基于集成学习的多产品化工过程软测量建模方法

化工过程通常具有非线性、时变以及多产品等特性。针对上述特点,在集成学习框架下建立自适应软测量模型。首先,面向具有多个产品的化工对象,借助k近邻法,以统计假设检验理论为依据,提出一种自适应局部化方法,获得多样性程度高的局部模型集合。然后,根据未知样本量化局部模型的泛化能力,通过选择性集成方法获得主导变量的估计值。此外,为了对主导变量估计值的精度进行评估,基于局部模型泛化误差,给出一种通用性高的模型性能评价方法。在仿真的盘尼西林生产过程上的运行结果验证了所提方法的有效性。     

A review of just-in-time learning-based soft sensor in industrial process

Data-driven soft sensing approaches have been a hot research field for decades and are increasingly used in industrial processes due to their advantages of easy implementation and high efficiency. However, nonlinear and time-varying problems widely exist in practical industrial processes. Just-in-time learning (JITL) was proposed to solve these problems and has attracted great attention in practical applications. To present a comprehensive review of JITL-based soft sensor studies and provide detailed technical guidance for new researchers, this paper introduces the recent research on JITL-based soft sensor modelling methods in the industrial process from three aspects: similarity criterion, sample subset, and local model, which include the whole process of establishing a JITL-based soft sensor. Moreover, the future research and innovation directions of JITL-based soft sensors in industrial processes are also prospected.     

Soft sensor based on multi-phase stacking ensemble model with self-selected primary learner for batch processes

In batch processes, existing soft sensing methodologies encounter substantial challenges when confronted with nonlinearity and multi-phase issues. In response to these challenges, an innovative soft sensing framework known as the multi-phase stacking ensemble model with self-selected primary learner is proposed. The main innovation of this framework lies in the solution to the primary learner selection issue within the stacking model. To commence, the batch process is divided into multiple phases employing a Gaussian mixture model, thereby establishing local ensemble models for each phase. Subsequently, the iterative self-selection of primary learners strategy is proposed, which iteratively selects suitable primary learners for these models, optimizing their combination of primary learners for each local model. This primary learner selection strategy effectively enhances the accuracy of predictions in the stacking ensemble model. To further enhance the performance, Bayesian optimization is utilized to tune the hyperparameters of each local ensemble model. This step guarantees optimal performance of the model across diverse phases. Extensive simulation experiments are conducted on an industrial penicillin fermentation process to validate the effectiveness of the proposed framework. According to the findings, the model demonstrated superior performance compared to existing single-learner soft sensing methods and commonly utilized ensemble-based soft sensing methods in terms of both R² score (0.97584) and RMSE (0.0513). Overall, this framework offers a novel approach for selecting primary learners in stacking ensemble models and enhancing the predictive performance in batch processes for soft sensing.     

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.     

基于流形正则化域适应湿式球磨机负荷参数软测量

针对多工况条件下球磨机关键负荷参数测量面临的复杂性问题,提出基于流形正则化域适应（domain adaptation with manifold regularization,DAMR）湿式球磨机负荷参数软测量的方法。该方法首先采用集成流形约束、最大方差及最大均值差异寻找特征变换矩阵,然后,将源建模领域和未建模领域的特征信息投射到公共子空间,最后,在子空间建立模型得到球磨机关键负荷参数的预测值。实验结果表明该方法能以较高的精度实现未知工况下湿式球磨机关键负荷参数的预测,且该方法对于流程工业多工况软测量和过程监控研究有一定的参考价值。     

基于递推PLS核算法的软测量在线学习方法

针对过程的动态时变特性,提出一种基于PLS核算法的软测量在线学习方法。该方法利用PLS核算法,通过递推学习具有代表性的新样本来改善模型的适应能力,较NIPALS算法具有更高的计算效率;并采用一种同时考虑输入和输出信息的相似度准则,有选择地删除一个或多个冗余样本,更有效地构建了训练样本集。工业聚丙烯熔融指数的软测量建模研究表明,本文提出的方法能够快速有效地跟踪牌号切换中熔融指数的变化。     

基于差分进化算法-最小二乘支持向量机的软测量建模

软测量技术是解决工业过程中存在的一类难以在线测量参数估计问题的有效方法,该技术的核心是建立优良的数学模型。支持向量机是基于统计学理论的一种机器学习方法,最小二乘支持向量机是一种扩展的支持向量机,相对于支持向量机具有较快求解速度。最小二乘支持向量机存在着参数选择的问题,针对这个问题,采用差分进化算法进行参数选择。提出基于差分进化算法的最小二乘支持向量机应用于软测量建模,并将其应用于对苯二甲酸中对羧基苯甲醛含量测试的软测量建模中,获得了满意的结果。     

基于在线动态高斯过程回归抽油井动液面软测量建模

实践中, 抽油井动液面都是使用回声仪测试的, 无法实时在线检测。而基于示功图分析的动液面实时在线检测方法存在计算精度不高的缺陷。考虑到数据驱动软测量建模方法存在随时间推移出现的模型老化现象, 采用一种增量学习动态高斯过程回归(IDGPR)软测量建模方法, 实现对抽油井动液面深度的实时在线检测。首先建立基本动态高斯过程回归软测量模型, 在模型投入现场运行后, 通过一种增量学习算法对模型进行在线更新, 使其不断适应油井工况变化, 自适应获得更加准确的软测量模型。现场应用表明, 该软测量模型具有较高的预测精度和较好的泛化能力, 可以满足工程应用要求。     

Local learning‐based adaptive soft sensor for catalyst activation prediction

This work presents an algorithm for the development of adaptive soft sensors. The method is based on the local learning framework, where locally valid models are built and maintained. In this framework, it is possible to model nonlinear relationship between the input and output data by the means of a combination of linear models. The method provides the possibility to perform adaptation at two levels: (i) recursive adaptation of the local models and (ii) the adaptation of the combination weights. The dataset used for evaluation of the algorithm describes a polymerization reactor where the target value is a simulated catalyst activity in the reactor. This dataset is also used to evaluate the performance of the proposed algorithm. The results show that the traditional recursive partial least squares algorithm struggles to deliver accurate predictions. In contrast to this, by exploiting the two‐level adaptation scheme, the proposed algorithm delivers more accurate results. © 2010 American Institute of Chemical Engineers AIChE J, 57, 2011     

基于稳定Hammerstein模型的在线软测量建模方法及应用

针对复杂工业过程中由于存在未建模动态和不确定干扰,导致关键变量的软测量精度下降的问题,提出了一种基于稳定Hammerstein模型(H模型)的在线软测量建模方法。H模型的非线性增益采用带有时变稳定学习算法的小波神经网络模型,线性系统部分采用基于递推最小二乘的ARX模型,基于输入到状态稳定性理论证明了H模型辨识误差的有界性。其中小波神经网络具有表征强非线性的特性,稳定学习算法可抑制未建模动态和不确定干扰的影响,改善了模型的预测精度和自适应能力。以典型非线性系统和实际污水处理过程为例进行了仿真研究,结果表明,基于稳定H模型的软测量方法具有较高的在线软测量精度。     

Review of adaptation mechanisms for data-driven soft sensors

In this article, we review and discuss algorithms for adaptive data-driven soft sensing. In order to be able to provide a comprehensive overview of the adaptation techniques, adaptive soft sensing methods are reviewed from the perspective of machine learning theory for adaptive learning systems. In particular, the concept drift theory is exploited to classify the algorithms into three different types, which are: (i) moving windows techniques; (ii) recursive adaptation techniques; and (iii) ensemble-based methods. The most significant algorithms are described in some detail and critically reviewed in this work. We also provide a comprehensive list of publications where adaptive soft sensors were proposed and applied to practical problems. Furthermore in order to enable the comparison of different methods to standard soft sensor applications, a list of publicly available data sets for the development of data-driven soft sensors is presented.     

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。     

化工过程深度神经网络软测量的结构与参数自动调整方法

深度学习在流程工业的软测量领域已经得到了应用。然而,深度神经网络（DNN）的结构和参数需要人工调整,这需要扎实的机器学习知识基础和丰富的参数调整经验,烦琐的调整过程限制了深度学习在化工领域的推广应用。在大量实验的基础上,对DNN的每个关键参数的选取过程进行了系统化的分析,提出了几乎无须人工干预的基于DNN软测量的结构和参数自动调整方法,极大地简化了参数调整过程,能够给工程技术人员学习及应用深度学习提供参考。对原油蒸馏装置及煤气化装置的案例分析验证了所提出方法的有效性和通用性。     

Dynamic soft sensor development based on Gaussian mixture regression for fermentation processes

The dynamic soft sensor based on a single Gaussian process regression (GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation processes,may result in large prediction errors and complexity of the soft sensor.Therefore,a dynamic soft sensor based on Gaussian mixture regression (GMR) was proposed to overcome the problems.Two structure parameters,the number of Gaussian components and the order of the model,are crucial to the soft sensor model.To achieve a simple and effective soft sensor,an iterative strategy was proposed to optimize the two structure parameters synchronously.For the aim of comparisons,the proposed dynamic GMR soft sensor and the existing dynamic GPR soft sensor were both investigated to estimate biomass concentration in a Penicillin simulation process and an industrial Erythromycin fermentation process.Results show that the proposed dynamic GMR soft sensor has higher prediction accuracy and is more suitable for dynamic multiphase/multimode fermentation processes.     

External analysis‐based regression model for robust soft sensing of multimode chemical processes

To remove the influence of operation mode changes in the chemical process, the whole variable set is partitioned into external, main, and quality variables. External variables are related to the operation mode. Two regression models are initially developed between external variables and main variables/quality variables, based on which the influence of the operation mode is removed from both input and output of the soft sensor. Then, an additional regression model is constructed for soft sensing, which is robust to the change of the operation mode. Compared to existing methods, the new method has advantages to handle two critical issues: (1) capable of quality estimation in new process modes; (2) able to distinguish changes in operation modes from process faults. Besides, a monitoring and analysis strategy is proposed for performance evaluation of the new soft sensor. Two case studies are provided to illustrate the efficiency of the proposed method. © 2013 American Institute of Chemical Engineers AIChE J, 60: 136–147, 2014     

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.     

一种基于支持向量机增量学习的软测量建模方法

针对软测量模型在现场的失效问题,提出一种基于支持向量增量学习的软测量建模方法,将增量样本中违背Karush-Kuhn-Tucker条件的样本引入到工作样本集中,同时将非支持向量中到特征空间超球球心距离较小的样本剔除出工作样本集。并将提出的方法用于对二甲苯吸附分离过程中产品纯度的预测中。     

基于GA-SVM的烟气含氧量软测量

针对电站锅炉烟气含氧量传统硬件测量方法成本昂贵、使用寿命短等缺陷,提出一种基于支持向量机的软测量方法。首先结合机理分析和数据相关性分析选取相关过程参数作为模型输入参数,使用遗传算法对支持向量机进行参数寻优,构建基于遗传算法参数优化的支持向量机(GA-SVM)软测量模型。实验结果表明:该模型能较好地反映烟气含氧量的变化趋势。