Design Boiler Combustion Optimization System Based On GA-BP Network Model And C#

Recently the environmental pollution especially haze problem becoming increasingly serious, coal-fired boilers are attracting more and more attention because pollution emissions from coal-fired boilers is one of the major sources of the environment pollution. The existing boiler combustion control technology of power plant has increasingly apparent shortcomings, and has become more and more difficult to meet the actual needs. So high-efficiency and low-emission combustion optimization technology is increasingly becoming the focus of the study.At present, there are two methods to improve combustion, which are traditional method and intelligent control method. Boiler combustion system is a complex large system with nonlinearity and strong coupling. The traditional method only takes single factors into account, not fully reflecting the true state of the system. However, the intelligent control is very suitable for modeling and optimization of nonlinear system with strong coupling, so it has more and more attention. This paper introduces the design of a boiler combustion optimization system based on it.By analyzing the factors of boiler combustion control, BP neural network algorithm is selected for modeling and analyzing the boiler combustion process in this thesis for boiler combustion characteristics difficultly represented by simple and clear mathematical models. As the BP algorithm has some shortcomings such as slow convergence rate and easily to fall into the local extremum, we choose the genetic algorithm to optimize the network and make full use of its global searching ability to optimize the weights and thresholds of the BP neural network, establish a reasonable GA-BP network model and realize the Matlab simulation. The result has proved that optimizing the neural network by genetic algorithm improves the training precision and convergence speed of the model, so that the model can reflect the operating performance of the boiler combustion.Secondly, the communication system is designed through the analysis of the process of boiler combustion optimization. Calling Matlab engine function library realizes the communication between C# and the GA-BP network mode. Optimization program of real time access to the force control database is realized by Dbcom interface. Force control system is connected with DCS interface by OPC, to realize the transformation from theoretical research to actual field application.Finally the program of boiler combustion optimization is designed by C# programming language. The GA-BP model is employed as the objective function of the optimization and the output of the model is employed as the goal of the optimization. The input value of the coal feeding, air blowing and induced draft fans are obtained through the genetic optimization when the output of the model is reached the optimal value to guide the control parameters during the boiler operation and let the boiler performance to achieve optimal.