In response to the goal of Carbon peak Carbon neutral,China's circulating fluidized bed boilers participate in deep peaking oper-ation on a large scale,resulting in large fluctuation ranges of NOx emission concentration in boilers,poor control effect,and difficulty in meeting the demand for ultra-low emission of pollutants,so it is important to accurately model and predict the NOx emission concentra-tion in deep peaking.Based on the instantaneous carbon model,the NOx generation and reduction mechanism in the furnace was deeply an-alyzed,and the instantaneous carbon combustion model,O2 dynamic balance model,CO soft measurement model,NOx generation and re-duction model were established to complete the calculation of the mechanism of the NOx concentration at the entrance of the SNCR.The amount of coal feed,bed temperature,flue gas temperature and oxygen content,the first and second airflow,and the flow rate of the urea so-lution were selected as the input variables for the NOx emission concentration,and the NOx emission concentration was predicted by the SNCR inlet model.The SNCR inlet NOx concentration was used as an extended input variable,and the data set was reconstructed by correlation analysis and delay compensation between all input variables and NOx emission concentration.The reconstructed data set was trained and predicted by using long and short-term memory neural network,and whale optimization algorithm was used for the optimization of parameters of the long and short-term memory neural network to establish a NOx emission concentration model,the mechanism-data hy-brid prediction model,for deep peaking of circulating fluidized bed boilers.The simulation validation shows that the hybrid prediction mod-el has good prediction performance and generalization ability under different working conditions,and is able to realize real-time prediction of NOx emission concentration in circulating fluidized bed boilers at variable loads,and significantly improves all the error performance in-dexes compared with other prediction models,with an average absolute error δMAE up to 2.14 mg/m3,an average relative percentage errorδMApe up to 5.68％,and a coefficient of determination R2 up to 0.902 1.The hybrid prediction model can accurately predict the NOX emis-sion concentration under deep peaking in circulating fluidized bed boilers,which provides a reference for the design of the ultra-low emis-sion intelligent control system of circulating fluidized bed boilers.
circulating fluidized bed boilerdeep peaking regulationNO x emission concentrationdelayed compensationhybrid predic-tive model
万方数据
