Set diagnosis on the power station´s devices by fuzzy neural network

Current situation for energy system which is consist from thermo power station faced on diagnosis of generator fault set without break down maintenance. In ageing thermo power plants, large turbo generator´s retrofits or main drive to upgrade was poor reliability associated with increase maintenance cost. Introduction of higher competition in the power market and subsequent introduction of new environmental constraints in our energy system, installed plants life time extension with overall performance improvement through upgrade or retrofit of main components is today a valuable. Also, set fault diagnosis during life time and predictive maintenance can be defined as collecting information from machines as they operate to aid in making decisions about their health, repair and possible improvements in order to reach maximum reliability, before any unplanned break down. As the turbo-generator fault set occurs when sensors should be put on bearing of these to detect vibration signal for extracting fault symptoms, but the relationships between faults and fault symptoms are too complex to get enough accuracy for industry application. In this paper, a new diagnosis method based on fuzzy neural network is proposed and a fuzzy neural network system is structured by associating the fuzzy set theory with neural network technology.