人工神经网络在气相色谱保留值预测上的应用

应用人工神经网络对气相色谱Ｋｏｖａｔｓ保留指数进行多点预测研究。基于人工神经网络的典型模型（ＢＰ网络）,采用文献中的数据,建立了反映溶质的Ｋｏｖａｔｓ指数与溶质的溶剂化参数以及其与固定相的相参数之间关系的数学模型,并采用多元性回归方法和人工神经网络对溶质的Ｋｏｖａｔｓ指数进行了预测研究。     

气相色谱与液相色谱保留值的换算方法

根据色谱热力学理论,在色谱保留值公式统一形式的基础上导出了气相色谱保留系数（I）与反相液相色谱保留公式参数a,c之间的关系式,证明结构类似化合物的a,c值与保留指数呈线性关系,同时存在氢键作用能、偶极矩作用的影响,从而提出了色相色谱与反相液相色谱保留值换算的方法;该理论为氯代芳烃的文献数据所证实。     

人工神经网络方法预测气相色谱保留指数

用误差反向传播（ＢＰ）的人工神经网络（ＡＮＮ）模型及分子结构描述码作为输入特征参数，预测气相色谱保留指数．研究了链烷烃、环脂烃、烯烃及醇、酯、醚等３００个化合物，预测结果平均相对误差不大于２．８３％．     

从信息论指标预测氯代羟基苯甲醛的气相色谱保留值

分子结构与其保留值规律的研究是色谱热力学研究的主要内容。几十年来,许多色谱工作者为探索分子结构与色谱保留值之间的关系作了不懈努力。用分子的拓扑结构指标来关联化合物的气相色谱行为,是十分引人注目的一个方法。到目前为止,已经提出了多种拓扑结构指标。本文试图定义一种信息论指标,     

人工神经网络法预测炸药组分的色谱保留值参数

 以分子拓扑指数作为炸药组分的结构描述符 ,利用反向传播算法 (BP)人工神经网络 ,以Sigmoid函数为传递函数 ,分子连接性指数0 χ ,1χ ,2 χ与边邻接指数 (ε)为输入向量 ,反相高效液相色谱保留值参数logkw 和S为输出向量 ,将输入向量归一化至 - 3～ 3区间 ,输出向量归一化至 0～ 1区间 ,网络精度取 0 5 ,学习步长 η的初始值取0 2 ,动量因子α取 0 5 ,通过对 2 0种炸药的网络模型进行训练 ,建立了炸药分子结构与logkw 和S之间的定量模型。结果表明 ,该模型较好地反映了炸药分子结构与保留值之间的关系。     

硫醇的分子连接性指数与气相色谱保留值

硫醇的分子连接性指数与气相色谱保留值赵邦屯王利亚（洛阳师专化学系洛阳４７１０２２）关键词硫醇分子连接性指数气相色谱保留值中图分类号Ｏ６５７．７１有机化合物的色谱保留行为与其结构之间的定量关系研究一直是物理化学、分析化学和生物化学的研究对象之一。长期以...     

气相色谱保留值与疏水亲脂参数的关系

]本文利用数理统计方法,研究了分子结构参数与气相色谱保留行为的关系,重点考察了疏水亲脂参数logP以及结合诱导效应指数F和分子连通性指数1X,对于极性和非极性物质色谱保留值的不同贡献。并通过对保留值的预测,证明了它们的密切相关性。     

溶质在气相色谱中进样量和保留值关系的方程

考虑到气相中溶质分子和其它成分在固定相上的竞争吸附作用,提出了一个描述溶质在气相色谱中进样量和保留值的关系式.由此方程可以获得两个描述色谱体系特征的重要参数:溶质和其它成分在固定相表面竞争吸附的热力学平衡常数Ka和单位体积固定相所能吸附溶质的量NmS.当其它参数给定时,Ka的大小直接决定溶质进样量与保留值关系式的性质.通过试验对此方程进行了初步验证.     

气相色谱中保留值与进样量的关系

提出了测量气相色谱中吸附等温线的新方法，用不同进样量下测定的容量因子计算平衡时气-固两相组分浓度。利用建立的方法分别测量了正-己烷、正-壬烷和正-十一烷在邻苯二甲酸二辛酯(DOP)、阿皮松-L(Apiezon)和β，β′-氧二丙腈(ODPN)柱上的吸附等温线，讨论了色谱峰形状与吸附等温线的对应关系。研究了气相色谱中进样量对保留值的影响，利用佛伦德利希(Freundlich)吸附等温式导出了描述保留值与进样量关系的数学表达式。理论和实验证明，保留值与进样量具有良好的对数线性关系。     

定标粒子理论的气相色谱保留值方程

以定标粒子理论为基础,通过对溶质、溶剂分子间的相互作用加以系统研究,得到了描述溶质、溶剂分子参量及色谱条件对气相色谱过程中溶质容量因子的影响规律。通过实验证实了溶质容量因子在一定范围内与柱压近似呈线性关系,并验证了容量因子与柱温及加和性物性参量的关系。     

传感器阵列信号处理的人工神经网络方法

本文提出传感器阵列信号处理的人工神经网络方法,并以K~+/Ca~(2+)/NO_3~-/Cl~-阵列系统为对象,尝试了该方法的效果。结果表明,其拟合最大相对误差不超过7.4％,预测最大相对误差不超过6.9％。可见,其性能良好,可望成为各种传感器阵列信号处理的有用工具。     

人工神经网络在溶解度预测方面的应用

溶解度作为一项重要的物化指标,一直是化学学科的研究重点。然而,通过实验测量获得数据耗时费力,因此,科研人员建立了多种理论方法来进行估算,其中,人工神经网络因其能够关联复杂的多变量情况而受到广泛关注。本文综述了人工神经网络在物质溶解度预测方面的应用,介绍了应用最广泛的3种神经网络(BP神经网络、小波神经网络、径向基神经网络)的模型结构、预测方法和预测优势,探讨了神经网络的不足以及改进方法。文章最后对神经网络在物质溶解度预测方面的发展前景进行了展望。与其他方法相比,人工神经网络技术在物质溶解度预测方面具有预测结果精确度高、操作简单等特点,具有广阔的应用前景,但输入变量选择、隐含层节点数确定、避免局部最优等问题还需逐步建立系统的理论指导。     

Prediction of Programmed-temperature Retention Values of Naphthas by Artificial Neural Networks

Abstract

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.     

Prediction of Rheological Properties of Multi-Component Dispersions by Using Artificial Neural Networks

This article shows the ability of artificial neural network (ANN) technology for predicting the correlation between rheological properties of multi-component food model systems and their chemical compositions. Multi-component food model systems were made of whey protein isolate (WPI) (2, 4 wt%), Iranian tragacanth gum (TG) (Astragalus gossypinus) (0.5, 1 wt%) and oleic acid (5, 10% v/v). The input parameters of the neural networks (NN) were these chemical compositions, namely WPI and TG concentrations, and oleic acid volume fractions. The output parameters of the NN models were rheological properties of multi-component food model systems (flow and consistency indices, viscosity, loss and storage moduli). Results showed that, ANN with training algorithm of back propagation (BP) was the best one for the creation of nonlinear mapping between input and output parameters. The best topology was 3-10-5. The ANN model predicted the rheological properties of multi-component food model systems with average RMSE 4.529 and average MAE 3.018. These results show that the ANN can potentially be used to estimate rheological parameters of multi-component food model systems from chemical composition. This development may have significant potential to improve product quality control and reduce time and costs by minimizing the rheological experiments.     

Prediction of Chemical Inhibitors Efficiency for Reducing Deposition Thickness Using Artificial Neural Network

Prediction of efficiency of chemical inhibitors to mitigation of deposition thickness is a key to developing crude oil transportation process. In this work, a feed-forward artificial neural network (ANN) algorithm has been applied to predict the influence of the mitigation effect of ethylene-co-vinyl acetate (EVA) copolymer and its combination with chloroform (C), acetone (A), P-xylene (PX), and petroleum ether (PE) on the deposition thickness in the pipeline. An optimized three-layer feed-forward ANN model using properties of the oil pipeline such as: inlet oil temperature, environmental (coolant mixture) temperature, oil Reynolds numbers; properties of injected inhibitor such as molecular weight, boiling point, and amount of injection; and time is presented. Different networks are considered and trained using 62661 data sets; the accuracy of the network is validated by 20888 testing data sets. To verify the network generalization, 29 different experiment data sets of four different set of inhibitors have been considered. It is found that the proposed ANN model is an alternative to experimentation and predicts deposition thickness without experimentation, vast information, and tedious and time-consuming calculations.     

用人工神经网络预测催化精馏塔开工过程的研究

催化精馏是使化学反应过程和精馏分离过程结合在一起,是伴有化学反应的新型特殊精馏过程.“反应精馏”概念自20年代提出以来,从30年代到60年代初,研究都是对特定体系的工艺探索;70年代后,研究扩展到非均相催化反应体系,出现了非均相催化精馏过程,成为了反应精馏的一个重要分支;