基于Bootstrap多神经网络的软测量方法

针对原油蒸馏过程常规软测量模型难以适应原油进料性质变化的问题,提出Bootstrap多神经网络的非线性软测量处理策略.通过Bootstrap算法复制出训练集样本空间上的多个样本子空间,训练出多神经网络模型,避免了单个神经网络易于陷入局部最优及过度训练的弱点,具有较高的准确率和泛化能力.本处理策略用于建立常压塔一线干点的软测量模型,仿真结果表明模型预测准确率和鲁棒性较好,对原油性质变化具有较好的适应性.该方法将会改进实际蒸馏过程在进料性质变化情况下的产品质量指标的软测量精度.     

基于Bootstrap多神经网络的软测量方法

针对原油蒸馏过程常规软测量模型难以适应原油进料性质变化的问题,提出Bootstrap多神经网络的非线性软测量处理策略。通过Bootstrap算法复制出训练集样本空间上的多个样本子空间,训练出多神经网络模型,避免了单个神经网络易于陷入局部最优及过度训练的弱点,具有较高的准确率和泛化能力。本处理策略用于建立常压塔一线干点的软测量模型,仿真结果表明模型预测准确率和鲁棒性较好,对原油性质变化具有较好的适应性。该方法将会改进实际蒸馏过程在进料性质变化情况下的产品质量指标的软测量精度。     

常减压装置初馏塔顶产品干点软测量的应用研究

在常减压装置中,影响初馏塔顶石脑油干点的因素很多,反应十分复杂,故难以建立准确的机理模型.针对传统的主元分析法(PCA)或自适应模糊推理系统(ANFIS)建立软测模型中的缺点,本文提出采用主元分析法预处理输入变量,再结合自适应模糊推理系统,进行常减压装置初馏塔顶石脑油干点的软测量模型的改进,能及时测定化工过程的变量,对稳定生产过程,有效控制产品质量具有重要意义.通过MATLAB仿真,表明该改进型方法的软测建模效果较好,建模的训练时间大大节省了,且泛化能力和拟合精度很好.     

融入先验知识的径向基神经网络软测量建模

针对神经网络软测量建模过程中有效信息丢失的情况,在传统3层径向基神经网络(RBFNN)模型的输入层和隐含层之间引入先验层。先验层与输入层之间的权值可直接表征通过机理、统计或者人工智能算法分析得到的先验知识,即各个输入变量的重要程度信息,该权值的变化可以改变RBFNN聚类的空间形状,使得样本在训练过程中的聚类更为合理,从而提高了RBFNN软测量模型的预测精度。RBFNN模型在污水处理过程的生化需氧量(BOD)预测中得到了验证。仿真结果表明,相比传统3层RBFNN网络,融入先验知识的4层RBFNN软测量模型具有更优异的拟合能力。     

浮选生产过程经济技术指标的软测量建模

依据浮选过程的工艺机理和操作经验,初选了浮选过程经济技术指标神经网络软测量模型的输入变量,运用主元分析法对输入变量进行主元分解,降低输入变量维数且消除了输入变量之间的线性相关性,再通过基于最近邻聚类学习算法的径向基函数神经网络进行建模。仿真结果表明,该模型具有较快的训练速率和较高的预测精度,可以满足浮选过程实时控制的在线软测量要求。     

虚拟蒸馏装置及软测量方法研究

利用HYSYS流程模拟软件建立虚拟常减压装置。为研究软测量方法提供准确、方便和科学的研究条件。通过对常减压装置负荷变化的真实模拟。探讨了负荷变化对软测量模型泛化能力影响和改进软测量模型的途径。针对基于RBF神经网络常减压装置汽油产品的干点软测量模型的负荷变化问题。提出的改进方法增强了其在实际生产过程应用的适应范围．有利于该方法在实际生产过程中的长期可靠应用。     

基于多神经网络结构的常压塔侧线产品质量软测量

根据常压塔的原料进料及产品多变，提出采用多神经网络结构建立侧线产品质量软测量模型。利用基于马氏距离的数据分类技术、对输入样本分类。利用产品质量化验分析值，对软测量模型进行校正。实际应用表明多神经网络结构的软测量精度高。     

时序-神经网络模型在磨煤机一次风量测量中的应用

针对制粉系统存在的大惯性和大迟延等特点,提出了一种基于时序-神经网络的一次风量软测量模型。在建模过程中,考虑了生产过程输入变量和输出变量的时序,给出了辅助变量选取和数据预处理方法。某电厂实际运行结果表明,该模型的准确性较目前广泛应用的静态神经网络软测量模型有显著提高。该研究为磨煤机一次风量的测量提供了一定的理论基础。     

常减压装置初馏塔物料平衡控制的实施

介绍一个以物料平衡为模型的多变量控制系统。该多变量系统对常减压装置的初馏塔进行物料平衡控制，即在初馏塔的进料量等于流出量的基础上，加上塔底液位的变化量作预测控制以及进料换热后的温度变化作为前馈调节量。该方案投用后，常减压装置在提、降量的过程中以及原油性质频繁变化时，初馏塔均能达到很好的控制效果，使产品质量保持稳定，取得了令人满意的结果。     

基于特征提取和极限学习机的软测量方法

针对建模数据存在的高维、共线性等特征,以及常用的基于人工智能的建模方法存在的模型结构难以确定、学习速度慢等缺点,提出了由基于主元分析(PCA)的特征提取和基于优化极限学习机(OELM)的建模算法两部分组成的软测量方法.采用PCA消除输入变量间的共线性并降低输入变量维数,以提取的线性无关的独立变量作为软测量模型的输入,从而简化模型结构.采用集成极限学习机(ELM)与支持向量机(SVM)算法优点的OELM方法作为建模算法,避免了ELM模型的随机性和SVM模型求解的复杂性.将特征提取方法与OELM方法结合后,提高了软测量模型的训练速度和预测性能.采用所述方法,对混凝土抗压强度的软测量问题进行了实验研究,验证了所提方法的有效性.该方法同时可以应用于基于雷达、光电等高维数据的目标识别,具有广阔的应用前景.     

基于FA-SVR的丙酮精制产品质量软测量模型

针对某丙酮精制过程,提出采用FA与SVR相结合的方法建立丙酮产品质量的软测量模型。采用因子分析(FA)方法提取辅助变量的特征信息,并消除各变量之间的相关性,然后利用支持向量回归(SVR)建立丙酮产品质量指标的软测量模型。在实际生产过程数据上进行了仿真实验,并与传统的稳健回归分析及神经网络等方法进行了比较,结果表明本方法具有良好的预测效果。     

基于因子回归模型的软测量方法

在工业过程中,有很多重要变量往往无法在线检测,通常通过软测量方法进行估计,主元回归是其中1种常用方法。相比于主元,因子更具广泛意义,更能反映数据的本质特征。基于此,提出1种基于因子回归模型的软测量方法,先对过程日常运行数据进行因子分析,建立因子生成模型,并提取因子信息,然后建立因子与关键变量间的因子回归模型,在线应用时先将可测变量代入生成模型得到因子变量,然后将因子代入到因子回归模型,软测量出关键变量。将该方法应用到化工吸附分离过程中,比较了因子回归模型与主元回归模型的软测量效果,结果表明前者优于后者。     

Product Quality Prediction by a Neural Soft-Sensor Based on MSA and PCA

A novel soft-sensor model which incorporates PCA (principal component analysis), RBF (Radial Basis Function) networks, and MSA (Multi-scale analysis), is proposed to infer the properties of manufactured products from real process variables. PCA is carried out to select the most relevant process features and to eliminate the correlations of input variables; multi-scale analysis is introduced to acquire much more information and to reduce uncertainty in the system; and RBF networks are used to characterize the nonlinearity of the process. A prediction of the melt index (MI), or quality of polypropylene produced in an actual industrial process, is taken as a case study. Research results show that the proposed method provides promising prediction reliability and accuracy.     

Inferential estimation of kerosene dry point in refineries with varying crudes

A bootstrap aggregated model approach to the estimation of product quality in refineries with varying crudes is proposed in this paper. The varying crudes cause the relationship between process variables and product quality variables to change, which makes product quality estimation by soft-sensors a difficult problem. The essential idea in this paper is to build an inferential estimation model for each type of feed oil and use an on-line feed oil classifier to determine the feed oil type. Bootstrap aggregated neural networks are used in developing the on-line feed oil classifier and a bootstrap aggregated partial least square regression model is developed for each data group corresponding to each type of feed crude oil. The amount of training data in crude oil distillation is usually small and this brings difficulties for classification and estimation modelling. In order to enhance model reliability and robustness, bootstrap aggregated models are developed. The inferential estimation results of kerosene dry point on both simulated data and industrial data show that the proposed method can significantly improve the overall inferential estimation performance.     

炼油厂原油蒸馏装置软仪表技术的研究与应用

原油蒸馏的产品指标都是用ASTM沸点为质量衡量标准,操作工通常都是依赖化验分析数据进行操作,这样常使得操作工操作经常远离约束区.在线分析仪较之化验分析数据有很大改进,但在线分析仪购置费用昂贵,维护工作量大,提供的分析数据滞后较大,不适合闭环控制.文中开发的炼油厂原油蒸馏装置软仪表技术采用了独特的压力补偿温度机制,其最大...     

D-FNN based soft-sensor modeling and migration reconfiguration of polymerizing process

A soft-sensor modeling method based on dynamic fuzzy neural network (D-FNN) is proposed for forecasting the key technology indicator convention velocity of vinyl chloride monomer (VCM) in the polyvinylchloride (PVC) polymerizing process. Based on the problem complexity and precision demand, D-FNN model can be constructed combining the system prior knowledge. Firstly, kernel principal component analysis (KPCA) method is adopted to select the auxiliary variables of soft-sensing model in order to reduce the model dimensionality. Then a hybrid structure and parameters learning algorithm of D-FNN is proposed to achieve the favorable approximation performance, which includes the rule extraction principles, the classification learning strategy, the precedent parameters arrangements, the rule trimming technology based on error descendent ratio and the consequent parameters decision based on extended Kalman filter (EKF). The proposed soft-sensor model can automatically determine if the fuzzy rules are generated/eliminated or not so as to realize the nonlinear mapping between input and output variables of the discussed soft-sensor model. Model migration method is adopted to realize the on-line adaptive revision and reconfiguration of soft-sensor model. In the end, simulation results show that the proposed model can significantly enhance the predictive accuracy and robustness of the technical-and-economic indexes and satisfy the real-time control requirements of PVC polymerizing production process.     

A virtual metrology model based on recursive canonical variate analysis with applications to sputtering process

In data driven process monitoring, soft-sensor, or virtual metrology (VM) model is often employed to predict product's quality variables using sensor variables of the manufacturing process. Partial least squares (PLS) are commonly used to achieve this purpose. However, PLS seeks the direction of maximum co-variation between process variables and quality variables. Hence, a PLS model may include the directions representing variations in the process sensor variables that are irrelevant to predicting quality variables. In this case, when direction of sensor variables’ variations most influential to quality variables is nearly orthogonal to direction of largest process variations, a PLS model will lack generalization capability. In contrast to PLS, canonical variate analysis (CVA) identifies a set of basis vector pairs which would maximize the correlation between input and output. Thus, it may uncover complex relationships that reflect the structure between quality variables and process sensor variables. In this work, an adaptive VM based on recursive CVA (RCVA) is proposed. Case study on a numerical example demonstrates the capability of CVA-based VM model compared to PLS-based VM model. Superiority of the proposed model is also presented when it applied to an industrial sputtering process.     

基于多元逐步回归和反向传播方法的粗汽油干点软测量模型

建立了粗汽油干点软测量模型。模型分别采用多元逐步回归方法和反向传播方法。结果表明：多元逐步回归方法可筛选自变量，但会将一些重要因素剔除；而神经网络可通过预选输入单元确定网络结构。通过对建立好的模型进行预测，可获得较满意的粗汽油干点值。     

Neural network-based identification of SMB chromatographic processes

In this contribution, the identification problem for the control of nonlinear simulated moving bed (SMB) chromatographic processes is addressed. For process control the flow rates of extract, desorbent, and recycle of the SMB process, and the switching time are the manipulated variables. But these variables influence the process in a strongly coupled manner. Therefore, a new set of input variables is introduced by a nonlinear transformation of the physical inputs, such that the couplings are reduced considerably. The front positions of the axial concentration profile are taken as model outputs. Multilayer feedforward neural networks (NN) are utilized as approximating models of the nonlinear input–output behavior. The gradient distribution of the model outputs with respect to the inputs is used to determine their structural parameters and the network size is chosen by the SVD method. To illustrate the effectiveness of the identification method, a laboratory scale SMB process is used as an example. The simulation results of the identified model confirm a very good approximation of the first principles models and exhibit a satisfactory long-range prediction performance.