Intelligent sensor fault detection and identification for temperature control

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.