Research On Modeling In Boiler Combustion Of Multiple Conditions Based On Neural Network

In recent years, with the increasing shortage of energy and pollution of fog and haze, the state made more stringent requirements on power plants. Wants to survive, power plants must pay attention to energy saving and emission reduction. And the boiler combustion directly affects energy consumption and pollutant emissions.To improve the boiler efficiency and reduce NOx emissions is the main goals of the power plant flue gas boiler combustion optimization. Combustion characteristics model is the core of combustion optimization. Through the analysis of the development, characteristics, structure of BP neural network and the theory of the neural network model, structure and the rules of learning, artificial neural network model can fit any nonlinear function and has good generalization ability and has the self-learning of the complex issues. The core content of this paper is that model combined with genetic algorithm to find the optimal target values, and the optimal target value for each operating parameter values.Firstly, this paper gives a research to the effect factors of boiler combustion, and then points out the emphasis-to build a neural network model for boiler combustion data of600MW units in Datong second power plant and use genetic algorithm to optimize models. Eventually, this paper gives combustion adjustment parameter values that can achieve higher efficiency and lower emission in different conditions.From the units’thermodynamic experiments point of view, the way in this paper managed to optimize combustion, played a role in NOx reduction, and can improve boiler efficiency to some extent to achieve the purpose of energy saving and emission reduction.