A new dynamic neuro-fuzzy system applied to fault diagnosis of an evaporation station

This chapter investigates the development and application of a new type of neuro-fuzzy system, namely the neuro-fuzzy system with interconnected fuzzy rules to robust fault diagnosis of an industrial plant. Hybrid learning based on the fuzzy c-means clustering and steepest-descent method algorithms...

Full description

Saved in:
Bibliographic Details
Published inFault Detection, Supervision and Safety of Technical Processes 2006 pp. 222 - 227
Main Authors Mirea, Letitia, Patton, Ron J.
Format Book Chapter
LanguageEnglish
Published Elsevier Science Ltd 2007
Online AccessGet full text
ISBN0080444857
9780080444857
DOI10.1016/B978-008044485-7/50038-5

Cover

More Information
Summary:This chapter investigates the development and application of a new type of neuro-fuzzy system, namely the neuro-fuzzy system with interconnected fuzzy rules to robust fault diagnosis of an industrial plant. Hybrid learning based on the fuzzy c-means clustering and steepest-descent method algorithms is used to train the neuro-fuzzy system. The experimental case study refers to the sensor and actuator fault diagnosis of an evaporation station from a sugar factory. An extended neuro-fuzzy generalized observer scheme is used to generate the residuals (symptoms) in the form of the one-step-ahead prediction errors. These are then analyzed by a neural classifier to take the appropriate decision regarding the actual behavior of the process.
ISBN:0080444857
9780080444857
DOI:10.1016/B978-008044485-7/50038-5