Prediction Interval for Autoregressive Time Series via Oracally Efficient Estimation of Multi‐Step‐Ahead Innovation Distribution Function

A kernel distribution estimator (KDE) is proposed for multi‐step‐ahead prediction error distribution of autoregressive time series, based on prediction residuals. Under general assumptions, the KDE is proved to be oracally efficient as the infeasible KDE and the empirical cumulative distribution function (cdf) based on unobserved prediction errors. Quantile estimator is obtained from the oracally efficient KDE, and prediction interval for multi‐step‐ahead future observation is constructed using the estimated quantiles and shown to achieve asymptotically the nominal confidence levels. Simulation examples corroborate the asymptotic theory.     

用微扰理论状态方程预测电解质水溶液的密度

对微扰理论的电解质水溶液状态方程作了进一步简化．由水的分子参数和离子直径,计算了包含强酸在内的12个单一电解质水溶液、9个二元和1个四元电解质水溶液在不同温度下的密度．对单一电解质水溶液密度关联准确度在1％之内,对混合电解质水溶液密度预测的平均相对偏差在2％左右,若阳离子直径采用由单一电解质水溶液的回归值代替Pauling直径,则能进一步改善预测准确度．     

算子逼近在过程神经网络动态预测中的研究与应用

从泛函分析的角度出发,将动态预测的问题看作算子逼近问题,分析并证明算子逼近能力,进而提出了过程神经网络的动态预测方法,并将时间序列预测问题转化为泛函逼近或算子逼近问题,证明了过程神经网络能以任意精度逼近任意连续算子。最后以Mackey-Glass混沌时间序列预测和打浆度的预测为例,验证该方法的有效性和实用性。     

On the application of theoretical methods for the prediction of fluorescence maxima of organic dyes

Theoretical methods, especially the well established Pariser-Parr-Pople molecular orbital method, have proved to be very useful in colour prediction of organic dye molecules. Because of the increasing importance of highly fluorescent substances for applications as optical brighteners as well as laser dyes there exists a clear need for a theoretical model which allows the prediction of fluorescence maxima with comparable accuracy to that of absorption maxima. It is shown that the simulation of the change of molecular geometry upon excitation by a simple iterative procedure within the framework of the PPP-method can be used for the calculation of fluorescence maxima with satisfactory accuracy thus allowing reliable predictions for this class of dyes. Therefore the method discussed may prove very helpful in practical and synthetic work on fluorescent organic dyes.     

反向传播网络在乙烯裂解炉预测分析中的应用研究

利用MATLAB工具箱中的BP神经网络模型建立了乙烯裂解炉的三层神经网络模型,分析和预测了裂解产物乙烯和丙烯的收率,将预测的结果和生产过程数据作比较,结果表明,该模型的预测值和实际生产数据值吻合很好,可用于乙烯生产的预测分析和预测控制。     

三元非共沸混合制冷剂热力性质算法

为了确保计算的精确性,文中采用PRHV与Lee-Kesler-P lǒcker(LKP)模型相结合的方法计算混合工质汽液相平衡参数与焓、熵等热物理性质,即利用Huron-V idal混合规则,采用立方型PR方程和过量G ibbs自由能NRTL模型相结合的PRHV模型预测相平衡参数,在此基础上,由LKP多参数状态方程计算的焓、熵等状态参数。文中验证了这种预测方法的可靠性与准确性,此方法可作为系统循环模拟计算中相平衡及热力参数的精确计算方法。     

BANDWIDTH SELECTION IN KERNEL SMOOTHING OF TIME SERIES

Abstract. The kernel smoothing method has been considered as a useful tool for identification and prediction in time series models. In practice this method is to be tuned by a smoothing parameter. For selection of the smoothing parameter, Härdle and Vieu (Kernel regression smoothing of time series. J. Time Ser. Anal. 13(1992), 209–32) considered a cross-validation rule and proved its asymptotic optimality. In this paper we strengthen their result for a wider use of the kernel smoothing of time series.     

基于IFOA-KELM-MEA模型的游梁式抽油机采油系统井下工况的短期预测

实现对井下工况的预测是及时掌握抽油井生产状态的有效方法,对提高油井生产效率和降低维护成本具有十分重要的意义。采用混沌理论实现抽油井井下工况的短期预测,首先将所提取的示功图的不变曲线矩特征向量作为预测变量,在证明其数据序列具有混沌特性后,由核极限学习机（kernel extreme learning machine,ELM）建立混沌时间序列预测模型,对其中的几个不确定参数采用改进的果蝇优化算法（improved fruit fly optimizationalgorithm,IFOA）进行优化选取,IFOA采用全局群体多样进化和局部个体随机变异的策略,最后,对模型所预测的结果进行物元分析（matter-element analysis,MEA）,诊断其属于哪种故障类型。由某油田作业区的两口生产井进行实例验证,结果表明所提出的IFOA-KELM-MEA预测模型是合理有效的。     

航空发动机磨损趋势预测模型研究

文章讨论了神经网络的BP算法和遗传算法,提出用遗传算法来优化BP神经网络,应用遗传算法训练神经网络权重,实现网络结构的优化,用优化后的BP人工神经网络建立了航空发动机磨损故障趋势预测模型,利用发动机的光谱监测数据作为预测磨损趋势的特征参数,进行了模型的训练和预测试验,并将该模型预测结果与BP算法和多元线性回归法的预测结果进行了比较,证明了基于遗传算法的人工神经网络是航空发动机磨损故障趋势预测的一种理想方法。     

边邻接指数预测火炸药分子摩尔体积的研究

边邻接指数是从 Randic的图论指数衍生出的拓扑指数 ,本文利用 Estrada提出的计算方法 ,计算了 6 2种火炸药分子的边邻接指数 ,并与分子摩尔体积建立了相关方程。结果表明 ,两者具有良好的相关性 (r=0 .96 46 ) ,所得方程可以较好地预测火炸药分子的分子摩尔体积     

Theoretical predictions on temperature-dependent strength for MAX phases

MAX phases have great application potential in high-temperature fields due to their unique combination of ceramic and metallic properties. In this work, a physics-based theoretical model is developed for the prediction of temperature-dependent strength of MAX phases, based on the force-heat equivalence energy principle. The quantitative relationship between the strength, Young's modulus, temperature, and melting point is revealed by the proposed model. Through the comparison between theoretical predictions of strength and available experimental results from the literature, the model is proved to be efficient in predicting the strength of MAX phases at high temperatures. Since the melting point and Young's modulus of material can be easily obtained, the proposed theoretical model provides a convenient and feasible method for predicting the temperature-dependent strength of MAX phases.     

基团贡献状态方程的开发与热力学模型参数的理论预测

热力学模型是研究流体相行为和热力学性质的重要工具。理论模型的有效应用离不开模型参数的确定。为赋予热力学模型的预测功能，目前的策略一是建立基团贡献(GC)状态方程(EOS)，二是探索热力学模型参数的理论预测方法。围绕先前开发的变阱宽方阱链流体状态方程(SWCF-VR)，采用基团贡献法思路获得了不同基团对模型参数的贡献值，建立了GC-SWCF方程，证实GC-SWCF方程能满意预测纯物质的密度。进一步将似导体屏蔽模型(COSMO)与SWCF结合，基于COSMO方法获得了192种有机化合物的SWCF方程的模型参数，这是一种不依赖实验数据确定模型参数的理论方法。发现COSMO+SWCF能较好地预测纯物质的密度。引入一个与温度无关的二元交互作用可调参数后，GC-SWCF与COSMO+SWCF都可应用于二元混合物密度与气液相平衡的计算中。     

基于对应态原理的过剩焓模型

本文把局部组成概念引入三参数对应态原理中,提出了一个新的过剩焓模型。经用30组物系考核并与UNIFAC、PRG、NRTL及UNIQUAC模型比较,表明新模型关联精度甚高。由二元参数推算多元系,效果也较好。     

RP—HPLC流动相组成优化方法的研究及其专家系统的建造

本文提出了一种既便于自动求值,又不致产生歧义的色谱分离优化目标函数。对于反相高效液相色谱RP-HPLC流动相组成优化问题,提出了新的高效迭代方法,并建立了组成优化专家系统。该系统包括优化搜索区域确定、实验谱图辨识、保留特性关系的自适应回归和最优目标预测等功能。经实验验证,该系统具有较高的迭代搜索效率。     

Relation of crystalline structure and mechanical properties of nucleated polypropylene

Four heterogeneous nucleating agents were added to polypropylene (PP) homoblock and random copolymers. Melting and crystallization of the polymers were studied by differential scanning calorimetry (DSC), and characteristics derived from the crystallization exotherms were related to the mechanical properties of injection molded bars. A very close correlation was found between the crystallization characteristics and Young's modulus of the polymers. The general correlation proved to be valid for all three polymers studied and also for each nucleating agent. The developed empirical correlation makes possible the approximate prediction of stiffness from a simple DSC trace. Further study is needed to give the relationship better physical meaning and to extend it to other mechanical properties.     

A mathematical model for predicting the soil nitrogen status under varying fertilizer practices in a continuous cropping sequence

A mathematical model has been proposed for predicting the changes in soil nitrogen status due to continuous fertilization in a continuous cropping sequence. The model also enabled the prediction of the steady state of soil nitrogen for a specified fertilizer practice.The model was applied to six years nitrogen availability data of four fertilizer practices in finger millet-maize-cowpea sequence followed in the Long Term Fertilizer Experiments conducted at Tamil Nadu Agricultural University, Coimbatore, India. The agreement between the predicted soil nitrogen status by the model and the actuals was proved by employing reliability index.     

局部应力-应变法预测大型波纹管的疲劳寿命

鉴于大型波纹管膨胀节全尺寸疲劳寿命试验在工程上实现的困难性,研究了基于局部应力－应变法预测大型波纹管的疲劳寿命。应用非线性有限元获取波纹管的最大局部应力应变,并据此局部应变设计简化的试板。当弯曲试板上的最大应变等于波纹管的最大局部应变时,板的弯曲疲劳试验寿命即可代替波纹管的试验寿命。本方法在工程设计中被证明是实用且可靠的,它也适用于低压工况下通用尺寸波纹管的疲劳寿命的预测。     

用径向分布函数及Lennard-Jones位能模型计算真实流体的PVT性质

用顺序解析平衡法,结合Ｌｅｎｎａｒｄ－Ｊｏｎｅｓ（Ｌ－Ｊ）位能函数模型计算径向分布函数,然后直接代入统计热力学所给出的理论状态方程预测真实流体的ＰＶＴ性质。Ｌ－Ｊ位能模型参数由临界温度Ｔｃ和临界压力Ｐ确定。结果表明该方法能成功地预测非极性和弱极性纯流体的ＰＶＴ性质。当分子尺寸小于正己烷时,除临界温度附近之外,预测的饱和液体体积的平均相对误差一般小于５％,对于分子尺寸更大的流体,可应用象Ｋｉｈａｒａ模型这样的三参数位能模型来提高预测精度。     

高频脉冲电场作用下乳状液液滴动力学模型

基于乳状液中液滴在电场中的受力情况的分析，建立了W/O乳状液中液滴振荡固有频率公式，从理论角度分析和解释了高频脉冲电场对W/O乳状液的破乳机理，从力学的角度分析了最佳频率存在的理论基础，并推导出了最佳频率的计算公式。该固有频率与液滴尺寸、界面张力、黏度、温度、密度等有关。为了验证最佳频率公式的可靠性，用正辛烷乳状液进行了室内实验。实验结果表明，理论最佳频率公式的预测结果与实验测得的最佳频率结果吻合，经修正后与白油实验结果也非常接近。     

Dyeing machine control using in-line colour measurement Part 2: On-line control of dye exhaustion rate

Part 1 of this paper reported a novel method of dyebath analysis, based on an in-line analysis cell with links to a computer-based match prediction system that included compensation for changes in dyebath temperature. We now describe the cell's use in feedback control of the rate of uptake of dye from the dyebath by controlling the dyebath temperature in conventional (all-in) and continuous-addition dyeing. For all-in dyeing, a high level of control was achieved, allowing experimental verification of the theoretical result that a quadratic exhaustion profile gives the best levelness. When dye was added continuously, a linear exhaustion profile proved to be the most robust and gave the best levelness with either linear or exponential addition of dye.