Optimizing pulverized coal combustion performance based on ANN and GA

In this work, an effective method based on artificial neural network (ANN) and genetic algorithms (GA) is suggested for modeling the carbon burnout behavior in a tangentially fired utility boiler and optimizing the operating conditions to achieve the highest boiler heat efficiency consecutively. When carbon burnout behavior under various operating conditions are experimentally investigated, the comparison between the output of ANN modeling and the experimental data shows satisfactory agreement. A genetic algorithm is employed to perform a search to determine the optimum solution of the neural network model, identifying appropriate setpoints for the current operating conditions.