State monitoring of induced draft fan in thermal power plant by gravitational searching algorithm optimized BP neural network

The state monitoring issue of the induced draft fan in a thermal power plant by employing the gravitational searching algorithm optimized BP neural network is investigated in this paper. A new method to estimate the air quantity of the induced draft air of a thermal power plant is proposed based on the historical operation data extracted from the supervisory information system (SIS). In order to predict the air quantity of the induced draft fan, all the variables infecting the air quantity are selected as the inputs of the BP neural network, which is optimized by the gravitational searching algorithm. After training the neural network, a prediction model of the air quantity is established and the maximum prediction error is less than 3%. Meanwhile, the method can also be used in the state monitoring by comparing the actual and predicted air quantity. Finally, extensive simulation results are presented to validate the effectiveness of the proposed approach.