To online estimate the concentrations of key components at the outlet of bisphenol‐A (BPA) synthesis reactor, a hybrid modeling approach is proposed in this paper. First, the simplified mechanism model for the synthesis of BPA in an industrial fixed‐bed reactor is deduced on the basis of mass and energy balance. Second, considering that the initial concentrations of reactants at the inlet of BPA synthesis reactor cannot be measured in real‐time, the modified stochastic gradient boosting‐Gaussian process regression approach previously proposed by the authors is employed to online estimate the initial concentrations of reactants. Furthermore, modified stochastic gradient boosting‐Gaussian process regression method is also adopted to model the nonlinear influence of the reaction factors ( i.e., initial concentrations of reactants and inlet temperature) on the reaction rate constants in the simplified mechanism model. Finally, the hybrid modeling approach for BPA synthesis process is achieved by integrating the simplified mechanism model with the estimation models of initial concentrations and reaction rate constants. The feasibility and validity of the proposed hybrid model is verified through an industrial BPA synthesis process. On the basis of the hybrid model, the sensitivity analyses of the initial concentrations and inlet temperature are conducted, which can provide theoretical guidance for the operation optimization study in future work.
For accurate state prediction of chemical process characterized by connatural features of non-linearity and time variation, a novel online selective ensemble partial least squares learning paradigm, referred to as OSE-PLS, is proposed in this paper. First, the process states are differentiated to diverse local regions by just-in-time learning-based localization method to handle process non-linearity.Then, support vector domain description algorithm is applied to identify and remove redundant ones. Consequently, a variety of local PLS models are established for representing diverse process states. Inspired by the local outlier probability algorithm in outlier detection field, the combination weights of each PLS model are adaptively distinguished by definitely quantifying the probability that query data belong to an outlier in each local region. Finally, the prediction for query data is achieved through selective ensemble learning strategy. To effectively address the inherent time-varying characteristics of process, the OSE-PLS technique is equipped with adaptation mechanism of local model updating and online local model extraction, which enables OSE-PLS to acquire the capability of addressing both gradual and abrupt changes in process simultaneously. An industrial bisphenol-A distillation process is employed to demonstrate the superiorities of novel online selective ensemble partial least squares (OSE-PLS) approach. KEYWORDS adaptive soft sensor, just-in-time learning, local outlier probability, selective ensemble learning, support vector domain description Asia-Pac J Chem Eng. 2019;14:e2346.wileyonlinelibrary.com/journal/apj
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.