Working regimes classification for predictive maintenance of mill fan systems

In the present paper, the subject of analysis is a device from Maritsa East 2 thermal power plant - a mill fan. The choice of the given power plant is not occasional. This is the largest thermal power plant on the Balkan Peninsula. Mill fans are main part of the fuel preparation in the coal fired power plants. The possibility to predict eventual damages or wear out without switching off the device is significant for providing faultless and reliable work of the equipment avoiding incidents. Standard statistical and probabilistic (Bayesian) approaches for diagnostics are inapplicable to estimate mill fan vibration state due to non-stationarity, non-ergodicity and the significant noise level of the monitored vibrations. Promising results are obtained only using computational intelligence methods (fuzzy logic, neural and neuro-fuzzy networks). In the present paper, two neuro-fuzzy approaches are applied for classification of a mill fan system working regimes based on analysis of data available from its control system.