基于Fisher判别分析和核回归的质量监控和估计

A novel systematic quality monitoring and prediction method based on Fisher discriminant analysis (FDA) and kernel regression is proposed. The FDA method is first used for quality monitoring. If the process is under normal condition, then kernel regression is further used for quality prediction and estimation. If faults have occurred, the contribution plot in the fault feature direction is used for fault diagnosis. The proposed method can effectively detect the fault and has better ability to predict the response variables than principle component regression (PCR) and partial least squares (PLS). Application results to the industrial fluid catalytic cracking unit (FCCU) show the effectiveness of the proposed method.     

Prediction of the Melt Index Based on the Relevance Vector Machine with Modified Particle Swarm Optimization

A novel chemical soft‐sensor approach for the prediction of the melt index (MI) in the propylene polymerization industry is presented. The MI is considered as one of the important variables of quality that determine the product specifications. Thus, a reliable estimation of the MI is crucial in quality control. An accurate optimal predictive model of MI values with the relevance vector machine (RVM) is proposed, where the RVM is employed to build the MI prediction model; a modified particle swarm optimization (MPSO) algorithm is then introduced to optimize the parameter of the RVM, and the MPSO‐RVM model is thereby developed. An online correcting strategy (OCS) is further carried out to update the modeling data and to revise the model's parameter self‐adaptively whenever model mismatch happens. Based on the data from a real polypropylene production plant, a detailed comparison is carried out among the least squares support vector machine (LS‐SVM), RVM, MPSO‐RVM, and OCS‐MPSO‐RVM models. The research results reveal the prediction accuracy and validity of the proposed approach.     

Parameter Estimation in the Error‐in‐Variables Models Using the Gibbs Sampler

Least squares and maximum likelihood techniques have long been used in parameter estimation problems. However, those techniques provide only point estimates with unknown or approximate uncertainty information. Bayesian inference coupled with the Gibbs Sampler is an approach to parameter estimation that exploits modern computing technology. The estimation results are complete with exact uncertainty information. The Error‐in‐Variables model (EVM) approach is investigated in this study. In it, both dependent and independent variables contain measurement errors, and the true values and uncertainties of all measurements are estimated. This EVM set‐up leads to unusually large dimensionality in the estimation problem, which makes parameter estimation very difficult with classical techniques. In this paper, an innovative way of performing parameter estimation is introduced to chemical engineers. The paper shows that the method is simple and efficient; as well, complete and accurate uncertainty information about parameter estimates is readily available. Two real‐world EVM examples are demonstrated: a large‐scale linear model and an epidemiological model. The former is simple enough for most readers to understand the new concepts without difficulty. The latter has very interesting features in that a Poisson distribution is assumed, and a parameter with known distribution is retained while other unknown parameters are estimated. The Gibbs Sampler results are compared with those of the least squares.     

基于数据的城市污水泵站系统建模

根据Gelormino管网LTI离散模型,结合实际推导出可行的广义数据模型,提出了系统辨识方法:(1)通过数据挖掘技术实现模型结构聚类;(2)采用相关性分析技术确定模型结构;(3)采用最小二乘法及渐消记忆递推最小二乘法实现模型参数辨识及在线辨识。实例计算结果表明,该方法建立的数据模型可以很好地模拟并预测泵站的污水流入量、污水总量以及水位变化情况,可用于指导城市污水泵站的运行管理。     

Data-driven prediction model of indoor air quality in an underground space

Several data-driven prediction methods based on multiple linear regression (MLR), neural network (NN), and recurrent neural network (RNN) for the indoor air quality in a subway station are developed and compared. The RNN model can predict the air pollutant concentrations at a platform of a subway station by adding the previous temporal information of the pollutants on yesterday to the model. To optimize the prediction model, the variable importance in the projection (VIP) of the partial least squares (PLS) is used to select key input variables as a preprocessing step. The prediction models are applied to a real indoor air quality dataset from telemonitoring systems data (TMS), which exhibits some nonlinear dynamic behaviors show that the selected key variables have strong influence on the prediction performances of the models. It demonstrates that the RNN model has the ability to model the nonlinear and dynamic system, and the predicted result of the RNN model gives better modeling performance and higher interpretability than other data-driven prediction models.     

Modeling of Ozonation for Dissolved Ozone Dosing

Experimental research was carried out for calibration and validation of a model describing ozone decay and ozone exposure (CT), decrease in UV absorbance at 254 nm (UVA₂₅₄), increase in assimilable organic carbon concentration and bromate formation. The model proved to be able to predict these parameters on the basis of the applied ozone dosage. The experimental ozone dosages ranged from 0.4 mg-O₃/L to 0.9 mg-O₃/L for natural water with a dissolved organic carbon concentration of 2.4 mg-C/L. The UVA₂₅₄ was found to be an effective parameter for estimation of rapid ozone decay for natural water under experimental conditions tested. The experimental setup consisted of a bench-scale plug flow reactor (approximately 100 L/h) with dissolved ozone dosing.     

基于证据框架的最小二乘支持向量机在精对苯二甲酸生产中的应用

支持向量机是一种基于统计学习理论的新型机器学习方法.本文给出一种考虑损失函数的噪声模型参数β的贝叶斯证据框架最小二乘支持向量机回归算法,通过贝叶斯证据框架自动调整正则化参数和核参数,更好地实现了最小化误差和模型复杂性之间的折中.将提出的算法用于精对苯二甲酸（purified terephthalic acid,PTA）生产过程中的关键指标对羧基苯甲醛（4-carboxybenzaldhyde,4-CBA）含量的预测中,能很好地跟踪4-CBA含量的变化趋势,泛化能力较强,为4-CBA含量的实时预测提供了很好的解决方案.     

Recursive least squares based estimation schemes for self-tuning control

Recursive Least Squares (RLS) is the most popular parametric identification method used for on-line process model estimation and self-tuning control. The basic least squares scheme is outlined in this paper and its lack of ability to track changing process parameters is illustrated and explained. Several variants of the basic algorithm which have appeared elsewhere in the literature are discussed. Some of these algorithms contain different modifications to the basic scheme which are intended to prevent this loss of alertness to changing process parameters. Other variations of the least squares algorithm are presented which attempt to deal with parameter estimation in the presence of disturbances and unmodelled process dynamics.     

Prediction of the surface tension of binary systems based on the partial least squares method

To predict the surface tension of binary liquid systems, an empirical model is proposed using the partial least squares (PLS) based on the multivariate statistical analysis method. Required parameters for the PLS method to predict the surface tension of binary systems are composed of the thermophysical properties of only pure substances such as critical temperature, critical pressure, critical volume, molar volume, viscosity and vapor pressure for input data block (X) and the reported experimental surface tension data for output data block (Y). The data set for the experimental surface tension of binary liquid systems is divided into the training set for regression and the test set for predicting. An average relative error (%) results of regression and prediction indicate that the PLS method can be a useful tool for predicting the surface tension of liquid binary systems.     

The Effect of the Estimation on Goodness‐of‐Fit Tests in Time Series Models

Abstract. We analyze, by simulation, the finite‐sample properties of goodness‐of‐fit tests based on residual autocorrelation coefficients (simple and partial) obtained using different estimators frequently used in the analysis of autoregressive moving‐average time‐series models. The estimators considered are unconditional least squares, maximum likelihood and conditional least squares. The results suggest that although the tests based on these estimators are asymptotically equivalent for particular models and parameter values, their sampling properties for samples of the size commonly found in economic applications can differ substantially, because of differences in both finite‐sample estimation efficiencies and residual regeneration methods.     

基于主元独立性分析与混合核RVM的复杂过程区间预测方法研究及应用

近年来,随着化工过程日趋复杂,对过程监控及关键变量预测提出了更高的要求。传统意义上的点预测已不能满足化工过程上的实际需求,且点预测无法描述过程上的不确定性问题,因此不能很好地把握预测变量的趋势。由此,提出了一种基于主元独立性分析（principal component independent analysis,PCIA）与混合核相关向量机（RVM）的区间预测方法。首先,结合核主元成分分析（KPCA）和独立元分析（ICA）对复杂过程原始变量进行主元成分提取和独立性分析,形成独立主元;其次,将高斯核函数与多项式核函数相结合形成混合核,与RVM结合对得到的独立主元进行回归建模预测,并运用T分布对预测值进行区间估计;然后,构造区间评价综合函数对区间估计结果进行优劣分析,在分析预测区间覆盖率（PICP）及预测区间宽度（NMPIW）的基础上,引入累积偏差（AD）提高区间评判的合理性。最后,将所提方法应用到TE仿真过程进行区间预测分析,仿真结果表明,提出的区间预测方法对实际生产过程具有较高的预测精度和区间估计质量,可以有效地预测关键变量的趋势。     

Axial Dispersion Model for Estimation of Ozone Self-Decomposition

A new method using the axial dispersion model for estimation of ozone self-decomposition kinetics in a semibatch bubble column reactor was developed. The reaction rate coefficients for literature equations of ozone decomposition and the gas phase dispersion coefficient were estimated and compared with literature data. The reaction order in the pH range 7–10 with respect to ozone 1.12 and 0.51 the hydroxyl ion were obtained, which is in good agreement with literature. The model parameters were determined by parameter estimation using a nonlinear optimization method. A sensitivity analysis was conducted to obtain information on reliability and identifiability of the estimated parameters.     

近红外透射光谱法测定黄芪提取液中总皂苷含量

应用傅立叶变换近红外光谱仪透射光谱技术对黄芪提取液中总皂苷含量进行检测分析,采用主成分分析(PCA)和偏最小二乘回归法(PLS)建立了黄芪提取液中皂苷类物质含量近红外数学校正集模型,其相关系数R为0.99943、校正集标准偏差(RMSEC)为 0.544、预测集标准偏差(RMSEP)为0.567.用建立的数学校正集模型检测未知样品的含量,预测标准偏差(RMSEP)为0.576.该方法快速、准确、无损,适于中药活性成分的快速检测分析.     

基于最小二乘支持向量机的蜡沉积速率预测

考虑蜡沉积影响因素的复杂性和最小二乘支持向量机在小样本预测方面的优势,基于最小二乘支持向量机预测的原理,通过优化最小二乘支持向量机的参数,建立了蜡沉积速率的预测模型,并对蜡沉积速率进行了预测。结果表明：该方法在样本数量较小时仍具有较高的精度,蜡沉积速率的预测值和实验值的吻合程度较好;最小二乘支持向量机建模时可以得到直观的函数表达式,而神经网络方法却不能得到模型的显式表达式,因此该方法具有明显的优势;应用径向基核（RBF）作为核函数时,不同初值的正则化参数?和核函数宽度?对预测结果具有较大影响,使用时应合理选择。     

Prediction of properties of diesel/biodiesel blends by infrared spectroscopy and multivariate calibration

Partial least squares models (PLS) using near and middle infrared spectrometry were developed to predict quality parameters of diesel/biodiesel blends (density, sulphur content and distillation temperatures). Practical aspects are discussed, such as calibration set composition; model efficiency using different infrared regions and spectrometers; and the calibration transfer problem. The root mean square errors of prediction, employing both regions and equipment, were comparable with the reproducibility of the corresponding standard method for the properties investigated. Calibration transfer between the two instruments, using direct standardization (DS), yielded prediction errors comparable to those obtained with complete recalibration of the secondary instrument.     

Partial least squares with outlier detection in spectral analysis: A tool to predict gasoline properties

The aim of this study is to propose a novel partial least squares with outlier detection (PLS_OD) calibration method and show its usefulness in calibration successfully with data containing outlying objects. We apply this method in gasoline spectral analysis to predict gasoline properties. In particular, a comparative study of PLS_OD and other five methods is presented. The performances of the proposed method are illustrated on spectral data set with and without outliers. The obtained results suggest that the proposed method can be used for constructing satisfactory gasoline prediction model whether there are some outliers or not.     

基于拉曼光谱的高密度聚乙烯质量检测

密度和熔融指数是高密度聚乙烯（HDPE）产品最重要的质量指标。本文通过拉曼光谱,结合偏最小二乘法（PLS）分析,实现了对HDPE密度和熔融指数的同时检测。通过对2700～2970 cm^-1范围内HDPE的拉曼光谱进行PLS分析,发现了HDPE的密度与短支链数量的负相关,并建立了HDPE密度的PLS回归模型。模型所得密度预测值与真实值的相关系数（r）、平均相对误差（ARD）和预测标准误差（SEP）分别为0.950、0.09%和1.02,优于近红外光谱和基于凝聚态结构分析的拉曼光谱的检测结果。利用HDPE乙烯基含量与熔融指数的正相关,通过分析1288～1650 cm^-1范围内的拉曼光谱,建立了HDPE熔融指数的PLS回归模型,所得熔融指数的预测值与真实值的r、ARD和SEP分别为0.966、8.61%和0.99。与熔融指数的红外光谱检测结果相比,拉曼光谱的检测结果具有更高的精度。     

Maximum quasi-likelihood estimation for the near(2) model

Abstract.  Maximum quasi-likelihood estimation is investigated for the NEAR(2) model, an autoregressive time series model with marginal exponential distributions. In certain regions of the parameter space, simulations indicate that maximum quasi-likelihood estimators perform better than two-stage conditional least squares estimators in terms of the per cent of estimates falling in the parameter space. The problem of out-of-range estimates is shown to be caused by the lack of information in the data rather than the characteristics of the method of estimation.     

基于KPLS模型的间歇过程产品质量控制

针对间歇过程所具有的非线性特性,提出了一种基于核偏最小二乘(KPLS)模型的最终产品质量控制策略。利用初始条件、批次展开后的过程数据以及最终产品质量建立了间歇过程的KPLS模型;采用基于主成分分析(PCA)映射的预估方法对未知的过程数据进行补充,实现了最终产品质量的在线预测。为了解决最终产品质量的控制,利用T2统计量确定KPLS模型的适用范围,并作为约束引入产品质量控制问题,提高控制策略的可行性;采用粒子群优化(PSO)算法实现了优化问题的高效求解。仿真结果表明,与基于偏最小二乘(PLS)模型的控制策略相比,所提出的方法具有更高的预测精度,且能有效解决产品质量控制中出现的各种问题。