Numerical simulation and experimental investigations of air drawing model and air jet flow field model in wide slot positive pressure spunbonding process

An air drawing model of polymers and a model of the air jet flow field model in wide slot positive pressure spunbonding process are established. The air jet flow field model is solved by means of the finite difference method. The numerical simulation computation results of distributions of the air velocity match quite well with the experimental data. We find that the variation of the density and the specific heat capacity of polymer melt at constant pressure with polymer temperature have much effects on fiber diameter. The newly developed formulas were incorporated into a spunbonding theoretical model to predict the fiber diameter of nonwoven web. The air drawing model of polymer is solved with the help of the distributions of the air velocity measured by a Particle Image Velocimetry (PIV). The predicted fiber diameters agree with the experimental data well. It can be concluded that the higher air pressure, higher air velocity and air temperature can yield the finer fibers diameter. The higher inlet pressure and smaller jet angle will all cause higher x-axis position of air velocity and air pressure, which are beneficial to the air drawing of the polymer melt and thus to reducing the fiber diameter.     

Dynamic modeling and simulation of bottom outlet air flow field in wide slot positive pressure spunbonding drawing process

The air jet flow has an important influence in wide slot positive pressure spunbonding process that not only includes the filament fiber diameter, crystallinity, and birefringence, but also the fiber web evenness. In this work, the air drawing model and the air jet flow field model of bottom outlet in spunbonding process are established and studied. The characteristics and regularities of the plane air jet flow in wide slot positive pressure spunbonding process are also demonstrated. It is simulated by means of the finite difference method. The numerical simulation computation results of distribution of the air velocity match quite well with the experimental data. The air drawing model of polymer is solved with the help of the distribution of the air velocity. The predicted filament fiber diameter, crystallinity, and birefringence agree well with the experimental data. It was found that higher initial velocity and initial temperature of air can yield finer fibers, and its effect was very significant. The results also reveal the great potential for this research in the computer-assisted design of spunbonding technology and equipment.     

聚丙烯PP纺粘法非织造布工艺参数对纤维直径的影响

通过建立聚丙烯PP纺粘聚合物的气流牵伸数学模型,讨论了纺粘工艺参数对纤维直径的影响,对不同的工艺参数进行了实验,发现聚合物挤出量越小,聚合物熔体温度越大,气流初始温度越高,吸风速度越大,越有利于聚合物熔体的气流牵伸,纤维直径越小;纤维直径随着文丘里间隙的增加而先减小,然后再增加,文丘里间隙大小对纤维直径有很大的影响。     

微纳米纤维的熔喷制作工艺

通过数值计算方法和熔喷实验方法,探索微纳米纤维的熔喷制作工艺。选用 Shambaugh 一维数学模型,运用数值计算方法,得出空气速度、熔体流量和喷丝孔直径对纤维直径的影响关系。通过分析比较得到这 3 个参数对纤维直径减小程度的影响顺序：熔体流量影响最大,空气速度次之,喷丝孔直径影响最小。根据熔喷实际情况,得出喷丝孔直径不能够太大。设计微纳米纤维的熔喷实验工艺,进行熔喷工艺实验和纤维直径测定实验,得到了纳米级纤维。证明了工艺参数对纤维直径影响关系和影响顺序规律的正确性,也证实了微纳米纤维制作工艺的有效性。     

Comparison between artificial neural network and response surface methodology in the prediction of the parameters of heat set polypropylene yarns

In the present paper, a response surface model has been introduced to predict the geometrical parameters of heat set polypropylene pile yarns. The input factors of the presented model include yarn twist, initial yarn count, time, and temperature of heat setting and the response factors are yarn count, yarn shrinkage, crimp contraction and packing factor after the heat setting process. To analyse the effect of this process on the yarn parameters, the dry heat setting process has been applied to all samples at different times and temperatures using an oven equipped with air circulation because of better accuracy and control of temperature. The obtained results showed that there is a positive relation between time and temperature and output parameters. Finally, the predicting equations discussions about the optimum points for maximum shrinkage and interactions of parameters have been presented. Hence, due to some disability of the RSM method, an ANN model has been designed to predict the parameters at higher accuracy. The results of the accomplished ANN model represent a higher prediction correlation coefficient compared to RSM.     

Optimal geometry design of the melt‐blowing slot die with high stagnation temperature via the orthogonal array method and numerical simulation

In this paper, a method combining the orthogonal array design and the numerical simulation is proposed to optimize the geometry parameters of the melt‐blowing slot die. An index, the stagnation temperature, is used to evaluate the performance of the slot die. The stagnation temperature is obtained by simulating the subsonic compressible air jet from the melt‐blowing slot die, whereas the optimization is accomplished by the orthogonal array method. Three geometry parameters of the slot die: slot width, nose piece width, and slot angle are investigated. The results show that smaller slot angle and larger slot width will result in a higher stagnation temperature, which is beneficial to the air drawing of the polymer melt and thus to reducing fiber diameter, whereas the effect of nose piece width is insignificant. The optimal geometry parameters of the melt‐blowing slot die achieved in this study are: slot width of 1.5 mm, slot angle of 30°, and nose piece width of 2 mm.     

Modeling of thermal properties of multilayered fabrics by ANN consisting of polypropylene needle-punched nonwovens

This paper presents the prediction of thermal and evaporative resistances of multilayered fabrics meant for cold weather conditions using artificial neural network (ANN) model. Thermal and evaporative resistances of fabrics were evaluated using sweating guarded hot plate method. The significance and interdependency of thickness on other fabric and process parameters and its effect on prediction performance of ANN model is analyzed in detail. For this purpose, two different network architectures were used to predict the thermal properties of multilayered fabrics. In both the networks, three-layer structure consisting of input, hidden and output layers was used. First, network was constructed with four input parameters, namely linear density of fiber, mass per unit area, punch density, and thickness of nonwoven fabric which predicts thermal and evaporative resistances. Second network was made with three input parameters, namely linear density, mass per unit area, and punch density. The network parameters were optimized to give minimum mean square error (MSE), mean absolute error percentage, and good correlation coefficient. The trend analysis was conducted and influence of various input parameters on the thermal properties of multilayered fabrics was studied. The significance of each input parameter in the prediction of thermal properties was studied by carrying out sensitivity analysis. The mean square error of the test dataset before and after the exclusion of the corresponding input parameter is taken for analysis. The input parameters were ranked based on the MSE ratio of test dataset. The predicted thermal properties of multilayered fabrics are correlated well with the experimental values. It was observed that the ANN model with minimum input parameters, namely linear density of fiber, mass per unit area, and punch density can predict the thermal properties of multilayered fabrics with good accuracy.     

ARTIFICIAL NEURAL NETWORK MODELING OF APPLE DRYING PROCESS

Artificial neural network (ANN) modeling and several mathematical models were applied to predict the moisture ratio in an apple drying process. Four drying mathematical models were fitted to the data obtained from eight drying runs and the most accurate model was selected. Two sets of ANN modeling were also performed. In the first set, the data obtained from each pilot were modeled individually to compare the ANN predictions with the best mathematical model. In the second set of ANN modeling, the simultaneous effect of all the four input parameters including air velocity, air temperature, the thickness of apple slices and drying time was investigated. The results showed that the ANN predictions were more accurate in comparison with the best fitted mathematical model. In addition, none of the mathematical models are able to predict the effect of the four input parameters simultaneously, while the presented ANN model predicts this effect with a good precision.

PRACTICAL APPLICATIONS

Today, modeling of chemical engineering processes is widespread in the process industries. An accurate modeling results in a precise prediction of the products of a process which could be very expensive or even unsafe to evaluate by experimental experiences. Because artificial neural network modeling is more or less proved to be one of the best modelings against mathematical ones, we suggest it to be considered for industrial processes such as drying in the food industry.     

Effects of processing parameters on electrospun fiber morphology

This study describes the application of a hybrid neuro-fuzzy inference system to control electrospinning process and how to use this approach for developing an electrospun fiber quality prediction system. An adaptive neuro-fuzzy inference system model has been applied to the use of electrospinning process parameters to study the relationship between electrospinning processing parameters and electrospun fiber morphology. Fiber morphology has been predicted and the impact of each processing parameter has been investigated. It was found that four electrospinning process parameters including: polymer solution concentration, spinning distance, applied voltage, and volume flow rate are the most influential factors to the electrospun fiber morphology. It was observed that the relationship existing between electrospinning processing parameters and nanofiber morphology is nonlinear.     

A comparative prediction for tensile properties of ternary blended open-end rotor yarns using regression and neural network models

This study focused on predicting tensile properties of PES/CV/PAN blended Open-End Rotor yarns. The effective factors were fiber blend ratios (six stages from 0 to 100%), linear density (three count levels), mixing method (carding machine and drawframe), and number of passages in drawframe (one and two times) as production parameters. We performed a stepwise multiple linear regression (MLR) analysis and established an artificial neural network (ANN) model that trained with backpropagation rule as Levenberg–Marquardt. Then, we conducted a comparative analysis for both models in terms of prediction performance. As a result, ANN has given a slightly better prediction values than MLR for breaking strength but significantly better prediction values for breaking elongation.     

MODELING AND OPTIMIZATION OF CONSTANT RETORT TEMPERATURE (CRT) THERMAL PROCESSING USING COUPLED NEURAL NETWORKS AND GENETIC ALGORITHMS

Coupled artificial neural network (ANN) models and genetic algorithms (GA) were applied for developing prediction models and for optimization of constant temperature retort (CRT) thermal processing of conduction heating foods. ANN prediction models were developed for process time (Pt), average quality retention (Qv), surface cook value (Fs), equivalent energy consumption (En), final temperature difference (T_g) at can center, and lethality ratio (p, heating/total lethality). The processing conditions as inputs for ANN models were as follows: retort temperature (RT = 110–140C), thermal diffusivity (α= 1.1–2.14*10^?7m²/s), volume of can (V = 1.64–6.55*10^?4m³), ratio of height to diameter of can (R_dh= 0.2–1.8), total desired lethality value (F₀= 5–10 min) at can center and quality kinetic destruction parameters: decimal destruction time (D_q– 150–300 min) and their temperature dependence (z_q= 15–40C). The data for training and testing ANN models were obtained from a finite difference computer simulation program. A second order central composite design was used for constructing the experimental data for training ANN models, while an orthogonal experimental design with 6 factors and 3 levels was used for the generalization of trained ANN models. ANN model linked Genetic Algorithms (GA) were employed for searching for the optimal quality retention and corresponding retort temperature, and for investigating the effects of main processing factors. ANN‐based prediction models successfully described the various outputs of CRT thermal processing (correlation coefficients: R² > 0.98; relative errors: Er ≤ 3%). The coupled ANN‐GA models, verified under several typical processing conditions, could be effectively used for optimization of CRT thermal processing. The main processing conditions and their interactions in the order of their importance with respect to the optimal quality retention and corresponding retort temperature were: V >z_q >R_dh >; and z_q >F_d > R_dh >V, respectively.     

An artificial neural network for predicting the physiochemical properties of fish oil microcapsules obtained by spray drying

The aim of this work was to develop an artificial neural network (ANN) to predict the physiochemical properties of fish oil microcapsules obtained by spray drying method. The relation amongst inlet-drying air temperature, outlet-drying air temperature, aspirator rate, peristaltic pump rate, and spraying air flow rate with 5 performance indices, namely capsules’ residual moisture content, particle size, bulk density, encapsulation efficiency, and peroxide value was bridged by using ANN. A multilayer perceptron ANN was developed to predict the performance indices based on the input variables. The optimal ANN model was found to be a 5-10-5 structure with tangent sigmoid transfer function, Levenberg-Marquardt error minimization algorithm, and 1,000 training epochs. This optimal network was capable to predict the outputs with R² values higher than 0.87. It was concluded that ANN is a useful tool to investigate, approximate, and predict the encapsulation characteristics of fish oil.     

应用粗糙集和支持向量机的熔喷非织造布过滤性能预测

为预测熔喷非织造布的过滤性能,提出基于属性约简和支持向量机的预测方法。运用粗糙集理论在ROSETTA 环境下对含有9 个参数的熔喷非织造纤网结构参数全集进行约简,得到6 个各含3 个参数的约简集。分别将参数全集及各个约简集作为输入建立基于支持向量机（SVM）和ＢＰ 神经网络（BP-ANN）的28 个过滤性能预测模型,运用交叉验证法进行模型结构参数优化。结果表明：以含厚度、纤维直径和孔径的约简集为输入,基于ＳＶＭ模型预测准确度最高;其对过滤效率和过滤阻力的预测精度均超过98%,且CV 值均小于2%,表明这3 个参数是影响熔喷非织造布过滤性能的核心要素;基于SVM 模型的预测准确度总体优于基于BP-ANN模型的。     

Predicting the colour properties of viscose knitted fabrics using soft computing approaches

The aim of this paper was to predict the colour strength of viscose knitted fabrics by using fuzzy logic (FL) model based on dye concentration, salt concentration and alkali concentration as input variables. Moreover, the performance of fuzzy logic (FL) model is compared with that of artificial neural network (ANN) model. In addition, same parameters and data have been used in ANN model. From the experimental study, it was found that dye concentration has the main and greatest effects on the colour strength of viscose knitted fabrics. The coefficient of determination (R²), root mean square (RMS) and mean absolute errors (MAE) between the experimental colour strength and that predicted by FL model are found to be 0.977, 1.025 and 4.61%, respectively. Further, the coefficient of determination (R²), root mean square (RMS) and mean absolute errors (MAE) between the experimental colour strength and that predicted by ANN model are found to be 0.992, 0.726 and 3.28%, respectively. It was found that both ANN and FL models have ability and accuracy to predict the fabric colour strength effectively in non-linear domain. However, ANN prediction model shows higher prediction accuracy than that of Fuzzy model.     

纺织工业中的虚拟加工技术与模式

简要介绍了纺织品加工过程、人工神经网络（ANN）及其相关算法的特征。通过ANN技术建立的原料、纺纱、织造和后整理预测／反演模型，能够优化生产工艺，预测与控制产品质量，是纺织设计与虚拟加工的基础。采用主因子、聚类、案例模板和ANN等算法完成对输入参数的归纳、筛选与增补，是提高预测／反演模型精度和效率的有效步骤。以此构建的模块组合式虚拟加工系统，对纺织工业的快速、准确和理性加工，纺织品的低成本和高质量实现，具有重要意义。     

Optimization of process parameters in oriented strand board manufacturing with artificial neural network analysis

In the present work, an artificial neural network (ANN) model was developed for predicting the effects of some production factors such as adhesive ratio, press pressure and time, and wood density and moisture content on some physical properties of oriented strand board (OSB) such as moisture absorption, thickness swelling and thermal conductivity. The MATLAB Neural Network Toolbox was used for the training and optimization of the artificial neural network. The ANN model having the best prediction performance was determined by means of statistical and graphical comparisons. The results show that the prediction model is a useful, reliable and quite effective tool for predicting some physical properties of the OSB produced under different manufacturing conditions. Thus, this study has presented a novel and alternative approach to the literature to optimize process parameters in OSB manufacturing process.     

Modelling the growth of Leuconostoc mesenteroides by Artificial Neural Networks

The combined effect of temperature (10.5 to 24.5 degrees C), pH level (5.5 to 7.5), sodium chloride level (0.25% to 6.25%) and sodium nitrite level (0 to 200 ppm) on the predicted specific growth rate (Gr), lag-time (Lag) and maximum population density (yEnd) of Leuconostoc mesenteroides under aerobic and anaerobic conditions, was studied using an Artificial Neural Network-based model (ANN) in comparison with Response Surface Methodology (RS). For both aerobic and anaerobic conditions, two types of ANN model were elaborated, unidimensional for each of the growth parameters, and multidimensional in which the three parameters Gr, Lag, and yEnd are combined. Although in general no significant statistical differences were observed between both types of model, we opted for the unidimensional model, because it obtained the lowest mean value for the standard error of prediction for generalisation. The ANN models developed provided reliable estimates for the three kinetic parameters studied; the SEP values in aerobic conditions ranged from between 2.82% for Gr, 6.05% for Lag and 10% for yEnd, a higher degree accuracy than those of the RS model (Gr: 9.54%; Lag: 8.89%; yEnd: 10.27%). Similar results were observed for anaerobic conditions. During external validation, a higher degree of accuracy (Af) and bias (Bf) were observed for the ANN model compared with the RS model. ANN predictive growth models are a valuable tool, enabling swift determination of L. mesenteroides growth parameters.     

重组毕赤酵母表达期菌体浓度的软测量模型

建立了用于在线估计高密度重组毕赤酵母培养过程中处于表达阶段的菌体密度软测量模型。分别对比了基于遗传算法（GA）的动力学软测量模型以及基于人工神经网络（ANN）的软测量模型，并对神经网络软测量模型的拓扑结构以及训练参数进行了初步探讨。当采用基于遗传算法（GA）的动力学模型，模型拟舍值的最大误差为7．63％；在采用神经网络软测量技术时，选取合适的模型结构和输入参数，最大误差为3．12％，而且软测量模型可以很好地反映菌体浓度实时变化趋势。该研究结果表明，在酵母细胞的高密度培养过程中采用基于神经网络的软测量模型具有较高的准确度，可以较好地实时反映发酵过程中菌体浓度的变化。     

基于人工神经网络模型预测油炸外裹糊鱼块的丙烯酰胺含量

为实现对油炸外裹糊鱼块的丙烯酰胺含量的预测,采用响应面试验设计收集数据,建立以黄原胶和大豆纤维复配比例、外裹糊鱼块干燥时间、大豆油品质、油炸温度、油炸时间为输入值,油炸外裹糊鱼块的丙烯酰胺含量为输出值的反向传播人工神经网络（back propagation artificial neural network,BP-ANN）,预测外裹糊鱼块深度油炸过程丙烯酰胺含量的变化,并用训练集拟合,测试集评估模型的预测能力。结果显示,黄原胶和大豆纤维复配比例、外裹糊鱼块干燥时间、油炸温度、油炸时间对油炸外裹糊鱼块的丙烯酰胺含量均有显著影响,大豆油品质对油炸外裹糊鱼块中丙烯酰胺含量影响不显著。训练后的BP-ANN模型的相关系数R值为0.997,拟合良好,有很强的逼近能力;模型对新数据预测的误差较小,最大相对误差为5.34%,最小相对误差为0.12%,表明BP-ANN模型能准确预测油炸外裹糊鱼块的丙烯酰胺含量。     

基于外部特征信息的蟠桃质量预测模型

采用计算机图像处理技术对蟠桃的缝合中线处直径、与缝合中线垂直处的直径以及厚度3个几何特征参数进行分析,建立基于外部特征信息的蟠桃质量预测模型。通过多元线性回归方法拟合出实测值与蟠桃质量的预测模型,比较不同参数所得模型的拟合优度,找到最优质量预测模型。通过将MATLAB R2014a软件获取的像素值与相应几何参数进行拟合,最终得到像素质量预测模型,预测准确率达到91.87%。结果表明:基于外部特征信息的蟠桃质量预测研究是可行的,可为采用机器视觉方法进行蟠桃质量分级提供依据。