Soft sensor development based on improved just‐in‐time learning and relevant vector machine for batch processes

Abstract

AbstractThe 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.