Measurement Of The Carbon Content In Fly Ash Of Thermal Power Plants Based On Neural Network

The carbon content of fly ash thermal power is an important index that reflects combustion efficiency of coal-fired boiler. Control the range of the carbon content of fly ash when the unit keeps normal operation becomes an important topic of thermal power plants to save energy. As the premise of control carbon content of fly ash, measurement is one of the keys in measurement and control area. In this paper, the measurement of carbon content of fly ash is discussed. The importance of receiving real-time value quickly and accurately is indicated.Firstly, the reasons that affect the carbon content of fly ash is analyzed. According to the analysis of the specific impact of factors, operating parameters under different conditions of Baoding Thermal Power Plant200MW unit are collected. BP neural network is introduced, including its basic structure, network algorithm and network design, etc.Then, based on some prior knowledge this process is modeled using BP neural network on the Matlab platform and a reasonable BP neural network model of the carbon content of fly ash is established. All operating parameters collected are assigned and pretreated. The models are trained and tested and BP neural network models of fly ash carbon content under different conditions are obtained. This issue focuses on the analysis of the factors that affect the carbon content of fly ash and the establishing of the BP neural network model. BP neural network model of the carbon content of fly ash can get forecasting results in a short time and make sure the prediction error in an allowed range.