, respectively, in testing step. This ANN model performs better when compared to linear multi-variable regression. The wide range of processing variables considered for the formulation of this model, and its easy implementation in a spreadsheet using a set of equations, make it very useful and practical for process design and control.     

Modular Feed Forward Networks to Predict Sugar Diffusivity from Date Pulp Part I. Model Validation

In Tunisia, some 15,000 tons of fructose could be produced annually from second quality dates presently being left to rot. Extraction is the first step in producing sugar from these dates, and sugar diffusivity from the date paste governs the process. The objective of this project was therefore to measure in the laboratory, the sugar diffusivity of three date varieties (Manakher, Lemsi, and Alligue) under three different temperatures (50, 65 and 80°C), and from this data, develop an artificial neural network (ANN) model to predict sugar extraction. For each date variety, the laboratory procedure consisted of soaking a layer of date paste in water at one of the three temperatures and observing water sugar concentration at 20 mm from the date layer, every 15 min over a period of 240 min. This experimental data was then used to develop the ANN model, where several configurations were evaluated. Date sugar concentration with time was found to be significantly influenced by temperature and variety. The Lemsi variety allowed for the highest sugar extraction of 75% at 80°C. The optimal ANN model was found to be a network with two hidden layers and seven neurones in both the upper and lower levels of each hidden layers. This optimal model was capable of predicting sugar diffusivity from the different date varieties with a mean square error of 0.0037 and an 8.0% Error. The results show very good agreement between the predicted and the desired values of sugar diffusivity (R² = 0.98). The coefficient of determination was also very good (R² > 0.95), due to a small prediction error.     

超滤法澄清西番莲果汁的研究

以寻求提高西番莲原汁超滤时的渗透通量为目的，用国产芳香聚酰胺膜平板超滤器进行试验，对超滤操作条件，果汁预处理，膜的清洗进行研究。结果表明，西番莲原汁超滤时渗透通量最高的操作压力为0．15MPa，最佳进料速度为22mL/s，操作温度为室温；原汁经海藻酸钠—碳酸钠澄清剂预处理后可以明显增大渗透通量；超滤处理后。原汁的西番莲固有滋味和品质得到较好保留。采用超滤澄清法生产高质量的西番莲原汁是可行的。     

Effect of Ultrafiltration on Anthocyanin and Flavonol Content of Black Currant Juice (Ribes nigrum L.)

This paper evaluates the efficiency of ultrafiltration and the effects of processing on the total anthocyanin and flavonol contents of black currant juice at chosen operational conditions. Ultrafiltration of black currant juices was carried out using Biomax 100?kDa polyethersulfone membrane. Ultrafiltration was used to process the juice prior concentration by reverse osmosis; with the aim to enhance the efficiency of the concentration process in terms of permeate flux. To avoid the fouling of the membrane, the juices were depectinized with Panzym Super E liquid enzyme preparation. The ultrafiltration was carried out at a transmembrane pressure of 2?bars and the operating temperature of 25?°C. The effect of processing on the valuable anthocyanin and flavonol content of the juices was evaluated based on the results of high-performance liquid chromatography analyses. The article includes detailed analyses of anthocyanin and flavonol compounds of the enzyme treated and ultrafiltered juice as compared with the original juice. The results indicate that, due to the enzymatic treatment, the valuable compound content of the juice increases. However, the ultrafiltration process resulted in a significant loss of a valuable content; 54% of total flavonol and 50% of total anthocyanins maintained in ultrafiltered juice when compared to the feed samples.     

水酶法提取红花籽油的工艺优化及其抗氧化性研究

本文旨在寻找有效建模方法以预测亚临界CO₂萃取红花籽油的萃取率,优化其萃取工艺条件。以单因素实验为基础,采用Box-Behnken试验设计,研究了萃取压力、分离温度、萃取时间对红花籽油萃取率的影响,并采用响应面法（RSM）和人工神经网络（ANN）两种方法分别对同一实验进行建模分析,通过RSM数值优化、人工神经网络和遗传算法结合（ANN-GA)两种方法优化其工艺条件。结果表明,RSM与ANN两种模型均能较为精准预测,但通过两种模型的决定系数（R²）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）、均方根误差（RMSE）值比较,得出ANN模型（R²=0.9966）的预测效果较优于RSM模型（R²=0.9950）。ANN-GA确定的最佳萃取条件及萃取率分别为：萃取压力19.04 MPa、分离温度55.50 ℃、萃取时间134.98 min、萃取率23.52%。综上,RSM和ANN两种方法均可用于亚临界CO₂萃取带壳红花籽油的建模与优化,但ANN的预测准确度及拟合能力更为优秀。

     

Prediction of yarn crimp in PES multifilament woven barrier fabrics using artificial neural network

This research was aimed to develop artificial neural network (ANN) models to predict yarn crimp in woven barrier fabrics. For ANN training, 52 polyester (PES) multifilament barrier fabrics were produced by varying weft yarn and filament fineness, yarn type, weft density, weave type, and loom parameters. The supervised training of neural network was performed using Matlab® ANN toolbox function ‘trainbr’ which is the incorporation of Levenberg-Marquardt (LM) optimization and automated Bayesian regularization into backpropagation. From modeling outcomes, it was observed that both warp and weft yarn crimp models have generalized well with excellent coefficient of determination and trivial mean absolute error when tested on novel data. Moreover, input rank analysis of optimized network provided important information about model stability with respect to input variables, and trend analysis elucidated the input-crimp behavior using different input levels.     

Modeling flux behavior for membrane filtration of apple juice

The flux behavior of ceramic membranes with different pore sizes (0.2, 0.1 and 0.02 μm) was examined during dead-end membrane filtration of depectinized control (CTJ) and ascorbic acid treated (AAJ) apple juices. A new model based on an expanded exponential relationship was developed. The model represented the flux with precision over the entire filtration process for both juice types and all membrane pore sizes. Two parameters, A and B, provided a measure of the rate of flux decline. The same approach was used to model the permeate flux of CTJ for various 0.2 μm pore size polymeric membrane materials operated in a dead-end mode, and for tubular ultrafiltration membranes of different pore sizes (9, 20 and 100 kDa) operated in crossflow mode.     

Artificial neural network approach to simultaneously predict shelf life of two varieties of packaged rice snacks

Actual storage shelf life test by storing a packaged product under typical storage conditions is costly and time consuming. A new approach using an artificial neural network (ANN) algorithm for shelf life prediction of two varieties of moisture-sensitive rice snacks packaged in polyethylene and polypropylene bags and stored at various storage conditions was established. The ANN used to predict the shelf life was based on multilayer perceptron with back propagation algorithm. The ANN algorithm employed the data of product characteristics, package properties and storage conditions. The neural network comprised an input, one hidden and one output layers. The network was trained using Bayesian regularisation. The performance of ANN was measured using regression coefficient ( R ² = 0.23–0.28) and root mean square error (RMSE = 0.96–0.99). The ANN-predicted shelf lives agreed very well with actual shelf life data. ANN could be used as an alternative method for shelf life prediction of moisture-sensitive food products as well as product/package optimisation.     

A neuro-computing approach for modeling of residence time distribution (RTD) of carrot cubes in a vertical scraped surface heat exchanger (SSHE)

A neuro-computing approach was used for modeling two residence time distribution (RTD) functions — the time-specific (E-type distribution) and the cumulative particle concentration function (F-type distribution) — of carrot cubes in starch solutions in a vertical scraped surface heat exchanger (SSHE) of a pilot scale aseptic processing system. Experimental data obtained for E (t) and F(t) under various test conditions were used for both training and evaluation. Multi-layered artificial neural network (ANN) models with four input and two output neurons were trained. The network was optimized by the varying number of hidden layers, number of neurons in each hidden layer and learning runs, and a combination of learning rule and transfer functions, using a back-propagation algorithm. The trained ANN model was validated by a set of independent experimental data. The ANN models were also compared with conventional models developed based on multiple regression techniques. The results indicated that there was better agreement between experimental and ANN model predicted values for both E (t) and F (t) functions. The average modeling errors associated with ANN were 5.7 and 3.0%, respectively, for E(t) and F(t), while they were 15.5 and 12.3%, respectively, with the multiple regression models.     

A combined complete pore blocking and cake filtration model during ultrafiltration of polysaccharide in a batch cell

Ultrafiltration experiments of polysaccharide macromolecule have been performed in a batch, stirred as well as unstirred membrane cell using a fully retentive membrane over a wide range of operating conditions. A model based on Hermia’s approach for constant pressure dead-end filtration laws is proposed to analyze the flux decline behavior during ultrafiltration in a batch cell. Two model parameters, namely complete pore blocking coefficient and cake filtration coefficient are obtained by minimizing the error involved between calculated and experimental flux data. These parameters along with known operating conditions, membrane permeability and physical properties of feed enable one to predict the transient permeate flux decline. The effect of various operating conditions, such as feed solute concentration, stirrer speed and transmembrane pressure on the flux decline is studied. Experimental results show that operating conditions have significant effect on the onset of cake formation as well as on the flux decline behavior. Model predicted results are successfully compared with the experimental data.     

Identification of Fouling Mechanism During Ultrafiltration of Stevia Extract

Stevioside is one of the naturally occurring sweetener, which can be widely applied in food, drinks, medicine, and daily chemicals. Membrane separation has potential application in clarification of stevioside from pretreated stevia extract by ultrafiltration. In the present study, namely 5-, 10-, 30-, and 100-kDa molecular weight cutoff membranes have been used. Quantification of membrane fouling during ultrafiltration is essential for improving the efficiency of such filtration systems. A systematic analysis was carried out to identify the prevailing mechanism of membrane fouling using a batch unstirred filtration cell. It was observed that the flux decline phenomenon was governed by cake filtration in almost all the membranes. For 100 kDa membrane, both internal pore blocking and cake filtration are equally important. Resistance in series analysis shows that the cake resistance is several orders of magnitude higher than the membrane resistance. The cake resistance is almost independent of transmembrane pressure drop, which indicates the incompressible nature of the cake. A response surface analysis was carried out to quantify the development of cake resistance with time during ultrafiltration of various membranes. Quality parameters show that the 30-kDa membrane is better suited for clarification purposes. Identification of the fouling mechanism would aid in the process of design and scaling up of such clarification setup in future.     

Removal of phenolic compounds in pomegranate juices using ultrafiltration and laccase-ultrafiltration combinations

Phenolic compounds of fruit juices are responsible for haze and sediment formation as well as for color, bitterness and astringency. The influence of ultrafiltration (UF) and laccase-UF combination was investigated on phenolic contents of pomegranate juices and on filtration output. Laccase-treated and then ultrafiltered pomegranate juices have shown a rapid increase in their color, when compared to only ultrafiltered (control) samples. Kinetic parameters of laccase were also determined. During the oxidation period, the changes occurring in pomegranate juices were estimated from phenolic contents, color and anthocyanin measurements. Results have shown that laccase oxidation produced a significant decrease in phenolic content of pomegranate juices while juice color the increased. However, in recent literatures, the possibility to remove polyphenols in apple juices was reported. We decided in this study that laccase treatment can not be applied due to the loss of natural red color and unwanted dark brownish color formation in pomegranate juice.