Intelligent sensor fault detection and identification for temperature control


Postalcioglu S., Erkan K., BOLAT E.

11th WSEAS International Conference on Computers, Creteil, France, 26 - 28 July 2007, pp.131-132 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • City: Creteil
  • Country: France
  • Page Numbers: pp.131-132
  • Keywords: sensor fault, fault detection and identification, temperature control

Abstract

This paper addresses artificial intelligence and signal processing based online fault detection and identification. Fuzzy logic controller has been utilized for temperature control. Faults often cause undesired reactions, so to keep the system stable and to obtain an acceptable control performance is an important problem for control system design. In this paper, a multiplicative, an additive and a disturbance type of Termocouple sensor faults have been examined for temperature control. Feature vector of the sensor faults has been constructed using a statistical analysis. For classifier of the feature vector the Self Organizing Map (SOM) has been used. So sensor fault can be detected and identified using feature vector.