咪唑类离子液体捕集CO_2性能的定量结构-性质相关性(QSPR)研究

CO_2是主要的温室气体,大量CO_2的存在严重影响着人类的生存环境和生态平衡,而咪唑型离子液体具有独特的气体溶解性,在CO_2的捕集分离中有很好的应用前景。基于定量结构-性质相关性(QSPR)原理,研究了咪唑类离子液体捕集CO_2的性能与其结构参数之间的内在定量关系。应用遗传算法获得与捕集量最为密切相关的一组描述符作为输入参数,随后,分别采用多元线性回归算法及支持向量机结合粒子群优化算法建立了咪唑类离子液体捕集CO_2的性能与其描述符之间的线性和非线性模型。多元线性回归算法得出训练集和测试集的复相关系数分别为0.765和0.814,支持向量机算法得出训练集和测试集的复相关系数分别为0.987和0.933。对预测模型进行了评价验证以及稳定性分析,结果表明,2种模型具有良好的稳定性能和预测能力。     

基于PSO-SVM的咪唑类离子液体捕集CO_2性能预测

CO_2是主要的温室气体,大量CO_2的存在严重影响着环境,而咪唑类离子液体具有独特的气体选择溶解性,在CO_2的捕集分离中有非常好的应用前景。基于支持向量机方法,结合粒子群优化算法(PSO-SVM)建立了咪唑类离子液体捕集CO_2性能的理论预测模型,该模型包含温度、压力、密度、黏度和表面张力5个主要参数。根据PSO算法,得到模型的最优参数为惩罚参数C=100,不敏感损失参数ε=11.699 7,核函数的宽度γ=0.279 2;SVM算法得出训练集的相关系数r=0.993,均方根误差RMSE=12.012,平均绝对误差AAE=4.117,测试集r=0.999,RMSE=4.766,AAE=3.028。对预测模型进行了评价验证以及稳定性分析,明确了咪唑类离子液体捕集CO_2性能的主要影响因素及其重要程度。     

基于支持向量机的脂肪族化合物急性毒性的QSAR研究

基于定量结构-活性相关性(QSAR)原理.研究了106种脂肪族化合物结构与其急性毒性LC50(半数致死浓度)之间的内在定量关系.应用遗传算法从大量结构参数中优化筛选出与LC50最为密切相关的4个参数作为分子描述符,分别采用支持向量机(SVM)方法和多元线性回归(MLR)方法建立了相应的QSAR预测模型.分别采用内部验证及外部验证的方式对所建模型性能进行了验证.研究表明,2种模型均具有较高的稳定性、预测能力及泛化性能.其中支持向量机模型对训练集和预测集样本的预测平均绝对误差分别为0.336和0.364,优于多无线性同归方法所得结果.     

烃类及其衍生物闪点、沸点的定量构效关系

基于定量结构一性质相关性（QSPR）原理,研究了烃类及其衍生物闪点、沸点与其分子结构间的内在定量关系。应用CODESSA软件计算384种烃类及其衍生物的分子结构描述符,建立了闪点和沸点的QSPR模型。用最佳多元线性回归（B．MLR）方法筛选得到的分子描述符建立了线性回归模型。用B-MLR方法所选择的5个描述符作为支持向量机（SVM）的输入建立了非线性模型。所有的化合物被分为训练集和测试集,对每个模型的训练集和测试集的复相关系数、交互验证系数、均方根误差等进行了计算,并用测试集对模型的预测能力进行检验,预测结果表明：预测值与实验值均符合良好,所建立的闪点模型稳健,泛化能力强,预测误差小,预测的效果令人满意,但沸点的模型预测效果有待加强。相比烃类物质的模型,加了衍生物的模型性能均有所下降。     

纳米金属氧化物对人体细胞毒性效应的构效关系研究

为建立高效的纳米金属氧化物细胞生物毒性构效关系预测模型，研究了20种纳米金属氧化物在不同生物条件下对人正常肺上皮细胞(BEAS-2B)和角质层细胞(HaCaT)的毒性效应构效关系，并首次将元素周期描述符(定量描述符)与试验条件参数(定性描述符)相结合，共同表征金属氧化物的纳米结构特征。在采用支持向量机-特征递归消除法(Support Vector Machine-Recursive Feature Elimination, SVM-RFE)筛选的最优描述符作为输入参数的基础上，分别应用支持向量机(Support Vector Machine, SVM)和随机森林(Random Forest, RF)2种高效的建模方法，建立纳米材料构效关系(Structure-Activity Relationships for Nanoparticals, Nano-SAR)预测模型。2个算法训练集的准确率(ACC)均大于0.9,内部验证准确率均大于0.7,测试集外部验证的准确率也均大于0.8,模型验证结果表明2个算法均具有良好的稳定性和较强的预测能力。对比2个算法研究结果表明，RF算法优于SVM算法...     

基于BP神经网络的二元混合液体自燃温度预测

为了给工业界提供一种快速预测二元混合液体自燃温度的有效途径,将试验所测不同组分及配比的168个二元混合液体的自燃温度作为期望输出,将基于电性拓扑状态指数(ETSI)理论、引入混合ETSI概念而计算出的9种原子类型所对应的混合ETSI作为输入,采用三层BP神经网络技术建立了根据原子类型混合ETSI来预测混合液体自燃温度的BP神经网络模型,并应用改进的Garson算法进行多参数敏感性分析。经模型评价验证及稳定性分析,得到训练集的决定系数R2为0.965,平均绝对误差MAE为11.892 K,测试集的交叉验证系数Q2ext为0.923,平均绝对误差MAE为15.530 K,发现该模型的预测性能优于已有的多元非线性回归(MNR)模型,表明BP神经网络模型具有较好的拟合能力和预测能力,对烷、醇类混合体系自燃温度的预测精度最佳。     

烃类沸点的定量构效关系研究

应用CODESSA软件计算296种烃类物质的分子结构描述符,分别用启发式回归（HM）和最佳多元线性回归（B-MLR）筛选计算出的所有分子描述符,并建立沸点的线性回归模型。用B-MLR方法筛选出的4个描述符作为支持向量机（SVM）的输入建立了非线性模型。预测结果表明：所建立的模型稳健,泛化能力强,预测误差小。非线性模型（R2=0.9905,RMSE=10.2295）的性能优于线性回归模型（HM：R2=0.9819,RMSE=14.0606;B-MLR：R2=0.9842,RMSE=13.1058）,预测效果令人满意。     

支持向量机对多环芳烃毒性的定量构效预测

为了实现多环芳烃(PAHs)毒性的有效预测,提出应用定量构效技术对多环芳烃的空气-正辛醇分配系数(KOA)和致癌性进行预测。应用分子描述符和试验值确立构效关系,采用支持向量机算法(SVM)和人工神经网络算法(ANN)分别建立了PAHs的KOA回归预测模型和致癌性分类预测模型。利用网格划分(GS)、遗传算法(GA)、粒子群算法(PSO)对SVM进行参数寻优。应用均方误差(MSE)、拟合决定系数R2和分类准确率(Accuracy)分别对模型进行了验证与评价。结果表明,最佳回归预测模型GS-SVR的MSE为0.059 7,R2为0.913 0;最佳分类预测模型GA-SVC的Accuracy为95%。研究表明:应用SVM所建两种模型的稳定性和预测能力都优于应用ANN建立的模型;参数优化后模型的稳定性和预测能力得到了提高。     

二元互溶可燃混合液体闪点预测模型研究

基于定量结构-性质相关性(QSPR)原理,开展二元互溶可燃混合液体闪点与其结构信息间的内在定量关系(M-QSPR)研究。以332个不同组成和配比的二元互溶可燃混合液体闪点试验数据作为研究样本,根据体系中各纯组分的结构信息,计算相应的混合物描述符(SiRMS,Simplex Representation of Molecular Structure),应用遗传-多元线性回归(GA-MLR)算法从中优化筛选出一组与该体系闪点最密切相关的原子碎片参数作为输入参数,分别采用多元线性回归(MLR)和支持向量机(SVM)算法建立理论预测模型,并将其与文献已有模型进行比较。结果表明,MLR和SVM对测试集样本的平均绝对误差(AAE)分别为4.142 K、1.551 K,均方根误差(RMSE)分别为4.911 K、2.220 K,决定系数(R~2)分别为0.818、0.962。研究表明,影响二元混合液体闪点的主要SiRMS结构因素是■和■,并且随体系中■、■、■四原子碎片增多,闪点升高;随体系中■、■、■四原子碎片增多,闪点降低。同时,与内部交互作用和分子间非加和作用相比,分子间的可加和作用对该体系闪点的影响更为显著;与原子的局部电荷相比,原子类型对该体系闪点的影响更为显著。     

应用原子类型AI指数预测烃类燃烧热

以基于Xu指数的原子类型AI指数作为分子结构描述符,表征了80个液态烃的分子结构特征,并分别结合人工神经网络和多元线性回归方法,对这80种液态烃的燃烧热进行定量结构-性质相关性建模和预测研究。结果表明,基于Xu指数的原子类型AI指数能很好地表征烃类物质的分子结构特征。所建的最佳预测模型为基于Xu指数的原子类型AI指数多元线性回归模型,模型复相关系数为0.999,对测试集的平均预测相对误差为0.637%,模型预测值与实验值的一致性令人满意。     

A new method for the prediction of flash points for ternary miscible mixtures

The flash point is one of the most important physicochemical parameters used to characterize the fire and explosion hazard for flammable liquids. The flash points of ternary miscible mixtures with different components and compositions were measured in this study. Four model input parameters, being normal boiling point, the standard enthalpy of vaporization, the average number of carbon atoms and the stoichiometric concentration of the gas phase for mixtures, were employed and calculated based on the theory of vapor–liquid equilibrium. Both multiple linear regression (MLR) and multiple nonlinear regression (MNR) methods were applied to develop prediction models for the flash points of ternary miscible mixtures. The developed predictive models were validated using data measured experimentally as well as taking data on flash points of ternairy mixtures from the literature. Results showed that the obtained average absolute error of both the MLR and the MNR model for all the datasets were within the range of experimental error of flash point measurements. It is shown that the presented models can be effectively used to predict the flash points of ternary mixtures with only some common physicochemical parameters.     

Flash points measurements and prediction for binary miscible mixtures

Flash point is one of the most important parameters used to characterize the potential fire and explosion hazards for flammable liquids. In this study, flash points of twenty eight binary miscible mixtures comprised eighteen flammable pure components with different compositions were measured by using the closed cup apparatus. The obtained experimental data are further employed to develop simple and accurate models for predicting the flash points of binary miscible mixtures. Based on the vapor–liquid equilibrium theory, the normal boiling point, the standard enthalpy of vaporization, the average number of carbon atoms, and the stoichiometric concentration of the gas phase were selected as the dominant physicochemical parameters that were relevant to the overall flash point property of liquids. With these parameters for pure components as well as the compositions of mixtures, the new form of characteristic physicochemical parameters for mixtures were developed and used as the input parameters for the flash point prediction of mixtures. Both the modeling methods of multiple linear regression (MLR) and multiple nonlinear regression (MNR) were employed to model the possible quantitative relationships between the parameters for mixtures and the flash points of binary miscible mixtures. The resulted models showed satisfactory prediction ability, with the average absolute error for the external test set being 2.506 K for the MLR model and 2.537 K for the MNR model, respectively, both of which were within the range of the experimental error of FP measurements. Model validation was also performed to check the stability and predictivity of the presented models, and the results showed that both models were valid and predictive. The models were further compared to other previously published models. The results indicated the superiority of the presented models and revealed which can be effectively used to predict the FP of binary miscible mixtures, requiring only some common physicochemical parameters for the pure components other than any experimental flash point or flammability limit data as well as the use of the Le Chatelier law. This study can provide a simple, yet accurate way for engineering to predict the flash points of binary miscible mixtures as applied in the assessment of fire and explosion hazards and the development of inherently safer designs for chemical processes.     

基于QSPR方法的脂肪醇化合物闪点预测

为提高脂肪醇化合物闪点预测精度,提出基于定量结构-性质关系(QSPR)原理的脂肪醇化合物闪点预测方法。应用Dragon软件计算出91种脂肪醇的分子描述符,利用遗传函数算法(GFA)从1 481个描述符中筛选出3个与脂肪醇闪点关系最密切的分子描述符。分别用多元线性回归(MLR)方法和支持向量机(SVM)方法进行建模,并采用内部验证和外部检验的方式对模型的拟合度、预测性等性能进行验证。结果表明:预测集的MLR方法和SVM方法的平均绝对误差(AAE)分别为2.870 K和2.706 K;均方根误差(RMSE)为3.451 K和3.371 K。SVM模型在精度上略优于MLR模型,而MLR模型更为简单和方便。     

Correction model for CO detection in the coal combustion loss process in mines based on GWO-SVM

Accurate detection of CO gas is crucial to the prevention of coal combustion. Tuneable diode laser absorption spectroscopy (TDLAS) is a reliable method for CO detection during coal combustion. The influences of temperature and pressure cause changes in the line strength and linewidth of the index gases’ absorption spectra, leading to sizable measurement errors. To correct the distortion of the CO absorption spectrum caused by temperature and pressure fluctuation, a compensation model based on the grey wolf optimizer–support vector machine (GWO–SVM) was proposed. The results were compared with those of the single SVM, the back propagation neural network (BPNN), and multiple regression analysis (MRA). MRA was revealed to result in the lowest accuracy, which indicated that MRA is not ideal for compensation in TDLAS. The hyperparameter selection of the SVM had the disadvantages of randomness and blindness, which led to instability and large errors. The BPNN achieved better correction in the training stage, but severe overfitting occurred in the testing stage. The modified results revealed that the GWO–SVM model had higher accuracy and stability than the other models. It effectively inhibited the effects of temperature and pressure on the measured concentration and greatly improved the measurement accuracy. The equipment is thus suitable for CO gas detection with the aim to preventing coal combustion loss, and it can be further applied to loss prevention in other process fields.