基于混合遗传算法的人工神经网络模型及其对有机化合物熔点的预测

为了避免BP神经网络在训练过程中收敛于局部极小的缺陷,采用自适应交叉变异、最优保存的混合遗传算法对BP网络的权值和阈值进行优化,从而提出一种新的基于混合遗传算法的神经网络模型.该算法首先对一给定的网络结构,采用混合自适应交叉变异和最优保存策略,取各自的长处,用尽可能少的搜索代数找到问题的最优解,从而既防止算法陷入局部最优,又保证算法有较好的平均适应值和最佳的适应值个体.采用上述优化策略的人工神经网络可明显改善收敛的稳定性和收敛速度,并确保网络收敛于全局极小点.人工神经网络运用于物性数据的预测是一个具有潜力和有待开发的领域.运用该模型,根据有机化合物的分子量、临界密度、正常沸点和偶极矩,对其熔点进行预测.预测结果表明：提出的混合遗传算法神经网络优于其他算法神经网络,而且预测结果优于文献上已有的Joback方程和许氏方程的计算值.     

环氧树脂灌封胶的性能预测及配方优化

支持向量机(SVM)是一种新型的机器学习方法,以结构风险最小化原则取代传统机器学习方法中的经验风险最小化原则,在小样本的机器学习中显示出了优异的性能。将SVM应用于双组分环氧树脂灌封胶的研制。通过对双组分环氧树脂灌封胶配方的学习,建立SVM推理模型,并结合穷举法对配方进行优化,结果表明所建SVM推理模型具有一定的预测能力,展示了其优越性和推广前景,可应用于胶粘剂配方的研制,对配方优化起到一定的指导作用。     

煤灰成分预测灰熔点的模型

利用我公司化验室对各种煤样灰熔点与灰成分的分析数据,采用最小二乘法对煤灰成分与灰熔点之间建立线性回归预测模型,通过预测模型方程式计算出预测值,并与煤样灰熔点实测值对比,具有较好的一致性,可为生产提供迅速、可靠的数据。     

基于SVM模型的生态系统服务评估与预测

采取千年生态系统评价分类方法,使用熵权法、变异系数法和层次聚类法构建生态系统服务指数ESI及评价体系,选取宁夏地区4个土地利用开发项目验证模型鲁棒性和评价体系科学性。选取典型土地利用开发项目进行成本效益拟合,发现生态系统服务对提高项目效益成本比率具有显著影响,区分土地利用开发项目考虑和未考虑生态系统服务2种情形,利用支持向量机回归方法对2022—2035年的数据进行预测分析,并对土地利用项目规划开发提出了建议。     

基于多核支持向量机的非线性模型预测控制

Multi-kernel-based support vector machine （SVM） model structure of nonlinear systems and its specific identification method is proposed, which is composed of a SVM with linear kernel function followed in series by a SVM with spline kernel function. With the help of this model, nonlinear model predictive control can be transformed to linear model predictive control, and consequently a unified analytical solution of optimal input of multi-step-ahead predictive control is possible to derive. This algorithm does not require online iterative optimization in order to be suitable for real-time control with less calculation. The simulation results of pH neutralization process and CSTR reactor show the effectiveness and advantages of the presented algorithm.     

支持向量机在混炼胶质量预测中的应用

介绍支持向量机（SVM）的原理，并试验研究密炼过程中应用SVM模型对混炼胶质量进行预测。结果表明，SVM预测模型所得结果与回归分析法模型的预测结果接近，且具有更强的泛化能力；其预测误差控制在门尼粘度均值的3％以内。     

基于支持向量机回归的天然气负荷预测研究

Natural gas load forecasting is a key process to the efficient operation of pipeline network. An accurate forecast is required to guarantee a balanced network operation and ensure safe gas supply at a minimum cost. Machine learning techniques have been increasingly applied to load forecasting. A novel regression technique based on the statistical learning theory, support vector machines (SVM), is investigated in this paper for natural gas shortterm load forecasting. SVM is based on the principle of structure risk minimization as opposed to the principle of empirical risk minimization in conventional regression techniques. Using a data set with 2 years load values we developed prediction model using SVM to obtain 31 days load predictions. The results on city natural gas short-term load forecasting show that SVM provides better prediction accuracy than neural network. The software package natural gas pipeline networks simulation and load forecasting (NGPNSLF) based on support vector regression prediction has been developed, which has also been applied in practice.     

遗传算法和梯度法联合训练的人工神经网络预测有机物熔点

应用遗传算法和梯度法联合训练人工神经网络,使之从有机物的分子量,临界密度,正常沸点和偶极矩预测其熔点。平均误差５．１％,效果优于Ｊｏｂａｃｋ方程和许氏方程。     

基于改进萤火虫算法优化SVM的滚动轴承故障诊断

针对萤火虫算法优化支持向量机时,收敛速度较慢、易陷入局部最小值等问题,将萤火虫算法进行改进来优化支持向量机,用此方法来对轴承故障进行诊断.经过对比实验,发现该方法分类效果和识别准确率均有一定的提高.     

基于最小二乘支持向量机的天然气负荷预测

对城市天然气负荷预测的研究,对于保证天然气管网用气量、优化管网的调度和设备维修具有极其重要的意义．在国内,对于城市天然气负荷预测的研究才刚刚起步,目前还没有较系统的理论．同技术与理论较为成熟的电力负荷预测研究相比较,两者既有许多相同点,又有不同之处．相同之处在     

定位贡献方法计算有机物熔点

A new method is proposed based on the position group contribution additivity for the prediction of melting points of covalent compounds. The characteristics of this method are the use of position distribution function, which could distinguish between most isomers including cis or trans structure of organic compounds. Contributions for hydrocarbons and hydrocarbon derivatives containing oxygen, nitrogen, chlorine, bromine and sulfur, are given. Results are compared with those by the most commonly used estimating methods. The average derivation for prediction of normal melting temperature of 730 compounds is 14.46 K, compared to 29.33 K with the method of Joback, and 27.81 K with the method of Constantinou-Gani. The present method is not only more accurate, but also much simpler and more stable.     

SVM算法预测发动机润滑油的高温清洁性

考察了发动机润滑油功能元素与其高温清净性能的相关性,用支持向量机算法和偏最小二乘算法定量预测了发动机润滑油高温清净性能。结果表明,利用发动机润滑油的功能元素能够预测其高温清净性。支持向量机法的预测结果要优于偏最小二乘法的结果。     

差示扫描量热仪测量聚丙烯熔点的不确定度评定

差示扫描量热仪(Differential Scanning Calorimeter,DSC)在测量高聚物的熔融、玻璃化转变温度等方面具有重要作用。国内一般采用GB/T 19466.3-2004中的方法来测定高聚物熔点,但此标准中并没有给出测量方法精密度,因此对DSC测量熔点的测量不确定度进行评定是非常必要的。本文通过DSC测定聚丙烯(Polypropylene,PP)熔点,讨论了测定过程中标准物质的标准值、样品均匀性以及仪器本身和重复测量等对测试结果的影响,并计算出DSC测定PP熔点的不确定度。     

低熔点共聚酯序列结构分析

采用PTA路线合成一系列低熔点共聚酯,在不改变其它条件的基础下,通过改变单体的配比,将所获得的聚合物的熔点控制在110℃左右。利用核磁共振对聚合物的序列结构进行表征,发现所制得的聚合物的无规度均接近1,表明所得共聚酯均接近无规共聚物。     

新冒落带高度算法FOA-SVM预计模型

针对顶板冒落带高度问题提出新的预计模型,通过搜集众多矿井的实测数据,在支持向量机理论基础上建立预计模型。采用果蝇优化算法对预计模型进行优化训练,建立FOA-SVM预计模型,利用实测数据对模型的预计结果进行检验,预计结果较为准确,比PSO-SVM模型和GA-SVM模型结果稳定性好计算精度高。     

Pervaporation of High Boiling Point Organic Compounds with Composite PDMS Membrane

High Boiling Point Organic Compounds (HBOCs ^{1 1}HBOCs: High Boiling Point Organic Compounds ) are defined as those organic compounds with boiling point over water (100°C). It is a challenging problem to separate HBOCs from their mixtures with water. Three HBOCs, propargyl alcohol, butanol, and pyridine, were selected as the experimental samples for observing their separation behaviors from water mixtures by PDMS membrane pervaporation. These HBOCs could preferentially permeate the PDMS membrane and were selectively extracted from the mixtures through the membrane. The experimental tests showed that the permeation flux of propargyl alcohol, butanol, and pyridine was 243.24, 976.5, and 904.70 gm^?2h^?1, with the corresponding selectivity of 3.78, 29.65, and 26.09, respectively. The effects of the feed flow rate, feed concentration, and temperature on the separation behaviors were examined. By comparison with distillation that separates different components in a mixture on the basis of boiling point, the membrane pervaporation seems to behave a “reverse direction” selective separation for the HBOCs. For those aqueous mixtures with tiny content of HBOCs, the “reverse selective separation” by membrane pervaporation should be considered as a promising and effective technology.     

有机化合物沸点估算的复合基团拓扑空间方法

基于传统基团划分方法进行了有机化合物分子的空间设计,用基团模指数表征基团在分子中的位置,用基团-邻接原子对增加对基团环境影响的考虑,建立了有机化合物物性估算的复合基团拓扑空间方法。提出了估算正常沸点的表达式,使用了1171种有机化合物拟合出了相应的基团和基团．邻接原子对的参数,其估算的平均相对偏差为1．58％,为与前期工作进行比较,故用前期工作所用的669种物质进行了估算,其平均相对偏差为1．29％。将本方法和常用的方法以及本工作前期提出的方法进行了比较,结果表明本方法有更高的准确度和可靠性。     

三元可燃性液体水溶液闪点的理论预测

为了预测三元互溶可燃性液体水溶液的闪点,分析确定了影响混合溶液闪点的主要因素,如沸点、相对分子质量、相对密度、饱和蒸汽压、表面张力等。将这些因素作为输入变量,应用支持向量机算法对混合溶液闪点与其对应理化参数之间的内在定量相关性进行了研究,建立了三元互溶可燃性液体水溶液闪点的理论预测模型。对预测模型进行了验证,讨论了模型的有效性和可靠性;解释了模型反映的机制,明确了混合溶液闪点的主要影响因素及其重要程度。