Application of artificial neural networks in multifactor optimization of an FIA system for the determination of aluminium

A methodology based on the coupling of experimental design and artificial neural networks (ANNs) is proposed in the optimization of a new flow injection system for the spectrophotometric determination of Al(III) with Arsenazo DBM, which has for the first time been used as chromogenic reagent in the quantitative analysis of aluminium. An orthogonal design is utilized to design the experimental protocol, in which three variables are varied simultaneously. Feedforward-type neural networks with faster back propagation (BP) algorithm are applied to model the system, and then optimization of the experimental conditions is carried out in the neural network with 3-7-1 structure, which have been confirmed to be able to provide the maximum performance. In contrast to traditional methods, the use of this methodology has advantages in terms of a reduction in analysis time and an improvement in the ability of optimization. The method has been applied to the determination of Al(III) in steel samples and provided satisfactory results.     

Application of artificial neural networks in multifactor optimization of an FIA system for the determination of aluminium

A methodology based on the coupling of experimental design and artificial neural networks (ANNs) is proposed in the optimization of a new flow injection system for the spectrophotometric determination of Al(III) with Arsenazo DBM, which has for the first time been used as chromogenic reagent in the quantitative analysis of aluminium. An orthogonal design is utilized to design the experimental protocol, in which three variables are varied simultaneously. Feedforward-type neural networks with faster back propagation (BP) algorithm are applied to model the system, and then optimization of the experimental conditions is carried out in the neural network with 3-7-1 structure, which have been confirmed to be able to provide the maximum performance. In contrast to traditional methods, the use of this methodology has advantages in terms of a reduction in analysis time and an improvement in the ability of optimization. The method has been applied to the determination of Al(III) in steel samples and provided satisfactory results. Received: 26 May 1999 / Revised: 29 July 1999 / Accepted: 17 August 1999     

化学计量学在毛细管电泳中的应用

综述了最优化方法，多元校正方法、人工神经网络、曲线分辨、信号处理等化学计量学方法在毛细管电泳分离分析中的应用，展望了化 社量学在毛细管电泳中的应用前景，引用参考文献55篇。     

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.     

Direct and inverse neural network modeling in free radical polymerization

The first part of this paper reviews of the most important aspects regarding the use of neural networks in the polymerization reaction engineering. Then, direct and inverse neural network modeling of the batch, bulk free radical polymerization of methyl methacrylate is performed. To obtain monomer conversion, number and weight average molecular weights, and mass reaction viscosity, separate neural networks and, a network with multiple outputs were built (direct neural network modeling). The inverse neural network modeling gives the reaction conditions (temperature and initial initiator concentration) that assure certain values of conversion and polymerization degree at the end of the reaction. Each network is a multi-layer perceptron with one or two hidden layers and a different number of hidden neurons. The best topology correlates with the smallest error at the end of the training phase. The possibility of obtaining accurate results is demonstrated with a relatively simple architecture of the networks. Two types of neural network modeling, direct and inverse, represent possible alternatives to classical procedures of modeling and optimization, each producing accurate results and having simple methodologies.     

分析化学中的非线性校准

对分析化学中的非线性校准作了系统的讨论，对近年来分析化学中非线性及有关问题的方法和研究进展作了较全面的评述，各种非线性校准方法可不同程度地成功地用于解决非线性问题，迄今为止，人工神经网络（ＡＮＮ）被认为是解决非线性校准问题的最优方法之一。     

Ethyl alcohol production optimization by coupling genetic algorithm and multilayer perceptron neural network

In this present article, genetic algorithms and multilayer perceptron neural network (MLPNN) have been integrated in order to reduce the complexity of an optimization problem. A data-driven identification method based on MLPNN and optimal design of experiments is described in detail. The nonlinear model of an extractive ethanol process, represented by a MLPNN, is optimized using real-coded and binary-coded genetic algorithms to determine the optimal operational conditions. In order to check the validity of the computational modeling, the results were compared with the optimization of a deterministic model, whose kinetic parameters were experimentally determined as functions of the temperature.     

A comparison between neural network method and semi empirical equations to predict the solubility of different compounds in supercritical carbon dioxide

Accuracy of seven semi empirical equations for the estimation of solubility of 30 different compounds in supercritical carbon dioxide has been compared with a new neural network method. To base this comparison on a fair basis, a unique set of experimental data was used for both optimization of semi empirical equations’ parameters and training, validation and testing of neural network. Results showed that neural network method with an average relative deviation of about 5.3% was more accurate than the best semi empirical equation with an average relative deviation of about 15.96% for same compounds. It was also found that the average relative deviation of semi empirical equations varies sharply among different compounds, while this quantity is less dependent on material type for neural network method.     

Smart Determination of Difference Index for Asphaltene Stability Evaluation

Precipitation and deposition of asphaltene during different stages of petroleum production is recognized as problematic in oil industry because of the increase in production cost and the inhibition of a consistent flow of crude oil in different medium. Numerous correlations have been developed to determine asphaltene stability in crude oil. In this study, a novel ONN method was used to estimate difference index from SARA fraction data for rapid, accurate, and cost-effective determination of asphaltene stability. Neural networks are highly in danger of trapping in local minima. To eliminate this flaw, a hybrid genetic algorithm-pattern search technique was used instead of common back-propagation algorithm for training the employed neural network. A comparison between neural network and optimized neural network indicated superiority of optimized neural network.      

Predicting cis/trans structure of alkene based on infrared spectra.

The application of chemometrics to analyze the information of the cis/trans structure of alkenes in infrared spectra (IR) is introduced. For data from the OMNIC IR spectral database, two feature selection methods, Fisher ratios and genetic algorithm-partial least squares (GA-PLS), and two classification methods, support vector machine (SVM) and probabilistic neural network (PNN), have been used to obtain optimization classifiers. At last, some spectra from other IR databases are used to evaluate the optimization classifiers. It has been demonstrated that both the SVM and PNN optimization classifiers could give preferable predictive results about the cis and trans structures of alkene.     

Estimation of solid vapor pressures of pure compounds at different temperatures using a multilayer network with particle swarm algorithm

Solid vapor pressures (P^S) of pure compounds have been estimated at several temperatures using a hybrid model that includes an artificial neural network with particle swarm optimization and a group contribution method. A total of 700 data points of solid vapor pressure versus temperature, corresponding to 70 substances, have been used to train the neural network developed using Matlab. The following properties were considered as input parameters: 36 structural groups, molecular mass, dipole moment, temperature and pressure in the triple point (upper limit of the sublimation curve), and the limiting value P^S → 0 as T → 0 (lower limit of the sublimation curve). Then, the solid vapor pressures of 28 other solids (280 data points) have been predicted and results compared to experimental data from the literature. The study shows that the proposed method represents an excellent alternative for the prediction of solid vapor pressures from the knowledge of some other available properties and from the structure of the molecule.     

Application of artificial neural networks in multifactor optimization of an on-line microwave FIA system for catalytic kinetic determination of ruthenium (III)

A methodology based on the coupling of experimental design and artificial neural networks (ANNs) is proposed in the optimization of a flow injection system for the spectrophotometric determination of Ru (III) with m-acetylchlorophosphonazo (CPA-mA), which has been for the first time used for the optimization of high-performance capillary zone electrophoresis (J. Chromatogr. A 793 (1998) 317). And since it has been applied in many other regions like micellar electrokinetic chromatography, ion-interaction chromatography, HPLC, etc. (J. Chromatogr. A 850 (1999) 345; J. Chromatogr. A 799 (1998) 35; J. Chromatogr. A 799 (1998) 47). An orthogonal design is utilized to design the experimental protocol, in which five variables are varied simultaneously (Anal. Chim. Acta 360 (1998) 227). Feedforward-type neural networks with extended delta-bar-delta (EDBD) algorithm are applied to model the system, and the optimization of the experimental conditions is carried out in the neural network with 5-5-1 structure, which have been confirmed to be able to provide the maximum performance. In contrast to traditional methods, the use of this methodology has advantages in terms of a reduction in analysis time and an improvement in the ability of optimization. Under the optimum experimental conditions, Ru (III) can be determined in the range 0.040-0.60 mug ml(-1) with detection limit of 0.03 mug ml(-1) and the sampling frequency of 34 h(-1). The method has been applied to the determination of Ru (III) in refined ore as well as in secondary alloy and provided satisfactory results.     

Neural network studies. 4. Introduction to associative neural networks

Associative neural network (ASNN) represents a combination of an ensemble of feed-forward neural networks and the k-nearest neighbor technique. This method uses the correlation between ensemble responses as a measure of distance amid the analyzed cases for the nearest neighbor technique. This provides an improved prediction by the bias correction of the neural network ensemble. An associative neural network has a memory that can coincide with the training set. If new data becomes available, the network further improves its predictive ability and provides a reasonable approximation of the unknown function without a need to retrain the neural network ensemble. This feature of the method dramatically improves its predictive ability over traditional neural networks and k-nearest neighbor techniques, as demonstrated using several artificial data sets and a program to predict lipophilicity of chemical compounds. Another important feature of ASNN is the possibility to interpret neural network results by analysis of correlations between data cases in the space of models. It is shown that analysis of such correlations makes it possible to provide "property-targeted" clustering of data. The possible applications and importance of ASNN in drug design and medicinal and combinatorial chemistry are discussed. The method is available on-line at http://www.vcclab.org/lab/asnn.     

级联神经网络用于单扫描示波极谱信号的测定

将改进小波神经网络与BP神经网络相结合,提出一种新的混级联神经网络结构,用于单扫描示波极谱信号的同时测定。通过对网络结构的优化和网络参数的调整,加快了训练速度,提高了预测的准确度。用该法对邻、间硝基氯苯混合样进行了预测,结果满意。对级联神经网络法与单一BP神经网络法的预测结果进行了比较,表明级联神经网络优于单一BP神经网络。     

Chromatographic Behavior of Fosinopril Sodium and Fosinoprilat Using Neural Networks

In this paper, the chromatographic characterization of fosinopril sodium and fosinoprilat is presented. The first stept was pK _a determination for the active substance and its degradation product using RP-LC. It was followed by optimization employing the combination of experimental design and artificial neural networks. For the definition of input and output variables, the central composite design for three factors was built. Back propagation algorithm was applied to model the system, and then the optimization of the experimental conditions was carried out in the neural network with 3-8-2 structure, which confirmed to be able to provide the maximum performance. From the method optimization, the most appropriate experimental conditions for fosinopril sodium and fosinoprilat analysis were extracted. The optimized method was validated and applied in the quality control of tablets and for forced degradation studies.     

Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network

Coal ash fusion temperature is important to boiler designers and operators of power plants. Fusion temperature is determined by the chemical composition of coal ash, however, their relationships are not precisely known. A novel neural network, ACO-BP neural network, is used to model coal ash fusion temperature based on its chemical composition. Ant colony optimization (ACO) is an ecological system algorithm, which draws its inspiration from the foraging behavior of real ants. A three-layer network is designed with 10 hidden nodes. The oxide contents consist of the inputs of the network and the fusion temperature is the output. Data on 80 typical Chinese coal ash samples were used for training and testing. Results show that ACO-BP neural network can obtain better performance compared with empirical formulas and BP neural network. The well-trained neural network can be used as a useful tool to predict coal ash fusion temperature according to the oxide contents of the coal ash.