Implementation of Artificial Neural Networks (ANN) modelling in Power Plant operation optimisation

Artificial Neural Networks (ANN) consist an alternative method of solving complex problems. They operate as a “black box” model learning from examples, which is capable of dealing with non-linear problems and predicting results at high speed. An advantage of using ANN is their ability to handle large and complex systems with many interrelated parameters. They seem to simply ignore excess data that are of minimal significance and instead they concentrate on the more important input data. The application reported in the present paper considers the implementation of ANN models for the prediction of particulate emissions and ash characteristic temperatures from a Power Plant by taking into consideration main operating parameters and fly ash composition, respectively. This can demonstrate the suitability of Artificial Neural Networks as a tool for Electrostatic Precipitator (ESP) and boiler operation optimisation.