Neuro-fuzzy model of the detergent leavings kinetics' removal in a clean in place system
Abstract
This paper has focused on the Neuro-Fuzzy model of the detergent leavings kinetics' removal of a CIP System, which has been evaluated based on the pH measured. The plant dynamics has been identified for different operational conditions. Flow rates above 10, 5 L.min-1 has no contribution for the rinsing process time decreasing; it allows to state that is possible to optimize the process reducing energy, water and steam consumption as well as the time of unused machinery, with consequent productivity gains. The obtained models, based on Neuro-Fuzzy systems, allowed the prediction of the system dynamics behavior. The results of the obtained models were validated when compared with the experimental data. Three triangular membership functions for the input data modeled accordingly the pH dynamics with an error of 0.011 when comparing the validation data and the obtained model.
URI
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84903485911&partnerID=40&md5=8382ef7cd95e4e16b959e9daa9046aabhttps://repositorio.maua.br/handle/MAUA/960
Collections
Related items
Showing items related by title, author, creator and subject.
-
Use of Educational Tool for Modeling Temperature Control Systems as a Remote Teaching and Learning Strategy in Engineering (Artigo de Periódico)
Assis W.O.; Coelho A.D. (International Association of Engineers, 2023)This paper presents the use of a teaching tool that allows the model identification of a temperature control system by applying several methods such as Step Response Method, Least Squares Method, Moving Average Least Square ... -
LPV system identification using the matchable observable linear identification approach (Artigo de Periódico)
P. Lopes dos Santos; Rodrigo Alvite Romano; T-P Azevedo-Perdicoúlis; Daniel E. Rivera; J. A. Ramos (2017) -
Modular modelling methodology applied to the dynamic analysis of parallel mechanisms (Artigo de Periódico)
Tarcisio Antonio Hess Coelho; Renato Maia Matarazzo Orsino; Fernando Malvezzi (Elsevier BV, 2021)