For the effective monitoring of batch processes with uneven multiphases, phase partitioning and discriminant analysis are two critical problems. To fully solve these two problems, a systematic strategy including fuzzy phase partitioning and hybrid discriminant analysis is proposed. First, using a new unsupervised, multiscale, sequential partition (UMSP), each batch is divided into phases with transitions using different clustering scales. On this basis, two multiplesupport-vector-data-description (SVDD) models are built for online phase partitioning and monitoring, and a hybriddiscriminant-analysis method is then developed for online fault detection. The effectiveness and advantages of the proposed method are illustrated with a 2D, handwritten example and a fed-batch penicillin-fermentation process.
Soft sensors using just-in-time learning
(JITL) have attracted
much attention in the application of online prediction in batch processes
because of the ability to perform adaptive updating and dynamic modeling.
However, developing effective JITL-based soft sensors of batch processes
remains challenging due to the unlabeled data caused by the expensive
online measuring instruments and long time-consuming offline analysis.
Besides, the multiphase and nonlinear characteristics of batch processes
make this challenge more complicated. To cope with this challenge,
a novel soft sensor framework, termed semisupervised just-in-time
relevance vector regression (SJRVR), is proposed. The SJRVR integrates
JITL, adversarial autoencoder (AAE), and RVR into a unified framework
to address soft sensor modeling for multiphase batch processes with
unlabeled data. In this framework, an unlabeled data processing strategy
based on process mechanism and AAE (MAAE) is presented to utilize
the useful information on unlabeled data. Moreover, a local regression
model is constructed using JITL with a designed modeling data selection
strategy and RVR to address the soft sensor modeling for process data
with multiphase and nonlinear characteristics. The effectiveness of
the SJRVR method is illustrated with a penicillin fermentation process.
The online measurement of key quality variables based on soft sensors plays a critical role in ensuring the safety and stability of batch processes. Recently, the relevant vector machine (RVM) was introduced into soft sensors for batch processes. However, the RVM-based soft sensor has limitations in addressing the time-varying, high-dimensional, and dynamic data of batch processes. To address these issues, based on improved just-in-time learning and the relevant vector machine, an adaptive soft sensor, termed IJITL-RVM, is proposed in this paper. The IJITL-RVM integrates the IJITL algorithm and the RVM algorithm into a unified online modelling framework with the ability to perform adaptive updating and dynamic modelling. First, to enhance the performance of online prediction, an IJITL is designed to select modelling data based on the support vector data description (SVDD) algorithm and the kernel trick. Based on the comprehensive consideration of the strong nonlinearity and high dimensionality of process data, the IJITL can adaptively and accurately select the modelling data. Afterward, a local model is established by using the RVM for online prediction. Three applications, including a numerical simulation example, some UCI datasets, and a penicillin fermentation process, are provided to illustrate the superiority of the IJITL-RVM-based soft sensor.
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.