基于渐近理论的两阶段过程辨识方法

提出了一种基于渐近理论的两阶段过程辨识方法：先用高阶模型得到无偏估计和频域方差;然后通过OE模型与MDL定阶法进行降阶处理。它将多变量模型结构辨识转换为易于实现的单变量问题,同时通过模型频域方差进行模型验证,解决了传统多变量辨识方法的阶次估计及模型验证难的问题。采用多通道测试信号,测试时间短,对装置生产影响小。应用实例表明了算法的有效性。     

基于Kernel特征空间分解的组分仪递推模型

提出一种Kernel映射空间中特征值问题的递推求解算法，用于建立能够在线快速更新的软组分仪模型。该算法由向前更新和向后更新两个递推阶段组成，只需极小的计算量即可获得新的特征空间信息，且无需保存整个Kernel矩阵。通过对Tennessee Eastman（TE）过程的终端产品质量的建模研究表明，基于提出的快速更新算法建立的软组分仪模型可以获得准确的预报精度，而且在过程故障情况下也显著优于无在线更新的组分仪模型。     

基于互信息的PCA方法及其在过程监测中的应用

主元分析(PCA)是一种经典的特征提取方法,已被广泛用于多变量统计过程监测,其算法的本质在于提取过程数据各变量之间的相关性。然而,传统PCA算法中定义的相关性矩阵局限于计算变量间的线性关系,无法衡量两个变量间相互依赖的强弱程度。为此,提出一种新的基于互信息的PCA方法(MIPCA)并将之应用于过程监测。与传统PCA所不同的是,MIPCA通过计算两两变量间的互信息来定义相关性,将原始相关性矩阵取而代之为互信息矩阵,并利用该互信息矩阵的特征向量实现对过程数据的特征提取。在此基础上,可以建立相应的统计监测模型。最后,通过实例验证MIPCA用于过程监测的可行性和有效性。     

自适应粒子群优化算法在聚丙烯熔融指数预报上的应用

针对丙烯聚合生产控制中聚丙烯熔融指数在线测量的控制要求,以及过程变量间相关性高的特点,提出一种基于自适应粒子群优化算法和径向基函数神经网络的聚丙烯熔融指数预报新方法。该方法采用变参数的自适应粒子群优化算法提高优化算法的效率和收敛性,并且融合了主成分分析、统计建模以及智能优化方法,从而降低了预报模型的复杂度。提出了一种基于径向基函数神经网络的统计预报模型的参数优化和结构优化方法。使用该统计模型对工厂实际生产过程进行预报,并与国内外相关研究报道相比较,表明了本文所提出的预报方法的有效性和更高的准确性。     

阶梯式多变量DMC分散优化算法及工程化实现

提出基于状态空间模型的阶梯式多变量动态矩阵控制分散优化算法,使计算量大大减少,并在自行研制的先进控制平台上,实现了这种算法.该算法的工程化实现方法,使用户可以方便地构建自动控制系统并实施多变量动态矩阵控制.对双容水箱的控制实验表明,该控制算法对具有多变量、时滞、耦合和不确定性的复杂对象,具有良好的控制效果.     

高强混凝土质量与影响因素的多因变量偏最小二乘回归(PLSR)分析

运用偏最小二乘回归(PLSR)的原理,分析研究了胶凝材料用量、水胶比、硅粉掺量、粉煤灰掺量、坍落度以及水、石、砂掺量等有关因素对高强混凝土7d,28d和90d抗压强度的影响;并用R统计软件进行了多元多重线性回归分析,建立了高强混凝土抗压强度与其影响因素之间的多因变量的PLSR模型,该模型的预测误差较小,能较好地应用于混凝土施工质量预测和控制。     

基于过程迁移的间歇过程终点质量预报方法

提出了一种基于过程迁移的间歇过程质量预报方法,旨在解决新间歇过程数据不足难以建立准确预报模型的问题。该方法基于多元统计回归分析模型,通过构建相似间歇过程间的共同潜变量空间,将已有相似间歇过程的数据信息迁移应用到未建模的新间歇过程中,实现新间歇过程的快速建模和质量预报。在线应用时,利用在线数据不断更新过程迁移模型;同时,实时估计模型预测误差的置信区间,判断预报模型预测误差的稳定性;为克服相似过程间可能存在的差异给迁移模型带来的不利影响,根据数据相似度逐步剔除相似间歇过程数据。最后,通过仿真实验验证了所提方法的有效性。     

基于过程迁移的间歇过程终点质量预报方法

提出了一种基于过程迁移的间歇过程质量预报方法,旨在解决新间歇过程数据不足难以建立准确预报模型的问题。该方法基于多元统计回归分析模型,通过构建相似间歇过程间的共同潜变量空间,将已有相似间歇过程的数据信息迁移应用到未建模的新间歇过程中,实现新间歇过程的快速建模和质量预报。在线应用时,利用在线数据不断更新过程迁移模型;同时,实时估计模型预测误差的置信区间,判断预报模型预测误差的稳定性;为克服相似过程间可能存在的差异给迁移模型带来的不利影响,根据数据相似度逐步剔除相似间歇过程数据。最后,通过仿真实验验证了所提方法的有效性。     

缺失数据下基于EM算法的非线性过程建模

线性时变参数系统(LPV)将多阶段、非线性的过程建模转化为线性多模型的辨识问题,近年来得到了极大关注。考虑缺失数据下LPV系统的离线建模问题,首先引入一个二进制变量表征输出样本缺失状态,选取过程关键变量作为调度变量,确定主要工况点;然后围绕不同工况点建立局部子模型,将输出缺失部分和采样数据的模型归属当作隐藏变量,利用EM算法进行参数估计,再采用高斯权重函数融合各子模型。最后分别针对典型二阶过程和连续搅拌反应釜(CSTR),运用提出的多模型和算法进行仿真实验,表明有效性。     

基于自适应粒子群优化算法的预测控制算法及其在加热炉支管平衡中的应用

多变量和输出受限系统的预测控制问题一般表现为一个不易直接求解的多变量且多约束的非线性动态规划问题.传统优化方法在解决此优化问题时,存在易收敛到非法解或局部极小、计算时间长以及对模型参数与初值依赖性强的缺点.提出了一种基于自适应粒子群优化的预测控制算法(APSO-DMC),采用自适应粒子群优化算法(APSO)作为模型预测控制的优化方法,在线实时求解最优控制律,从而有效地克服了传统优化方法的不足.将此算法应用于常减压装置加热炉支管温度平衡控制中,仿真试验结果显示了该方法的有效性.     

近红外光谱法测定银杏叶提取液中总黄酮含量

应用近红外光谱技术建立了快速测定银杏叶提取液中总黄酮含量的方法.将高效液相色谱法测定的总黄酮含量作为参考标准值用于建模,考察预测残差平方和(Predictive residual error sum of square,PRESS)与主成分之间的关系,主成分数为2时得到PRESS最小;用偏最小二乘法(PLS)进行回归分析得到的回归系数为0.98206、交叉验证结果的回归系数为0.96322,表明预测模型具有良好的稳定性.高效液相色谱法测定的银杏叶提取液中总黄酮含量与本方法的预测值之间存在良好的线性关系,t-检验结果表明,两种方法测得的总黄酮含量无显著性差异.本方法快速、简便,能准确地预测银杏叶提取液中总黄酮的含量.     

基于MLFN-PLSR的PX氧化反应组合建模方法

针对对二甲苯（p-xylene，PX）氧化反应过程中影响主要副产物对羧基苯甲醛（4-carboxybenzaldehyde，4-CBA）含量的因素众多且呈高度非线性的特征，提出了多层前向型神经网络（multi-layer feedforward network，MLFN）与偏最小二乘回归（partial least squares regression，PLSR）相结合的建模方法，建立反应产物中4-CBA含量关联模型。MLFN-PLSR采用三层网络结构和尽量多的隐节点，通过MLFN充分提取样本数据信息；然后采用PLSR消除隐含层输出冗余信息，建立具有良好预测精度的模型。与MLFN相比，最佳性能模型的预测偏差平方和均值下降了12.11%、模型平均预测偏差平方和均值下降了8.37%。与PLSR相比，最佳性能模型的预测偏差平方和均值下降了70.62%。     

Monitoring PV in corn and soybean oils by NIR spectroscopy

NIR spectroscopy was used successfully in our laboratory to monitor oxidation levels in vegetable oils. Calibration models were developed to measure PV in both soy and corn oils, using partial least squares (PLS) regression and forward stepwise multiple linear regression, from NIR transmission spectra. PV can be measured successfully in both corn and soy oils using a single calibration. The most successful calibration was based on PLS regression of first derivative spectra. When this calibration was applied to validation sample sets containing equal numbers of corn and soy oil samples, with PV ranging from 0 to 20 meq/kg, a correlation coefficient of 0.99 between titration and NIR values was obtained, with a standard error of prediction equal to 0.72 meq/kg. For both types of oil, changes occurred in the 2068 nm region of the NIR spectra as oxidation levels increased. These changes appear to be associated with the formation of hydroperoxides during oxidation of the oils.     

基于主曲线的软测量方法及其在精馏塔上的应用

为解决工业过程软测量中的变量维数高、数据相互耦合、非线性强等问题,提出了基于主曲线的软测量方法。其中的基于主曲线的非线性回归模型借鉴了PLS的基本思想,采用主曲线提取隐变量信息的同时考虑了自变量与因变量的相关性;在隐变量空间中,采用多项式函数拟合隐变量之间的非线性关系。在实例研究中,分别采用纯函数数据和氯乙烯精馏塔实时运行数据对该模型进行了验证。仿真结果表明,该模型所需要的隐变量数目比传统的PLS模型更少,并且能够实现更为精确的预测,可较好地处理工业过程中存在的数据高耦合度以及强非线性问题。     

Fault detection and diagnosis in a non-Gaussian process with modified kernel independent component regression

Quality-related fault detection and diagnosis are crucial in the data-driven process monitoring field. Most existing methods are based on principal component analysis (PCA) or partial least squares (PLS), which will miss high-order statistical information when the industrial process does not satisfy a Gaussian distribution. Meanwhile, the traditional contribution plot is difficult to directly apply to nonlinear processes in some cases due to its limitation of convergence. As such, a modified kernel independent component regression (MKICR) model, which considers high-order statistical information, is proposed for quality-related fault detection and faulty variable identification. First, the relationship between the independent components and quality variables is established by kernel independent component regression, and the correlation matrix is obtained. Then, the kernel independent components can be suitably divided into quality-related and quality-unrelated parts. Finally, an analysis of the contribution of each variable to the statistics based on Lagrange's mean value theorem is presented. In addition, a numerical case and the Tennessee Eastman process (TEP) demonstrate the efficacy and superiority of the proposed method.     

ESTIMATION OF COEFFICIENTS OF TIME SERIES REGRESSION WITH A NONSTATIONARY ERROR PROCESS

Abstract. We treat a problem of estimating unknown coefficients of a time series regression when the variance of the error changes with time, i.e. when a process which the error term obeys is nonstationary. First, we show the weak consistency of the ordinary least squares estimator for the coefficients of a polynomial regression under some assumptions on the covariance structure of the error process. Next, we propose a nonparametric method for estimating the variance of the error process and a weighted least squares estimator of the regression coefficients, which is constructed by using the estimator of the variance. We investigate statistical properties of our proposed estimator in the following way. We consider the prediction of a future value of a linear trend by using our proposed estimator and evaluate its prediction error. By simulation studies, we compare the prediction error of the predictor constructed by using our proposed estimator with the prediction errors obtained for other estimators including the ordinary least squares estimator when the variance of the error process increases with time and the sample sizes are small. As a result, our proposed estimator seems to be reasonable.     

Development of calibration models for quality control in the production of ethylene/propylene copolymers by FTIR spectroscopy,multivariate statistical tools,and artificial neural networks

Principal component regression (PCR), partial least squares (PLS), StepWise ordinary least squares regression (OLS), and back‐propagation artificial neural network (BP‐ANN) are applied here for the determination of the propylene concentration of a set of 83 production samples of ethylene–propylene copolymers from their infrared spectra. The set of available samples was split into (a) a training set, for models calculation; (b) a test set, for selecting the correct number of latent variables in PCR and PLS and the end point of the training phase of BP‐ANN; (c) a production set, for evaluating the predictive ability of the models. The predictive ability of the models is thus evaluated by genuine predictions. The model obtained by StepWise OLS turned out to be the best one, both in fitting and prediction. The study of the breakdown number of samples to be included in the training set showed that at least 52 experiments are necessary to build a reliable and predictive calibration model. It can be concluded that FTIR spectroscopy and OLS can be properly employed for monitoring the synthesis or the final product of ethylene–propylene copolymers, by predicting the concentration of propylene directly along the process line. © 2008 Wiley Periodicals, Inc. J Appl Polym Sci, 2008     

Using least squares to generate forecasts in regressions with serial correlation

Abstract. The topic of serial correlation in regression models has attracted a great deal of research in the last 50 years. Most of these studies have assumed that the structure of the error covariance matrix Ω was known or could be consistently estimated from the data. In this article, we describe a new procedure for generating forecasts for regression models with serial correlation based on ordinary least squares and on an approximate representation of the form of the autocorrelation. We prove that the predictors from this specification are asymtotically efficient under some regularity conditions. In addition, we show that there is not much to be gained in trying to identify the correct form of the serial correlation since efficient forecasts can be generated using autoregressive approximations of the autocorrelation. A large simulation study is also used to compare the finite sample predictive efficiencies of this new estimator vis‐à‐vis estimators based on ordinary least squares and generalized least squares.     

DESIGN OF A COMPOSITION ESTIMATOR FOR INFERENTIAL CONTROL OF DISTILLATION COLUMNS

In distillation column control, secondary measurements such as temperatures and flows are widely used in order to infer product composition. This paper addresses the design of the linear static estimators using the secondary measurements for estimating product compositions of distillation columns. Based on the unified framework for the estimator design, the relationships among various static estimators are discussed in terms of the estimator structure. Il is shown that the projection estimator is equivalent to the regression estimators in the special cases. Since the projection estimator heavily depends on the measured inputs such as reflux flow and heat input to the reboiler due to its structural characteristic, the estimation performance is far more sensitive to measurement noise and nonlinearity of them, compared wiih the regression estimators based on the PCR or PLS method. It is also found that the use of the measured inputs leads to performance deterioration of both the projection and regression estimators because of their nonlinear effects on the product compositions especially in high-purity columns. Design guidelines for the PCR and PLS estimators are presented by analyzing the results of the simulation studies on a high-purity column example. The estimator based on the guidelines is robust to sensor noise and has a good predictive power     

Application of fuzzy partial least squares (FPLS) modeling nonlinear biological processes

We applied a nonlinear fuzzy partial least squares (FPLS) algorithm for modeling a biological wastewater treatment plant. FPLS embeds the Takagi-Sugeno-Kang (TSK) fuzzy model into the regression framework of the partial least squares (PLS) method, in which FPLS utilizes a TSK fuzzy model for nonlinear characteristics of the PLS inner regression. Using this approach, the interpretability of the TSK fuzzy model overcomes some of the handicaps of previous nonlinear PLS (NLPLS) algorithms. As a result, the FPLS model gives a more favorable modeling environment in which the knowledge of experts can be easily applied. Results from applications show that FPLS has the ability to model the nonlinear process and multiple operating conditions and is able to identify various operating regions in a simulation benchmark of biological process as well as in a full-scale wastewater treatment process. The result shows that it has the ability to model the nonlinear process and handle multiple operating conditions and is able to predict the key components of nonlinear biological processes.