Dynamic prediction of milk ultrafiltration performance: A neural network approach

Neural network models were tested in connection with the dynamic prediction of permeate flux (J_P), total hydraulic resistance (R_T) and the solutes rejection for the crossflow ultrafiltration of milk at different transmembrane pressure (TMP) and temperature (T). This process has complex non-linear dependencies on the operating conditions. Thus it provides demanding test of the neural network approach to the process variables prediction. Two neural network models with single hidden layer were constructed to predict the time dependent rate of J_P/R_T and rejections from a limited number of training data. The modelling results showed that there is an excellent agreement between the experimental data and predicted values, with average errors less than 1%. The experimental results showed that the R_T and solutes rejection (except for protein) increased greatly with time at each value of TMP and T, whereas the J_P decreased significantly for the same conditions. Increasing TMP at constant T led to an increase in the J_P, R_T and solutes rejection, but increasing T at constant TMP had no significant effect on the J_P, R_T and rejection of components.     

Application of artificial neural network for prediction of 10 crude oil properties

This study aims to develop an industrially reliable and accurate method to estimate crude oil properties from their Fourier transform infrared spectroscopy (FTIR) spectra. We used the complete FTIR spectral data of selected crude oil samples from seven different Canadian oil fields to predict 10 important crude oil properties using artificial neural networks (ANNs). The predicted properties include specific gravity, kinematic viscosity, total acid number, micro carbon content, and production of light and heavy naphtha, Kero, and distillate in oil refineries. The 107 different (65 light oil and 42 heavy/medium oil samples) crude oil samples used in this study came from seven oil fields and reservoirs across Canada. In line with standard practice, we used 80% of the dataset for training the ANN models and used the remaining 20% of the crude oil samples to test the models. In the ANN analysis, the mean squared error (MSE) was used as the loss function in models, and the mean absolute prediction error (MAPE) was used as a reference to compare the performance of different neural networks constructed with different numbers of layers. This work demonstrates that FTIR spectroscopy is a promising technique that provides rapid and accurate estimates for the oil properties of interest to the industry. A comparison of the values predicted by the validated ANN models and their corresponding measured (actual) values showed excellent prediction with the acceptable range of error (below 15%) aimed for by our industry partner for all properties except viscosity, for which building models based on the natural logarithmic values of measured viscosities significantly improved the results.     

A neural network approach to the prediction of diesel fuel lubricity

The continuous sulfur reduction in diesel fuel has resulted in poor fuel lubricity and engine pump failure, a fact that led to the development of a number of methods that measure the actual fuel lubricity level. However, lubricity measurement is costly and time consuming, and a number of predictive models have been developed in the past, based mainly on various fuel properties. In the present paper, a black box modeling approach is proposed, where the lubricity is approximated by a radial basis function (RBF) neural network that uses other fuel properties as inputs. The HFRR apparatus was used for lubricity measurements. In the present model, the variables used included the diesel fuel conductivity, density, kinematic viscosity at 40 °C, sulfur content and 90% distillation point, which produced the smallest error in the validation data.     

Coatings of Na-aluminosilicate zeolites prepared using predictions from an artificial neural network method

Predictions made by the Generalized Regression Neural Networks (GRNN) method were used to relate the initial compositions of various reaction mixtures to the types of Na-aluminosilicate zeolites that may be obtained from these compositions. In the light of the predictions made, coatings were prepared on stainless steel plates, which were characterized by X-ray diffraction and scanning electron microscopy prior to and after syntheses. Coatings of zeolites P, X, A, analcime as well as their mixtures could be obtained from a variety of previously unknown clear solution compositions, generally in good accordance with the predictions made by the GRNN method. Different textural properties were obtained for the coatings of the same zeolite, such as P and X, which could be prepared from a relatively wide range of compositions.     

Prediction of air pollutants by using an artificial neural network

The purpose of this study is to predict the amount of primary air pollution substances in Seoul, Korea. An artificial neural network (ANN) was used as a prediction method. The ANN with three layers is learned with past data, and the concentrations of air pollutants are predicted based on the pre-learned weights. The error back propagation method that has a powerful application to various fields was adopted as the learning rule. The concentrations of air pollutants from one to six hours in the future were predicted with the ANN. To verify the performance of the prediction method used in the present study, the predicted concentrations of air pollutants were compared with the measured data. From the comparison, it was found that the prediction method based on the ANN gives an acceptable accuracy for the limited prediction horizon.     

Correlating thermal conductivity of pure hydrocarbons and aromatics via perceptron artificial neural network (PANN) method

Accurate estimation of liquid thermal conductivity is highly necessary to appropriately design equipments in different industries. Respect to this necessity, in the current investigation a feed-forward artificial neural network(ANN) model is examined to correlate the liquid thermal conductivity of normal and aromatic hydrocarbons at the temperatures range of 257–338 K and atmospheric pressure. For this purpose, 956 experimental thermal conductivities for normal and aromatic hydrocarbons are collected from different previously published literature.During the modeling stage, to discriminate different substances, critical temperature(Tc), critical pressure(Pc)and acentric factor(ω) are utilized as the network inputs besides the temperature. During the examination, effects of different transfer functions and number of neurons in hidden layer are investigated to find the optimum network architecture. Besides, statistical error analysis considering the results obtained from available correlations and group contribution methods and proposed neural network is performed to reliably check the feasibility and accuracy of the proposed method. Respect to the obtained results, it can be concluded that the proposed neural network consisted of three layers namely, input, hidden and output layers with 22 neurons in hidden layer was the optimum ANN model. Generally, the proposed model enables to correlate the thermal conductivity of normal and aromatic hydrocarbons with absolute average relative deviation percent(AARD), mean square error(MSE), and correlation coefficient(R~2) of lower than 0.2%, 1.05 × 10~(-7) and 0.9994, respectively.     

Catalyst design for methane oxidative coupling by using artificial neural network and hybrid genetic algorithm

A new method for catalyst design was discussed based on artificial neural network, which was developed to simulate the relations between catalyst components and catalytic performance in the previous research. For enhancing efficiency of catalyst design, a new hybrid GA tested by TSP was generated for global optimization to design the ‘optimal’ catalyst. A multi-turn design strategy was described. Based on the previous research, the design method was applied for designing multi-component catalyst for methane oxidative coupling, some better catalysts, in which C₂ hydrocarbon yields were greater than 25% were designed. When reacting on the best catalyst, GHSV was , CH₄:O₂ was 3, reaction temperature was , methane conversion and C₂ hydrocarbon selectivity were 37.79% and 73.50%, respectively (C₂ hydrocarbon yield was 27.78%), which was higher than that of previous reported catalysts on no diluted gas condition, and showed a better prospect for industrialization of methane oxidative coupling. The research also showed that the new catalyst design method is highly efficient and universal.     

A stacked neural network approach for yield prediction of propylene polymerization

Prediction of reaction yield as the most important characteristic process of a slurry polymerization industrial process of propylene has been carried out. Stacked neural network as an effective method for modeling of inherently complex and nonlinear systems–especially a system with a limited number of experimental data points–was chosen for yield prediction. Also, effect of operational parameters on propylene polymerization yield was modeled by the use of this method. The catalyst system was Mg(OEt)₂/DIBP/TiCl₄/PTES/AlEt₃, where Mg(OEt)₂, DIBP (diisobutyl phthalate), TiCl₄, PTES (phenyl triethoxy silane), and triethyl aluminum (AlEt₃) (TEAl) were employed as support, internal electron donor (ID), catalyst precursor, external electron donor (ED), and co‐catalyst, respectively. The experimental results confirmed the validity of the proposed model. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

The control of MSF desalination plants based on inverse model control by neural network

In this paper, a nonlinear inverse model control strategy based on neural network is proposed for MSF desalination plant. Artificial neural networks (ANNs) can handle complex and nonlinear process relationships, and are robust to noisy data. The designed neural networks consist of three layers identified from input–output data and trained with a descent gradient algorithm. The set point tracking performance of the proposed method was studied when the disturbance is present in the MSF system. Three controllers are designed for controlling the top brine temperature, the level of last stage and salinity. These results show that a neural network inverse model control strategy (NNINVMC) is robust and highly promising to be implemented in such nonlinear systems. Also the comparison between the top brine temperature of the proposed model and NN predicted data from the literature supports the accuracy of the model.     

Hybrid neural network approach in description and prediction of dynamic behavior of chaotic chemical reaction systems

A chaotic system with available prior knowledge is identified with both the sequential hybrid neural network and the standard Artificial Neural Network (ANN). The identified models are validated with phase portrait, return map, the largest Lyapunov exponent and correlation dimension instead of using Sum of Square Errors (SSE). Interpolation and Extrapolation capability of the models are compared. This is demonstrated for nonisothermal, irreversible, first-order, series reaction A≇B≇C in a CSTR.     

Partition coefficient prediction of Baker's yeast invertase in aqueous two phase systems using hybrid group method data handling neural network

A hybrid GMDH neural network model has been developed in order to predict the partition coefficients of invertase from Baker's yeast. ATPS experiments were carried out changing the molar average mass of PEG(1500–6000 Da), p H(4.0–7.0), percentage of PEG(10.0–20.0 w/w), percentage of MgSO_4(8.0–16.0 w/w), percentage of the cell homogenate(10.0–20.0 w/w) and the percentage of MnSO_4(0–5.0 w/w) added as cosolute. The network evaluation was carried out comparing the partition coefficients obtained from the hybrid GMDH neural network with the experimental data using different statistical metrics. The hybrid GMDH neural network model showed better fitting(AARD = 32.752%) as well as good generalization capacity of the partition coefficients of the ATPS than the original GMDH network approach and a BPANN model. Therefore hybrid GMDH neural network model appears as a powerful tool for predicting partition coefficients during downstream processing of biomolecules.     

Experimental studies and artificial neural network modeling of surface tension of aqueous sodium L-prolinate solutions and piperazine blends

The surface tension study is very crucial for the design of CO2 gas absorption contacting equipment. The significance of the surface tension has been increasing due to its consideration in various technological fields. This property influences the mass transfer and hydrodynamics of gas absorption systems, mainly multiphase systems, in which the interface between gas and liquid exists. Therefore, in this study, surface tension of aqueous solutions of sodium L-prolinate(SP) and piperazine(PZ) blends were measured at ten different temperatures from(298.15 to 343.15) K. The SP mass fractions were 0.10, 0.20, and 0.30; while the mass fractions of PZ were 0.02 and 0.05. The experimental results showed that the surface tension increase with increasing the mass fractions of SP and PZ in aqueous blends, and decrease linearly with rising temperature. The experimental data of surface tension were correlated by two empirical correlations as a function of temperature and mass fractions for estimating the predicted data using the optimized correlation coefficients. Moreover, the modeling of surface tension data was carried out using Artificial Neural Network(ANN) approach. The results obtianed from ANN modeling were compared with applied empirical correlation. It was found that the ANN approach outperformed the empirical correlation used in this study. Besides, a quantitative analysis of variation(ANOVA) was performed in order to determine the significance of data. The surface tension of aqueous SP and SP + PZ was also compared with various conventional solvents.     

Tribological behavior prediction of friction materials for ultrasonic motors using Monte Carlo-based artificial neural network

In this article, the relationship of complexity, diversity, and uncertainty between components and tribological properties of friction materials based on a Monte Carlo-based artificial neural network (MC-ANN) model was predicted precisely. Meanwhile, the grey relational analysis was applied to figure out weight of factors, optimize formulation design, and calculate nonlinear dependency of ingredients. The accuracy of model was studied by comparing experimental and simulated values on the basis of statistical methods (root-mean-squared error). It was found that the model exhibited an excellent performance in predicting and fitting effect. Moreover, comprehensive analysis of weight indicated that nano-SiO₂ and mica exerted a significant role in improving the friction stability and wear resistance. According to different contents of each ingredient, the corresponding friction coefficient and specific wear rate could be obtained by virtue of a well-trained MC-ANN model without experiments, which saved a lot of time and money. It can be expected that the results of this work will extend the current research and pave a route for further in-depth studies of friction materials. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 47157.     

Development of an artificial neural network correlation for prediction of hold-up of slurry transport in pipelines

In the literature, very few correlations have been proposed for hold-up prediction in slurry pipelines. However, these correlations fail to predict hold-up over a wide range of conditions. Based on a databank of around 220 measurements collected from the open literature, a correlation for hold-up was derived using artificial neural network (ANN) modeling. The hold-up for slurry was found to be a function of nine parameters such as solids concentration, particle dia, slurry velocity, pressure drop and solid and liquid properties. Statistical analysis showed that the proposed correlation has an average absolute relative error (AARE) of 2.5% and a standard deviation of 3.0%. A comparison with selected correlations in the literature showed that the developed ANN correlation noticeably improved prediction of hold-up over a wide range of operating conditions, physical properties and pipe diameters. This correlation also predicts properly the trend of the effect of the operating and design parameters on hold-up.     

Prediction of the pH and the temperature-dependent swelling behavior of -alginate hydrogels by artificial neural networks

This paper considers the possibility of using artificial neural network models to identify model for swelling behavior as new techniques. Multi-layer feed-forward, radial basis function and generalized regression neural network models were employed to predict the swelling behaviors of Ca²⁺-alginate hydrogels under different environmental conditions of pH and temperature. The results show that an excellent correlation between the experimental and predicted swelling ratios was obtained by the artificial neural networks. Generalized regression neural network has a better performance than the other neural network models. The absolute mean error, the determination coefficient and the standard error of prediction were used as performance criteria. In addition, the performances of the neural network models are significantly superior compared with those of second-order swelling kinetics, quadratic and cubic models of response surface methodology.     

Thermal performance prediction of wickless heat pipe with Al2O3/water nanofluid using artificial neural network

A wickless heat pipe (WHP) comprises of an evacuated-close tube filled with an appropriate amount of working fluid. In this study, the effect of Al₂O₃/water nanofluid as the working media on thermal performance of WHP investigated and compared with pure water by designing an optimized Artificial Neural Network (ANN). ANN trained with the collected test data obtained from experimental setup and validated. Multilayer Perceptron configuration (MLP) adopted for the ANN. The MLP architecture consists of four input nodes representing the parameters; input power, volume concentration of nanofluid, filling ratio and mass rate in condenser section, and a single output node representing the thermal efficiency of WHP. According to sensitivity analysis results, volume concentration is the most significant parameter which affects the WHP performance. Also, since the ANN test output data are sufficiently close to experimental one, it can be inferred that the ANN model can be applied to accurately model WHP thermal performance.     

Operation simulation of a recycled electrochemical ozone generator using artificial neural network

The present work has focused on the modeling and simulation of a recycled ozone generator system via electrochemical oxidation of water. To produce ozone, a Pyrex glass electrochemical reactor, comprised of two separate half-cell by Nafion 117 membrane was applied. The applied anode and cathode electrodes were Ti/Sn-Sb-Ni and platinized titanium, respectively. The modeling and simulation of the reactor operation were done via artificial neural network (ANN) technique. In this regard, four important operational parameters (i.e. electrolyte concentration, applied voltage, flow rate and electrolysis time) and the generated ozone concentration were considered as the independent inputs and the network output, respectively. To find out the best model, six numbers of three-layered ANNs with different functions were constructed and optimized. Best simulation was related to a model, consist of Levenberg–Marquardt Back propagation learning algorithm (trainlm) and tangent sigmoid (tansig) as transfer function in the both hidden and output layers. Also, application of 10 hidden neurons and 80 iterations for the network calibration caused to satisfy the network training while overfitting was prevented. The K-fold cross-validation method, employed for the model evaluation, showed high correlation coefficient (0.9936) and low mean square error (3.58 × 10⁻⁴) for the testing data. Sensitivity analysis indicated order of relative importance the operational parameters on the ozone production as: time > [electrolyte] > voltage > flow rate.     

Gasoline quality prediction using gas chromatography and FTIR spectroscopy: An artificial intelligence approach

This paper reports on analysis of 45 gasoline samples with different qualities, namely, octane number and chemical composition. Measurements of data from gas chromatography and IR (FTIR) spectroscopy are used to gasoline quality prediction and classification. The data were processed using principal component analysis (PCA) and fuzzy C means (FCM) algorithm. The data were then analyzed following the neural network paradigms, hybrid neural network and support vector machines (SVM) classifier. The IR spectra were compressed and de-noised by the discrete wavelet analysis. Using the hybrid neural network and multi linear regression method (MLRM), excellent correlation between chemical composition of the gasoline samples and predicted value of the octane number was obtained. About 100% correct classification for six different categories of the gasoline was achieved, each of which has different qualities.     

Maximum solid concentrations of coal water slurries predicted by neural network models

The nonlinear back-propagation (BP) neural network models were developed to predict the maximum solid concentration of coal water slurry (CWS) which is a substitute for oil fuel, based on physicochemical properties of 37 typical Chinese coals. The Levenberg-Marquardt algorithm was used to train five BP neural network models with different input factors. The data pretreatment method, learning rate and hidden neuron number were optimized by training models. It is found that the Hardgrove grindability index (HGI), moisture and coalification degree of parent coal are 3 indispensable factors for the prediction of CWS maximum solid concentration. Each BP neural network model gives a more accurate prediction result than the traditional polynomial regression equation. The BP neural network model with 3 input factors of HGI, moisture and oxygen/carbon ratio gives the smallest mean absolute error of 0.40%, which is much lower than that of 1.15% given by the traditional polynomial regression equation.     

人工神经网络紫外光谱方法测定牙周康胶囊的含量

应用人工神经网络误差反向传播的方法对紫外吸收光谱重叠的牙周康胶囊进行组分不经分离的含量测定,网络隐蔽层的节点数为5,输入节点数为10时,甲硝唑和芬布芬的平均回收率分别为99.7%和99.9%,RSD分别为0.42%和0.45%.测定方法结果准确,操作简单、方便.对紫外吸收光谱重叠的药物来说,该法提供了一种含量测定的新途径.