Using artificial neural networks to model and interpret electrospun polysaccharide (Hylon VII starch) nanofiber diameter

Present work was aimed to develop an artificial neural networks (ANN) model to predict the polysaccharide-based biopolymer (Hylon VII starch) nanofiber diameter and classification of its quality (good, fair, and poor) as a function of polymer concentration, spinning distance, feed rate, and applied voltage during the electrospinning process. The relationship between diameter and its quality with process parameters is complex and nonlinear. The backpropagation algorithm was used to train the ANN model and achieved the classification accuracy, precision, and recall of 93.9%, 95.2%, and 95.2%, respectively. The average errors of the predicted fiber diameter for training and unseen testing data were found to be 0.05% and 2.6%, respectively. A stand-alone ANN software was designed to extract information on the electrospinning system from a small experimental database. It was successful in establishing the relationship between electrospinning process parameters and fiber quality and diameter. The yield of smaller diameter with good quality was favored by lower feed rate, lower polymer solution concentration, and higher applied voltage.     

聚丙烯腈纺丝工艺对纤维结构及染色性能的影响

本文用聚丙烯腈、丙烯酸甲酯和甲基丙烯磺酸钠、三元共聚物的硫氰酸钠溶液进行湿法纺丝,研究了纺丝液的温度和聚合物含量,纺丝速度及拉伸与水洗工序的先后顺序对纤维的结构和染色性的影响。结果发现,采用先拉伸后水洗与先水洗后拉伸两种工艺,纺得纤维的染色性和结构有明显差别。     

Modeling and Optimization of Anode‐Supported Solid Oxide Fuel Cells on Cell Parameters via Artificial Neural Network and Genetic Algorithm

An artificial neural network (ANN) and a genetic algorithm (GA) are employed to model and optimize cell parameters to improve the performance of singular, intermediate‐temperature, solid oxide fuel cells (IT‐SOFCs). The ANN model uses a feed‐forward neural network with an error back‐propagation algorithm. The ANN is trained using experimental data as a black‐box without using physical models. The developed model is able to predict the performance of the SOFC. An optimization algorithm is utilized to select the optimal SOFC parameters. The optimal values of four cell parameters (anode support thickness, anode support porosity, electrolyte thickness, and functional layer cathode thickness) are determined by using the GA under different conditions. The results show that these optimum cell parameters deliver the highest maximum power density under different constraints on the anode support thickness, porosity, and electrolyte thickness.     

Application of response surface methodology to evaluate the effect of dry‐spinning parameters on poly (ε‐caprolactone) fiber properties

Poly (ε‐caprolactone) fibers were prepared by dry‐spinning method. The effect of processing parameters on linear density, mechanical, and morphological properties of fibers was investigated using the response surface methodology (RSM). This method allowed evaluating a quantitative relationship between polymer concentrations, spinning speed, and draw ratio on the properties of the fibers. Polynomial regression model was fitted to the experimental data to generate predicted response. The results were subjected to analysis of variance to determine significant parameters. It was found that all three parameters had significant effect on linear density of fibers. Combined effect of concentration and spinning speed was observed in which the linear density of fiber was more sensitive to changes in the solution concentration at lower spinning speed. Polymer concentration had the largest influence on the mechanical properties of fibers. An average cross‐sectional radius of fibers was affected by concentration and draw ratio in opposite manner. Among all three parameters, only polymer concentration had significant effect on circularity of fiber cross sections. By applying the RSM, it was possible to obtain a mathematical model that can be used to better define processing parameters to fabricate dry‐spun PCL fiber in a more rational manner. © 2015 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2015 , 132, 42113.     

Correlating the 3D melt electrospun polycaprolactone fiber diameter and process parameters using neural networks

In the present work, we developed an artificial neural networks (ANN) model to predict and analyze the polycaprolactone fiber diameter as a function of 3D melt electrospinning process parameters. A total of 35 datasets having various combinations of electrospinning writing process variables (collector speed, tip to nozzle distance, applied pressure, and voltage) and resultant fiber diameter were considered for model development. The designed stand-alone ANN software extracts relationships between the process variables and fiber diameter in a 3D melt electrospinning system. The developed model could predict the fiber diameter with reasonable accuracy for both train (28) and test (7) datasets. The relative index of importance revealed the significance of process variables on the fiber diameter. Virtual melt spinning system with the mean values of the process variables identifies the quantitative relationship between the fiber diameter and process variables.     

Simulation of polyimide fibers with trilobal cross section produced by dry‐spinning technology

As one type of high performance fibers, polyimide fibers can be prepared from polyamic acid (PAA) solution by dry‐spinning technology. The transformation from the precursor of polyamic acid to polyimides via thermal cyclization reaction in the dry‐spinning process is a main distinguishing feature, which is very different from other fibers produced by dry‐spinning such as cellulose acetate fiber and polyurethane fiber. In this report, the dry‐spinning formation of polyimide fibers with trilobal cross section from PAA solution in N,N‐dimethylacetamide is simulated via a one‐dimensional model based on a viscoelastic constitutive equation, combined with profile degree equation of cross section and imidization kinetics equation. The glass transition temperature, imidization degree and profile degree of the filament along the spinline are predicted by the model, as well as relative parameters such as solvent mass fraction and temperature. As a simulated result, solidification of polyimide fibers take place about 150 cm from the spinneret which is farther than for cellulose acetate fiber (70 cm). Moreover, the final profile degree of fiber is affected by many spinning parameters, such as spinning temperature, surface tension, spinning solution concentration, major, and minor axis length of the spinneret hole. POLYM. ENG. SCI., 55:2148–2155, 2015. © 2015 Society of Plastics Engineers     

PREDICTION OF QUALITY CHANGES DURING OSMO-CONVECTIVE DRYING OF BLUEBERRIES USING NEURAL NETWORK MODELS FOR PROCESS OPTIMIZATION

Artificial neural network (ANN) models were used for predicting quality changes during osmo-convective drying of blueberries for process optimization. Osmotic drying usually involves treatment of fruits in an osmotic solution of predetermined concentration, temperature and time, and generally affects several associated quality factors such as color, texture, rehydration ratio as well as the finish drying time in a subsequent drier (usually air drying). Multi-layer neural network models with 3 inputs (concentration, osmotic temperature and contact time) were developed to predict 5 outputs: air drying time, color, texture, and rehydration ratio as well as a defined comprehensive index. The optimal configuration of neural network model was obtained by varying the main parameters of ANN: transfer function, learning rule, number of neurons and layers, and learning runs. The predictability of ANN models was compared with that of multiple regression models, confirming that ANN models had much better performance than conventional mathematical models. The prediction matrices and corresponding response curves for main processing properties under various osmotic dehydration conditions were used for searching the optimal processing conditions. The results indicated that it is feasible to use ANN for prediction and optimization of osmo-convective drying for blueberries.     

PREDICTION OF QUALITY CHANGES DURING OSMO-CONVECTIVE DRYING OF BLUEBERRIES USING NEURAL NETWORK MODELS FOR PROCESS OPTIMIZATION

Artificial neural network (ANN) models were used for predicting quality changes during osmo-convective drying of blueberries for process optimization. Osmotic drying usually involves treatment of fruits in an osmotic solution of predetermined concentration, temperature and time, and generally affects several associated quality factors such as color, texture, rehydration ratio as well as the finish drying time in a subsequent drier (usually air drying). Multi-layer neural network models with 3 inputs (concentration, osmotic temperature and contact time) were developed to predict 5 outputs: air drying time, color, texture, and rehydration ratio as well as a defined comprehensive index. The optimal configuration of neural network model was obtained by varying the main parameters of ANN: transfer function, learning rule, number of neurons and layers, and learning runs. The predictability of ANN models was compared with that of multiple regression models, confirming that ANN models had much better performance than conventional mathematical models. The prediction matrices and corresponding response curves for main processing properties under various osmotic dehydration conditions were used for searching the optimal processing conditions. The results indicated that it is feasible to use ANN for prediction and optimization of osmo-convective drying for blueberries.     

莫来石纺丝溶胶的流变特性及可纺性研究

本文以氢氧化铝为铝源,以硅溶胶为硅源,采用溶胶-凝胶技术制备了莫来石纺丝溶胶,采用稳态及动态两种测试模式,研究了纺丝溶胶的粘度及流变性能,并采用干法纺丝制备连续莫来石凝胶纤维,评价了溶胶的可纺性。结果表明,温度对溶胶的非牛顿指数及结构粘度指数影响不大,这将有利于纺丝工艺的调节;高固含量有利于莫来石凝胶纤维的纺丝成纤,制备的凝胶纤维更细,纺丝稳定性更好。     

Performance evaluation of an ANN–GA aided experimental modeling and optimization procedure for enhanced synthesis of marine biosurfactant in a stirred tank reactor

BACKGROUND: An improved resilient back‐propagation neural network modeling coupled with genetic algorithm aided optimization technique was employed for optimizing the process variables to maximize lipopeptide biosurfactant production by marine Bacillus circulans. RESULTS: An artificial neural network (ANN) was used to develop a non‐linear model based on a 2⁴ full factorial central composite design involving four independent parameters, agitation, aeration, temperature and pH with biosurfactant concentration as the process output. The polynomial model was optimized to maximize lipopeptide biosurfactants concentration using a genetic algorithm (GA). The ranges and levels of these critical process parameters were determined through single‐factor‐at‐a‐time experimental strategy. Improved ANN‐GA modeling and optimization were performed using MATLAB v.7.6 and the experimental design was obtained using Design Expert v.7.0. The ANN model was developed using the advanced neural network architecture called resilient back‐propagation algorithm. CONCLUSION: Process optimization for maximum production of marine microbial surfactant involving ANN‐GA aided experimental modeling and optimization was successfully carried out as the predicted optimal conditions were well validated by performing actual fermentation experiments. Approximately 52% enhancement in biosurfactant concentration was achieved using the above‐mentioned optimization strategy. © 2012 Society of Chemical Industry     

Reinforcing the phenomenological consistency in artificial neural network modeling of multiphase reactors

Artificial neural networks (ANN) aided with dimensional analysis have been successfully applied in multiphase reactors modeling when considerable amount of experimental data (or database) is available. An important problem that stemmed from this approach was the ambiguity to select the fittest combination of dimensionless numbers to be used as ANN inputs to predict a variable of interest. A genetic algorithm (GA) based methodology was proposed to optimize the combination of inputs by taking into account the phenomenological consistency (PC) of the resulting ANN models along with their fitting capabilities. PC is a measure of the capability of an ANN model to simulate outputs with specified gradient conditions with respect to the process variables. These conditions are imposed based on a priori knowledge of the system's behavior. PC used to be evaluated in the vicinity of a particular point in the database space. The novelty of the approach was the extension of the PC test around all the points available in the training data set. This technique may be regarded as a robust method to prevent data overfitting when the function to be learned by ANN is characterized by a monotonic behavior with respect to some of the process variables. The new approach was illustrated using as a case study the correlation of two-phase pressure drop in randomly packed beds with countercurrent flow.     

Dry‐jet‐wet spun polyurethane fibers. I. Optimization of the spinning parameters

This study examined the spinning of polyurethane‐based elastomeric fibers with the dry‐jet‐wet spinning method. The three important spinning variables that were chosen were the coagulation bath ratio (dimethylformamide/water), the bath temperature, and the stretch ratio. A three‐variable factorial design method, proposed by Box and Behnken, was used to optimize these process parameters. The spinning process was further fine‐tuned by the variation of the stretch ratio and the dope solid content. The effect of the dry‐jet length on the fiber properties was also studied. The tenacity and elastic recovery properties of the fibers were found to be optimum at a bath ratio (dimethylformamide/water) of 60 : 40, a bath temperature of 15°C, and a stretch ratio of 2.5. The density and sonic modulus were measured to determine the effect of varying the process variables on structural parameters such as the density and orientation. The surface morphological features, as revealed by scanning electron microscopy, were correlated to the fiber properties. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

改进干法腈纶纤维颜色的研究

国产干法腈纶纤维“b”颜色值与进口样品有较大差距,根据原料工艺路线、化学反应机理,对影响腈纶纤维尊色变化的原因进行了分析,找出了主要影响纤维颜色的因素,对纤维颜色增深产生在纺丝原液制备过程的若干因素,进行定性和定量分析,解决了干法腈纶纤维“b”颜色值高的问题,提出进一步增加腈纶纤维白度的实用性生产方法。     

Preparation of antimicrobial polyacrylonitrile fibers: Blending with polyacrylonitrile-co-3-allyl-5,5-dimethylhydantoin

Summary Polyacrylonitrile-co-3-allyl-5,5-dimethylhydantoin (Cop7-1) was prepared by a free radical polymerization process. The copolymer was blended with polyacrylonitrile (PAN) in a NaSCN aqueous solution, and the mixture was employed as a spinning solution. Rheological behavior of the spinning solution was studied. The PAN/Cop7-1 blend fibers were prepared through a two-stage wet spinning process. Tensile strengths of the blend fibers were lightly lower, but breaking elongations were higher than regular PAN fibers. Moisture regain and antistatic properties of the blend fibers were improved, while the thermal stability of the blend fibers decreased slightly. However, after treatment with 1% regular chlorine bleach, the blend fibers showed good antibacterial ability.     

Structure and properties of cellulose fibers from ionic liquids

1‐Butyl‐3‐methylimidazolium chloride ([BMIM]Cl) was used as a solvent for cellulose, the rheological behavior of the cellulose/[BMIM]Cl solution was studied, and the fibers were spun with a dry‐jet–wet‐spinning process. In addition, the structure and properties of the prepared cellulose fibers were investigated and compared with those of lyocell fibers. The results showed that the cellulose/[BMIM]Cl solution was a typical shear‐thinning fluid, and the temperature had little influence on the apparent viscosity of the solution when the shear rate was higher than 100 s^?1. In addition, the prepared fibers had a cellulose II crystal structure just like that of lyocell fibers, and the orientation and crystallinity of the fibers increased with the draw ratio increasing, so the mechanical properties of the fibers improved. Fibers with a tenacity of 4.28cN/dtex and a modulus of 56.8 cN/dtex were prepared. Moreover, the fibers had a smooth surface as well as a round and compact structure, and the dyeing and antifibrillation properties of the fibers were similar to those of lyocell fibers; however, the color of these dyed fibers was brighter than that of lyocell fibers. Therefore, these fibers could be a new kind of environmentally friendly cellulose fiber following lyocell fibers. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

PEEKWC ultrafiltration hollow‐fiber membranes: Preparation,morphology, and transport properties

A series of hollow‐fiber membranes was produced by the dry–wet spinning method from PEEKWC, a modified poly(ether ether ketone) with good mechanical, thermal, and chemical resistance. The fibers were prepared under different spinning conditions, varying the following spinning parameters: polymer concentration in the spinning solution, height of the air gap, and bore fluid composition. The effect of these parameters on the water permeability, the rejection of macromolecules (using dextrane with an average molecular weight of 68,800 g/mol), and the morphology of the membranes was studied. The results were also correlated to the viscosity of the spinning solution and to the ternary polymer/solvent/nonsolvent phase diagram. The morphology of the cross section and internal and external surfaces of the hollow fibers were analyzed using scanning electron microscopy (SEM). All membranes were shown to have a fingerlike void structure and a skin layer, depending on the spinning conditions, varying from (apparently) dense to porous. Pore size measurements by the bubble‐point method showed maximum pore sizes ranging from 0.3 to 2 μm. Permeability varied from 300 to 1000 L/(h^?1 m^?2 bar) and rejection to the dextrane from 10 to 78%. The viscosity of polymer solutions was in the range of 0.2 to 3.5 Pa s. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 91: 841–853, 2004     

聚羟基丁酸羟基戊酸共聚酯纤维干法纺丝成形研究

从生物源聚合体聚羟基丁酸羟基戊酸共聚酯（PHBV）出发,对其干法纺丝成形作了探索。重点研究了纺丝原液的流变行为,初生纤维截面形态,初生纤维可拉伸性能随存放时间的变化,拉伸过程对纤维力学性能的影响等。结果表明,用干法纺丝制备的PHBV初生纤维具有较好的可拉伸性,但需严格控制初生纤维的存放时间;经拉伸及后处理,PHBV纤维的断裂强度可以达到1.8cN/dtex以上,断裂伸长可以达到40％以上。     

主辅螺杆挤出高效动态混合高速纺丝研究

在本院自行研制的主辅螺杆挤出高效动态混合高速纺丝实验机上,采用辽化生产的牌号70835聚丙烯原料,进行了PP与PA的共混纺丝,以PR-86抗静电剂为添加剂的纺丝和有色丙纶的纺丝研究。结果表明:该项技术用于纺丝,工艺便于调整,纤维指标正常,特别是对高粘熔体具有高效混合能力,因此,为改性纤维的生产提供了较为理想的装置。     

Factorial optimization of the effects of melt‐spinning conditions on biodegradable as‐spun aliphatic–aromatic copolyester fibers. III. Diameter,tensile properties,and thermal shrinkage

To model the melt‐spinning process of biodegradable as‐spun linear aliphatic–aromatic copolyester fibers, a fraction factorial experimental design and appropriate statistical analysis for the 32 screening trials involving five control parameters were used. Because of their central role in the production processes and end use textiles, it is important to simulate the mechanical and thermal shrinkage properties of AAC fibers. Concise statistical models of fiber behavior are based on factorial experimental design data. Process's data are collected, analyzed, and mathematical models created to predict the diameter, tenacity, elongation at break, modulus, and thermal shrinkage of the spun fiber in terms of random variables and their associated probability distributions. The theoretical regression models obtained form the main source code in the enhanced forecasting program, which presents the melt‐spinning process of aromatic–aliphatic copolyester fibers. Factorial statistical approaches, based on over indicated region levels of melt‐spinning process parameters, are given in terms of assumptions and theory to produce biodegradable, environmentally friendly fibers for different applications. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2011