Desulfurization Process Optimization Of CFB Boiler Fueled With Mixed Waste Coal

Electricity generation of circulating fluidized bed boiler burning inferior coal blend fuels is one of the most important ways of comprehensive utilization of coal gangue. As a kind of clean combustion technology, circulating fluidized bed boiler has the characteristics of low pollutant emissions. But desulfurization efficiency does not reach the boiler design values in the actual production; to study the desulfurization process is of great significance.An industrial experiment was conducted on a300MW circulating fluidized bed boiler burning mixed waste coal which consists of middlings and coal gangue according to the proportion of6:4. This experiment mainly researched the self-desulfurization property of mixed waste coal, the effects of the boiler’s desulfurization efficiency when using limestone as desulfurizing agent and the effect of desulfurization on the NOx emission of boiler. The experiment shows that:the mixed waste coal can reach average15%of desulfurization efficiency under a usual load, and the bed temperature is an important factor affecting self-desulfurization property; The Ca/S molar ratio, the bed temperature and ratio of the primary/secondary wind have an important influence on the desulfurization efficiency; The NOx emission of boiler is at a low level in general and increases the rise of Ca/S molar ratio.The experiment study on influence factors and feasibility of the desulfurization activated by water spraying in the tail flue of CFB boiler fueled with coal gangue. The experimental results show that the inlet SO2concentrations, the Ca/S molar ratio, the water spraying quantity, the exhaust gas temperature have important effect on the SO2removal efficiency.Based on the experimental data and with the aid of mathematical software MATLAB. four BP neural network models were established to predict desulfurization efficiency. By comparison, it shows that the BP neural network model based on vector variable momentum BP and21of single hidden layer neurons number can predict desulfurization efficiency with mean diversion extent of3.02%and maximum error of7.43%. the model can better predict particle circulating flow rate, It can provide certain guidance for actual industrial production.