Analysis of ultrasonic velocity in refrigerants using artificial neural network

Several researchers have reported numerous measurements on ultrasonic velocity as a function of temperature and pressure using various experimental techniques. A large amount of experimental data is required in order to obtain accurate results for the chemical substances used. The present article explores the evaluation of ultrasonic velocity as a function of molecular weight, temperature and pressure using an artificial neural network (ANN) in six refrigerants. The network so developed predicts the ultrasonic velocity successfully. Statistical analysis of the results was performed using standard deviation (%) and relative average deviation. The correlation coefficient in our analysis was found to be 0.9999. The trained weights, obtained from ANN, are further employed to form equations to predict ultrasonic velocity at other temperatures and pressures.     

Empirical correction to the Peng–Robinson equation of state for the saturated region

This work presents an empirical correction to improve the Peng–Robinson equation of state (PR EOS) for representing the densities of pure liquids and liquid mixtures in the saturated region using the volume translation method. A temperature-dependent volume correction is employed to improve the original PR EOS so that it can match the true critical point of pure fluids. The volume correction is generalized as a function of the critical parameters and the reduced temperature. The volume translation PR (VTPR) EOS with the generalized volume correction accurately represents the saturated liquid densities for different polar and non-polar fluids, including alkanes, cycloparaffins, halogenated hydrocarbons, olefins, cyclic olefins, aromatics and inorganic molecules. The average relative deviations for 91 pure compounds was 1.37%. The generalized VTPR EOS was also used to predict the saturated liquid density of 53 binary mixtures with a relative deviation of 0.98%. The generalized VTPR EOS can also be extended to other materials. The accuracy of the generalized VTPR EOS compares well with other methods and equations of state.     

Quantitative structure chromatography relationships in reversed-phase high performance liquid chromatography: Prediction of retention behaviour using theoretically derived molecular properties

Summary The use of theoretically calculated molecular properties as predictors for retention in reversed-phase HPLC has been explored. HPLC retention times have been measured for a series of 47 substituted aromatic molecules in three solvent mixtures and steric and electronic properties of these compounds have been derived using semi-empirical molecular orbital and empirical theoretical methods. A subset of the experimental data (a training set) was used to derive property-retention time relationships and the remaining data were then used to test the predictive capability of the methods.Good retention time prediction was possible using derived regression equations for individual solvents and after including solvent parameters it was possible to predict retention for all solvents using a single equation. This method showed that the most useful properties were calculated log P and the calculated dipole moment of the solutes, and the calculated solvent polarisability. In addition, 90% of the data were used to train an artificial neural network and the remaining 10% of the data used to test the network; excellent prediction was obtained, the neural network approach being as successful as the regression analysis.     

数字图像法测定养殖水中的孔雀石绿

建立一种简单、可靠的养殖水中孔雀石绿的数字图像检测方法。以1-己基-3-甲基咪唑四氟硼酸盐离子液体富集水样品,再用手机拍照获取样品信息,最后用数字图像结合多层感知器神经网络定量分析孔雀石绿的含量。该法测定结果的相对标准偏差不大于6%(n=5),加标回收率为97.8%~103.0%。该方法可用于养殖水中孔雀石绿的含量测定。     

Prediction of coefficients of the Langmuir adsorption isotherm using various artificial intelligence (AI) techniques

Adsorption is a process that utilizes porous solid materials to separate some solutes from gas or liquid mixtures. The extent of this separation is often determined using the adsorption isotherms, i.e., semi-empirical correlation for relating the amount of adsorbed substances by the solid medium to its associated concentration in fluid phase at constant temperature. Prior to employing an adsorption isotherm, its coefficients should be adjusted using experimental data of a considered adsorption system. In this study, the coefficients of Langmuir model have been predicted using various types of artificial neural networks (ANNs), support vector machines, and adaptive neuro fuzzy interface systems, and coupled scheme of ANN-genetic algorithm. The employed ANN types are multi-layer perceptron neural network (MLPNN), radial basis function neural network, cascade feedforward neural network, and generalized neural network. The considered coefficients tried to be modeled as functions of temperature, pH, adsorbent density, and adsorbate molecular weight. Predictive accuracies of the AI techniques have been compared utilizing different statistical indices such as correlation coefficient (R²), mean square error, and absolute average relative deviation (AARD%). The results indicated that MLPNN was the most accurate model for predicting the coefficients of Langmuir isotherm, due to its AARDs of 24.64 and 22.40% for the first and second coefficients, respectively.     

基于QSAR模型的有机磷化合物毒性预测

随着有机磷化合物(OPs)的广泛应用,其在越来越多的环境介质中被检测出来。大多数OPs具有毒性,但人们缺乏快速且有效的预测手段来对毒性进行评估。本文将结合E-Dragon软件计算的分子描述符,采用不同的QSAR模型对36个OPs的毒性进行预测。文中采用后退法作为描述符筛选方法,以均方根误差(RMSE)作为评价标准,共找到14个对线性核函数支持向量机(SVM)模型贡献较大的描述符;在最终得到的SVM模型交叉验证结果中,计算值与实际值的相关系数为0. 913,均方根误差为0. 388;外部测试验证结果中,平均相对误差为9. 10%。此外,采用多元线性回归(MLR)、人工神经网络(ANN)以及偏最小二乘回归(PLS)模型对OPs的毒性进行预测,交叉验证结果显示,三个模型的计算值与实际值的相关系数分别为0. 878、0. 686与0. 620,没有SVM模型的预测能力好。因此采用线性核函数的SVM模型对OPs进行毒性预测是一个行之有效的方法。     

The correlations of the enthalpy of vaporization and the surface tension of molecular liquids

Correlation relations based on Stefan's rule, which defined dependence between the enthalpy of vaporization, the surface tension, the molar volume and the molar mass of a substance, were obtained. For development of the correlation equations two computational procedures were used: a method of the least squares and a method of artificial neural networks. The method of artificial neural networks was shown to give somewhat better results than the linear least-squares procedure. The average deviation of the calculated values from the experimental ones did not exceed 6% for training set of substances and 10% for control set (the method of the least squares). For the method of artificial neural networks it is 3% and 8%, respectively.     

Simultaneous determination of rifampicin and isoniazid by continuous-flow chemiluminescence with artificial neural network calibration

In this paper a continuous-flow chemiluminescence (CL) system with artificial neural network calibration is proposed for simultaneous determination of rifampicin and isoniazid. This method is based on the different kinetic spectra of the analytes in their CL reaction with alkaline N-bromosuccinimide as oxidant. The CL intensity was measured and recorded every second from 1 to 300 s. The data obtained were processed chemometrically by use of an artificial neural network. The experimental calibration set was 20 sample solutions. The relative standard errors of prediction for both analytes were approximately 5%. The proposed method was successfully applied to the simultaneous determination of rifampicin and isoniazid in a combined pharmaceutical formulation.     

弹性反传神经网络法预测烷基苯的疏水性常数

 介绍了应用人工神经网络预测烷基苯分子疏水性常数的方法。该法同传统方法相比 ,具有操作简便 ,适用范围广的特点。基于误差反传神经网络 ,建立了分子连接性指数 (χ)、范德华表面积 (Aw)和疏水性常数 (logP)之间的数学模型。应用该模型对烷基苯分子的疏水性常数进行预测 ,其平均相对偏差为 0 6 7%。并且通过与标准误差反传算法和自适应学习算法相比较 ,发现弹性反传算法具有训练速度快 ,参数选择简单的特点。     

Artificial neural networks applied to potentiometric titration of multi-component polybasic acid mixtures

A three-layer artificial neural network model with back-propagation of error is used to treat potentiometric acid-base titration data for estimating the concentrations of individual components in polybasic weak acid mixtures. The network's architecture and parameters were optimized and an empirical rule for dynamically adjusting the learning rate is put forward to improve the network's performance. Satisfactory prediction results were obtained for three-component samples containing maleic acid, propandioic acid and succinic acid with an average relative error of 4.5%.     

Forecasting of water thermal conductivity enhancement by adding nano-sized alumina particles

Operating fluids play an important role in heat transfer equipment. Water is inexpensive popular operating fluid with extensive applications, but its thermophysical properties are not good enough, especially for high temperature processes. Therefore, modification of its inherent characteristics by adding nano-sized solid particles found high popularities. Thermal conductivity is one of the most important thermophysical properties of an operating fluid in relatively all energy-based processes. Variation of thermal conductivity of nanofluids with different operating conditions is required to be understood in such processes. Therefore, the focus of this study is concentrated on modeling of thermal conductivity of water-alumina nanofluids using four different smart paradigms. Multilayer perceptron, radial basis function, cascade feedforward, and generalized regression neural networks are employed for the considered task. The best structure of these paradigms is determined, and then, their accuracies are compared using different statistical indices. Accuracy analyses confirmed that the generalized regression neural network outperforms other considered smart methodologies. It predicted more than 280 experimental datasets with excellent absolute average relative deviation?=?0.71%, mean square error?=?0.0006, root mean square error?=?0.023 and regression coefficient (R²)?=?0.9675. In the final stage, the proposed paradigm is used for investigation of the effect of influential parameters on the thermal conductivity of water-alumina nanofluids. This type of accurate and straightforward paradigm can broaden our insight about thermal behavior of homogeneous suspension of nano-size alumina particles in water.

     

Headspace-single drop microextraction (HS-SDME) in combination with high-performance liquid chromatography (HPLC) to evaluate the content of alkyl- and methoxy-phenolic compounds in biomass smoke

The content of ten phenolic compounds present in four different biomass smoke materials: rock rose (Cistus monpelienisis), prickly pear (Opuntia ficus indica), pine needles (Pinus canariensis), and almonds skin (Prunus dulcis), have been evaluated. The sampling method mainly consisted of a trap alkaline solution to solubilize the phenols, and was optimized by an experimental design. Average sampling efficiencies of 78.1% and an average precision value of 10.6% (as relative standard deviation, RSD), were obtained for the selected group of phenols. The trapped phenolates were further analyzed by a headspace-single drop microextraction (HS-SDME) procedure, in combination with high-performance liquid chromatography (HPLC) with UV detection. The optimum variables for the HS-SDME method were: 1-decanol as extractant solvent, 3.5 μL of microdrop volume, 2 mL of sample volume, a pH value of 2, saturation of NaCl, an extraction temperature of 60 °C, and an extraction time of 25 min. The optimized HS-SDME method presented detection limits ranging from 0.35 to 5.8 μg mL⁻¹, RSD values ranging from 0.7 to 7.4%, and an average relative recovery (RR) of 99.8% and an average standard deviation of 5.2. The average content of phenolic compounds in the biomass materials studied were 70, 161, 206 and 252 mg kg⁻¹ of biomass for prickly pear, almonds skin, rock rose, and pine needles, respectively. The main components of the smokes were vanillin, phenol and methoxyphenols, in all smoking materials studied.     

Semi-empirical correlation of solid solute solubility in supercritical carbon dioxide: Comparative study and proposition of a novel density-based model

A comprehensive data set on experimental solubility of 210 solid solutes in supercritical CO₂ counting 5550 data points has been used for comparison of the correlation performance of 21 empirical models. On the basis of the comparison results a new eight-parameter density-based model has been proposed. The comparison shows that the three-parameter models are the least accurate. The results also show that models that relate the logarithm of the solubility to the logarithm of solvent density and temperature are more accurate than models that include the pressure. When comparing the overall correlating performance in terms of average absolute relative deviation the proposed model is by far the best with an average absolute relative deviation lying in the range 0.17–81.99% and an average value of 8.88%.     

The estimation of kinematic viscosity of petroleum crude oils and fractions with a neural net

This paper illustrates how a neural net, a three-layered perceptron, can be trained to estimate viscosities for undefined crude oils and fractions. Three Saudi-Arabian crude oils were employed to illustrate the use of the neural net to approximate the relation in a very simple manner with no need for a priori knowledge of the system. This empirical correlation was accurate to 98.74% if tested on experimental data not used during training, which is a fivefold improvement on average results obtained by two recently-proposed equations to estimate the viscosity of hydrocarbons. Although the neural net equation seems to be less transparent than former correlations, a method called backward analysis is proposed to analyze the weight matrix of the neural net in order to gain valuable insight into the viscosity system.     

Modeling and prediction of activity coefficient ratio of electrolytes in aqueous electrolyte solution containing amino acids using artificial neural network

Modeling and prediction of activity coefficients of electrolytes and biomolecules is a key to developing the separation and purification processes of biomolecules. In this paper the systems containing amino acids or peptide + water + one electrolyte (NaCl, KCl, NaBr, KBr) are modeled by different types of neural networks and an artificial neural network (ANN) is designed that can predict the mean ionic activity coefficient ratio of electrolytes in presence and in absence of amino acid in different mixtures better than the common polynomial equations proposed for this kind of predictions. It was found that the designed ANN which is a multi-layer perceptron (MLP) type network can be better trained than other types of neural network.The root mean square deviation (RMSD) of the designed neural network in prediction of the mean ionic activity coefficient ratio of electrolytes is less than 0.005 and proves the effectiveness of the ANN in correlation and prediction of activity coefficients in the studied mixtures.     

Boiling Point of a Set of Alkanes,Alcohols and Chloroalkanes: QSAR with Atom Type Electrotopological State Indices Using Artificial Neural Networks

Abstract

The normal boiling point is modeled for a set of 372 saturated compounds, including 154 alkanes, 108 alcohols and 110 (poly)chloroalkanes. The newly introduced atom type electrotopological state indices serve as the structure variables and artificial neural networks (with back propagation of error) are used for the analysis. A network with a 6:7:1 architecture produces an average relative error of 0.97% for the whole data set, including the 21% of the data used as the test set. The mean absolute error (MAE) for this model is 4.00 for the whole set, corresponding to an rms error of 5.41; for the test set the MAE is 4.03 with an rms of 5.23. The low error on the test set indicates that this model has predictive power.