The industrial monitoring in complex processes with hundreds of variables is faced in this work. The Visbreaker process of the Sines Refinery is the case studied. Firstly dimension reduction is performed by multidimensional scaling, obtaining the process evolution in a three dimensional space. Then an evolving fuzzy system (eFS) is developed to detect eventual malfunction of sensors. This eFS takes the three reduced dimensions as antecedents and classifies the process state into normal and abnormal states. A comparison is made of several strategies for rule creation and evolution, for Takagi-Sugeno and for Mamdani systems. A software platform- the eFSLab (Evolving Fuzzy Systems Laboratory) - , with which this work has been developed, is presented and discussed. The obtained eFS show a good performance, classifying well the state of the process into abnormal-normal condition in about 95% of the cases, with a number of rules between 5 and 8.
Subject
Neuro-Fuzzy Modelling
Related Project
CLASSE - Classificação Sintética para Supervisão Industrial (Synthetic Classification for Industrial Supervision)
Conference
IFSA2009/EUSFLAT09, the 2009 International Fuzzy Systems Association World Congress and 2009 International Conference of the European Society for Fuzzy Logic and Technology, June 2009
Cited by
Year 2015 : 1 citations
Implementation of evolving fuzzy models of a nonlinear process
RE Precup, EI Voisan, EM Petriu… - Informatics in Control …, 2015 - ieeexplore.ieee.org
Abstract: This paper presents details on the implementation of evolving Takagi-Sugeno-
Kang (TSK) fuzzy models of a nonlinear process represented by the pendulum dynamics in
the framework of the representative pendulum-crane systems. The pendulum angle is the ...
Year 2014 : 1 citations
Online identification of evolving Takagi–Sugeno–Kang fuzzy models for crane systems
RE Precup, HI Filip, MB R?dac, EM Petriu, S Preitl… - Applied Soft …, 2014 - Elsevier
Abstract This paper suggests new evolving Takagi–Sugeno–Kang (TSK) fuzzy models
dedicated to crane systems. A set of evolving TSK fuzzy models with different numbers of
inputs are derived by the novel relatively simple and transparent implementation of an ...
Year 2009 : 1 citations
1. Radu-Emil Precup1, Radu-Codruţ David1, Stefan Preitl1, Emil M. Petriu2 2009 [PDF] de ni.ac.rsUPSO ALGORITHMS - facta.junis.ni.ac.rs
1"Politehnica" University of Timisoara, Department of Automation and Applied Informatics,
