基于变量分组DTW-MCVA的不等长间歇过程故障检测方法

针对不等长间歇过程监控中批次数据同步化未能充分挖掘局部信息的问题,提出一种基于变量分组DTW-MCVA（VGDTW-CVA）的不等长间歇过程故障检测方法。首先,利用互信息矩阵描述不等长间歇过程测量变量之间的相关性,并基于互信息矩阵进行变量分组。然后利用DTW算法对各个变量组分别进行同步化,并将同步化后的变量组整合为完整的三维数据集。最后,利用MCVA方法建立动态监控模型实现对间歇生产过程的在线监控。盘尼西林发酵过程的仿真结果表明,VGDTW-MCVA能够比基本的DTW-MCVA方法更好地监控间歇过程故障。     

基于变量分组DTW-MCVA的不等长间歇过程故障检测方法

针对不等长间歇过程监控中批次数据同步化未能充分挖掘局部信息的问题,提出一种基于变量分组DTW-MCVA (VGDTW-CVA)的不等长间歇过程故障检测方法。首先,利用互信息矩阵描述不等长间歇过程测量变量之间的相关性,并基于互信息矩阵进行变量分组。然后利用DTW算法对各个变量组分别进行同步化,并将同步化后的变量组整合为完整的三维数据集。最后,利用MCVA方法建立动态监控模型实现对间歇生产过程的在线监控。盘尼西林发酵过程的仿真结果表明,VGDTW-MCVA能够比基本的DTW-MCVA方法更好地监控间歇过程故障。     

基于核慢特征回归与互信息的常压塔软测量建模

针对工业过程的非线性及动态特性,提出了一种新的慢特征回归软测量方法。该方法首先通过添加时延数据构造动态数据集,利用互信息最大化准则筛选变量从而减少信息冗余的影响。同时该方法在慢特征分析的基础上引入核函数扩展,加强模型处理非线性数据的能力,并将获得的核慢特征用于回归建模。核慢特征分析通过分析样本的变化,提取具有缓慢变化特征的成分,可以有效地刻画工业过程的变化趋势,提升回归模型精度。最后该方法的有效性在常压塔常顶油干点与常一线初馏点的软测量模型中得到了验证。     

基于核慢特征回归与互信息的常压塔软测量建模

针对工业过程的非线性及动态特性,提出了一种新的慢特征回归软测量方法。该方法首先通过添加时延数据构造动态数据集,利用互信息最大化准则筛选变量从而减少信息冗余的影响。同时该方法在慢特征分析的基础上引入核函数扩展,加强模型处理非线性数据的能力,并将获得的核慢特征用于回归建模。核慢特征分析通过分析样本的变化,提取具有缓慢变化特征的成分,可以有效地刻画工业过程的变化趋势,提升回归模型精度。最后该方法的有效性在常压塔常顶油干点与常一线初馏点的软测量模型中得到了验证。     

基于神经网络的常压塔柴油凝点软测量的研究与应用

研究某炼油厂常压塔三线柴油凝点的软测量建模问题,分析过程变量对柴油凝点的影响。基于在线分析仪6min采样数据,利用前向网络和时延前向网络(TDNN)分别建立了三线柴油凝点的静态软测量模型和动态软测量模型,并结合在线分析仪对模型实现了在线修正。通过两种模型的仿真和在线实施效果,表明基于神经网络的软测量模型取得了较好的应用效果,而且动态模型的实施效果优于静态模型。     

基于二子空间协同训练算法的半监督软测量建模

在工业过程中,存在着辅助变量与主导变量数据比例严重失衡的问题。协同训练算法是其中一种利用无标签数据中的潜在信息以提升学习性能的模型训练方法。然而目前在协同训练软测量建模过程中,学习器之间存在严重的训练特性交叉重叠的问题,这将导致对主导变量的预测性能衰减。针对这一问题,提出基于二子空间协同训练算法的半监督软测量模型two-subspace co-training KNN(TSCO-KNN)。该模型将二子空间分块算法与协同训练算法相结合,利用辅助变量与主成分子空间PCS和残差子空间RS两个特征子空间的相关性程度,将数据变量拆分为两个具有显著差异性的学习数据集,进而使用KNN回归器进行协同训练,共同用于对主导变量的预测。最后在乙烯精馏塔塔顶乙烷浓度和TE过程产品浓度软测量中进行仿真研究,验证本文所提算法的有效性。     

基于图卷积网络的柴油加氢生产软测量建模

精制柴油闪点和石脑油终馏点是柴油加氢生产最重要的质量指标，但目前缺乏测量这两种指标的在线分析仪表，软测量是可行的替代方案。为完成这两种指标的软测量建模，分析柴油加氢生产过程的工艺机理和过程数据特征，完成了辅助变量的重构和筛选，确定了两个软测量对象的辅助变量集，基于图卷积网络建立闪点和终馏点的软测量模型进行仿真研究。仿真研究结果表明：相比于目前应用广泛的软测量模型，所提出的软测量方法具有更高的精度，可以提升柴油加氢生产软测量建模的有效性和准确性。     

基于快速独立分量分析的苯酚浓度软测量

针对软测量技术中辅助变量间可能存在的复杂的内在联系给辅助变量选择及提高模型精度等方面带来的诸多不利因素,提出了一种基于负熵最大的快速独立分量分析(Fast-ICA)方法,可以有效地消除辅助变量间的信息冗余现象,得到相互独立的分量.再通过互信息分析各个分量和主导变量间的内在联系,选择和主导变量联系较大的分量用于模型训练,并将其应用到苯酚(BF)浓度的软测量中.仿真结果表明:从经过ICA分解的独立分量中提取出样本特征并用于支持向量机模型(SVM)的训练,可以有效地减少冗余信息的干扰,提高软测量模型的估计精度和泛化能力.     

化工过程软测量建模方法研究进展

软测量仪表是解决化工过程中质量变量难以实时测量的重要手段。软测量仪表的核心问题是软测量建模。阐述了软测量建模与辨识和非线性建模的关系:质量变量和易测变量的动态关系存在于增量之间,辨识模型依赖于增量数据,软测量建模则是依赖于实测变量数据来获取这个动态关系;非线性建模建立了变量间的静态关系,忽略了对象动态特性,而软测量建模要兼顾对动态特性的表征。随着人们对过程特性的认识加深,软测量建模方法不断发展,经历了从机理建模到数据驱动建模,从线性建模到非线性建模,从静态建模到动态建模的过程。详细讨论了软测量建模的发展过程,众多建模方法的优缺点及适用情况和现在建模的热点,最后对软测量建模方法进行了总体展望。     

基于k-近邻互信息的发酵过程高斯过程回归建模

发酵过程中基质浓度往往无法在线测量,采用高斯过程回归（GPR）建立基质浓度的估计模型,实现了其软测量。不同于传统软测量方法对基质浓度的估计,该方法不仅可以得到估计值,还能够得到其估计方差。考虑到发酵过程中各变量之间的非线性、相关性,为了提高模型的预测性能,在模型建立之前首先用k-近邻互信息（k-MI）辅助变量选择方法对模型的输入变量进行选择。从青霉素发酵过程的应用结果来看,采用kMI-GPR方法取得了较好的估计效果。     

选择性集成LTDGPR模型的自适应软测量建模方法

随着时间的增加,传统时间差（TD）模型会出现性能显著下降的问题。为了提高TD模型的可靠性和预测精度,同时考虑过程的时滞特征,基于一种选择性集成策略,提出一种局部时间差高斯过程回归（LTDGPR）模型的自适应软测量建模方法。首先,提取出数据库中的时滞动态信息,对建模数据进行重构;然后,采取局部化策略对差分后的重构样本进行统计划分,得到LTDGPR模型集。对于新来的输入样本,选择部分泛化能力强的LTDGPR模型进行集成,估计出含一定时间差的主导变量动态偏移值;最后,基于TD模型思想对当前时刻主导变量值进行在线预测。通过脱丁烷塔过程的数据建模仿真研究,验证了所提方法的有效性和精度。     

基于互信息的分散式动态PCA故障检测方法

对现代大型复杂动态过程来讲,不同测量变量会存在不同的序列相关性,而且变量间的相互影响会体现在不同的采样时刻上。为此,结合利用分散式建模的优势,提出一种基于互信息的分散式动态过程故障检测方法。该方法在对每个测量变量都引入多个延时测量值后,利用互信息为每个变量区分出与其相关的测量值,并建立起相应的变量子块。这种变量分块方式使每个变量子块都能充分地获取与之相对应的自相关性与交叉相关性信息,较好地处理了数据的动态性问题。然后,利用主元分析（PCA）算法对每一变量子块进行统计建模从而建立起适于大规模动态过程的多模块化的故障检测模型。最后,通过实例验证该方法用于动态过程监测的可行性和有效性。     

Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables. In practical application scenarios, however, the feedback cycle of target variable is usually larger than that of the process variables, which causes the deficiency of prediction errors. Consequently soft sensor cannot be calibrated timely and deteriorates. We proposed a soft sensor calibration method by using Just-in-time modeling and AdaBoost learning method. A moving window consisting of a primary part and a secondary part is constructed. The primary part is made of history data from certain number of constant feedback cycles of target variable and the secondary part includes some coarse target values estimated initially by Just-in-time modeling during the latest feedback cycle of target variable. The data set of the whole moving window is processed by AdaBoost learning method to build an auxiliary estimation model and then target variable values of the latest corresponding feedback cycle are reestimated. Finally the soft sensor model is calibrated by using the reestimated target variable values when the target feedback is unavailable; otherwise using the feedback value. The feasibility and effectiveness of the proposed calibration method is tested and verified through a series of comparative experiments on a pH neutralization facility in our laboratory.     

基于OS-ELM的游梁式抽油机系统电动机负载扭矩的在线混合建模

由于难以掌握电动机工作效率与复杂动态负载的准确关系,游梁式抽油机系统普遍存在“大马拉小车”的现象。针对这个问题,研究负载动态变化下电动机负载扭矩的建模新方法,将“驴头”悬点载荷看作系统的负载,提出了基于OS-ELM的在线混合模型。首先根据采油工作原理,建立系统各机构的机理模型;然后针对模型中的主要不确定参数--井下摩擦力,建立基于OS-ELM的在线软测量模型,首先由历史生产数据离线训练得到初始结构,其次采用滑动窗口方法指导模型的在线更新。通过研究,井下摩擦力不再是依赖主观经验给定的定值,而是跟随系统变化的动态值,这更加符合实际生产工况。由一口生产井进行实例验证,仿真结果表明本文所提出方法是合理有效的。     

Deep learning for quality prediction of nonlinear dynamic processes with variable attention-based long short-term memory network

Industrial processes are often characterized with high nonlinearities and dynamics. For soft sensor modelling, it is important to model the nonlinear and dynamic relationship between input and output data. Thus, long short-term memory (LSTM) networks are suitable for quality prediction of soft sensor modelling. However, they do not consider the relevance of different input variables with the quality variable. To address this issue, a variable attention-based long short-term memory (VA-LSTM) network is proposed for soft sensing in this paper. In VA-LSTM, variable attention is designed to identify important input variables according to their relevance with quality prediction. After that, different attention weights are calculated and assigned to further obtain a weighted input sample at each time step. Finally, the LSTM network is exploited to capture the long-term dependencies of the weighted input time series to predict the quality variable. The performance of the proposed modelling method is validated on an industrial debutanizer column and a hydrocracking process.     

Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models

Linear models can be inappropriate when dealing with nonlinear and multimode processes, leading to a soft sensor with poor performance. Due to time-varying process behaviour it is necessary to derive and implement some kind of adaptation mechanism in order to keep the soft sensor performance at a desired level. Therefore, an adaptation mechanism for a soft sensor based on a mixture of Gaussian process regression models is proposed in this paper. A procedure for input variable selection based on mutual information is also presented. This procedure selects the most important input variables for output variable prediction, thus simplifying model development and adaptation. Apart from online prediction of the difficult-to-measure variable, this soft sensor can be used for adaptive process monitoring. The efficiency of the proposed method is benchmarked with the commonly applied recursive PLS and recursive PCA method on the Tennessee Eastman process and two real industrial examples.     

Modeling and identification for soft sensor systems based on the separation of multi-dynamic and static characteristics

Data-driven soft sensor is an effective solution to provide rapid and reliable estimations for key quality variables online.The secondary variables affect the primary variable in considerably different speed,and soft sensor systems exhibit multi-dynamic characteristics.Thus,the first contribution is improving the model in the previous study with multi-time-constant.The characteristics-separation-based model will be identified in substep way,and the stochastic Newton recursive (SNR) algorithm is adopted.Considering the dual-rate characteristics of soft sensor systems,the proposed model cannot be identified directly.Thus,two auxiliary models are first proposed to offer the intersample estimations at each update period,based on which the improved algorithm (DAM-SNR) is derived.These two auxiliary models function in switching mechanism which has been illustrated in detail.This algorithm serves for the identification of the proposed model together with the SNR algorithm,and the identification procedure is then presented.Finally,the laboratorial case confirms the effectiveness of the proposed soft sensor model and the algorithms.     

Application of support vector regression for developing soft sensors for nonlinear processes

The field of soft sensor development has gained significant importance in the recent past with the development of efficient and easily employable computational tools for this purpose. The basic idea is to convert the information contained in the input–output data collected from the process into a mathematical model. Such a mathematical model can be used as a cost efficient substitute for hardware sensors. The Support Vector Regression (SVR) tool is one such computational tool that has recently received much attention in the system identification literature, especially because of its successes in building nonlinear blackbox models. The main feature of the algorithm is the use of a nonlinear kernel transformation to map the input variables into a feature space so that their relationship with the output variable becomes linear in the transformed space. This method has excellent generalisation capabilities to high‐dimensional nonlinear problems due to the use of functions such as the radial basis functions which have good approximation capabilities as kernels. Another attractive feature of the method is its convex optimization formulation which eradicates the problem of local minima while identifying the nonlinear models. In this work, we demonstrate the application of SVR as an efficient and easy‐to‐use tool for developing soft sensors for nonlinear processes. In an industrial case study, we illustrate the development of a steady‐state Melt Index soft sensor for an industrial scale ethylene vinyl acetate (EVA) polymer extrusion process using SVR. The SVR‐based soft sensor, valid over a wide range of melt indices, outperformed the existing nonlinear least‐square‐based soft sensor in terms of lower prediction errors. In the remaining two other case studies, we demonstrate the application of SVR for developing soft sensors in the form of dynamic models for two nonlinear processes: a simulated pH neutralisation process and a laboratory scale twin screw polymer extrusion process. A heuristic procedure is proposed for developing a dynamic nonlinear‐ARX model‐based soft sensor using SVR, in which the optimal delay and orders are automatically arrived at using the input–output data.