Adaptive soft sensor modeling framework based on just-in-time learning and kernel partial least squares regression for nonlinear multiphase batch processes

• Published in: Computers & chemical engineering 2014-12, Vol.71, p.77-93
• Main Authors: Jin, Huaiping, Chen, Xiangguang, Yang, Jianwen, Wu, Lei
• Format: Article
• Language: English
• Subjects: Adaptive soft sensor; Algorithms; Applied sciences; Batch process; Biological and medical sciences; Biotechnology; Chlortetracycline fermentation process; Computer science; control theory; systems; Data processing. List processing. Character string processing; Enzyme engineering; Exact sciences and technology; Fermentation; Fundamental and applied biological sciences. Psychology; General equipment and techniques; Instruments, apparatus, components and techniques common to several branches of physics and astronomy; Just-in-time learning; Kernel partial least squares; Least squares method; Mathematical models; Memory organisation. Data processing; Methods. Procedures. Technologies; Microbial engineering. Fermentation and microbial culture technology; Multiphase; Nonlinearity; Partial mutual information; Phases; Physics; Production of selected enzymes; Sensors (chemical, optical, electrical, movement, gas, etc.); remote sensing; Similarity; Software; Strategy
• ISSN: 0098-1354; 1873-4375
• DOI: 10.1016/j.compchemeng.2014.07.014

•An adaptive soft sensing framework is proposed for multiphase batch processes.•New hybrid similarity measure and adaptive sample selection for JIT learning.•Phase identification using Gaussian mixture model and Bayesian inference.•Partial mutual information criterion for input variable selection.•Application to industrial CTC fermentation process with satisfactory results. Batch processes are characterized by inherent nonlinearity, multiple phases and time-varying behavior that pose great challenges for accurate state estimation. A multiphase just-in-time (MJIT) learning based kernel partial least squares (KPLS) method is proposed for multiphase batch processes. Gaussian mixture model is estimated to identify different operating phases where various JIT-KPLS frameworks are built. By applying Bayesian inference strategy, the query data is classified into a particular phase with the maximal posterior probability, and thus the corresponding JIT-KPLS framework is chosen for online prediction. To further improve the predictive accuracy of the MJIT-KPLS algorithm, a hybrid similarity measure and an adaptive selection strategy are proposed for selecting local modeling samples. Moreover, maximal similarity replacement rule is proposed to update database. A procedure of input variable selection based on partial mutual information is also presented. The effectiveness of the MJIT-KPLS algorithm is demonstrated through application to industrial fed-batch chlortetracycline fermentation process.