Combining prior knowledge with data driven modeling of a batch distillation column including start-up

Abstract

Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Hybrid semi-parametric modeling in process systems engineering: Past, present and future

“…neural networks. The biggest advantage of Fuzzy models, when compared to more data-driven techniques, is that they are interpretable, wherefore they can offer transparency in situations where physical models are difficult to derive (van Lith et al, 2002(van Lith et al, , 2003. However, for their derivation considerable more knowledge is required than for other data-driven models.…”

“…The integration of Fuzzy models along with first-principles knowledge can, as before, be accomplished in parallel (Abonyi et al, 1999;Fu & Barford, 1995b) or in series (van Lith et al, 2002(van Lith et al, , 2003Vieira, Dias, & Mota, 2005). Moreover they can be complementarily combined into an existing hybrid approach, e.g.…”

“…While the determination of the Fuzzy model parameters in the parallel hybrid case can be accomplished with standard techniques, not all of those techniques can be directly used in the serial approach, see (Preusting et al, 1996;Roubos, 2002;Roubos et al, 2000;Schubert et al, 1994a;Schubert, Simutis, Dors, Havlik, & Luebbert, 1994b;van Lith et al, 2003) for examples.…”

Root cause analysis of process fault conditions on an industrial concentrator circuit by use of causality maps and extreme learning machines

“…However, several studies have reported the potential and benefits derived from the use of hybrid systems for fault detection and diagnosis, combining fundamental process knowledge with data-base models (Van Lith et al, 2003;Venkatasubramanian et al, 2003c;Nandi et al, 2004;Van Sprang et al, 2005;Thornhill and Horch, 2007;Yang and Xiao, 2012), especially when considering large-scale industrial situations. From a model-based perspective, it has been shown that the use of hierarchical system decomposition, as a qualitative model-based reasoning tool, can provide effective modularity for structuring large-scale diagnostic knowledge bases (Prasad et al, 1998).…”

On the use of kernel-based methods in sound synthesis by physical modeling

“…Examples are found in the literature that span from the simple cases of partially linear models [7] and semi-physical modeling [10], in which physical insights are used to design suitable nonlinear transformations of part of the inputs, to more problem-specific cases in which prior knowledge about the physics of the process under observation is embedded in the model [5,17].…”