Abstract
Abstract In this paper, we propose extensions for surrogate model fitting based on partial least square (PLS) regression. The method itself consists of a three step procedure, in which first, linear mass balances are established, then PLS regression is used to reduce the number of independent variables, and finally non-linear surrogate models are fitted to the latent variables defined via the PLS regression. As PLS regression looks for relationships between independent and dependent variables, preprocessing of the sampled data was investigated. Preprocessing improves the fit of the surrogate model by a factor of two in a case study given by the ammonia synthesis reactor section. The additional application of process knowledge allows a new grid definition with incorporated dependencies between independent variables resulting in a further improvement of the fit.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
