Boiler combustion optimization air distribution method based on online model prediction

Abstract

Provided is a boiler combustion optimization air distribution method based on online model prediction. The method includes: constructing a boiler combustion optimization air distribution model by employing an improved BP neural network algorithm and model online update calculation; and performing optimization calculation on parameters such as the optimal oxygen amount, the primary air amount, each secondary air door and a burnout air door etc. with the combination of an adaptive genetic algorithm and dynamic optimization boundary so that a multi-target function constructed by the boiler efficiency and the pollutant discharge capacity reaches the optimal combustion range.

Description

technical field [0001] The invention relates to the field of coal-fired boiler combustion optimization, in particular to a boiler combustion optimization air distribution method based on online model prediction. Background technique [0002] At present, most of the air supply control in power plants adopts cascaded oxygen control and adjusts the air distribution method through manual experience. Without adjustment and misoperation, it will be difficult to meet the requirements of economical combustion and low emission in the long run. In serious cases, it will even cause safety accidents such as local high temperature, coking in the furnace, and bursting of water-cooled wall tubes. The deviation between the type of coal used and the type of coal designed is large, the boiler control process is more disturbing, and the boiler efficiency is reduced. Wind combustion appears to be particularly important. [0003] Boiler air supply and air distribution optimization methods need...

AI Technical Summary

Problems solved by technology

Algorithms for constructing models based on neural network technology and support vector machines have verified the accuracy of the model, while ignoring the timeliness of the model. Since the combustion process is not only nonlinear and strongly coupled, it also has time-varying characteristics, so , the effect of the model is obvious at the initial stage of construction, but as time goes by, the accuracy of the model is difficult to guarantee, so that it cannot meet the long-term optimization of air distribution adjustment

[0004] The boiler combustion optimization air distribution system is a multi-objective optimization problem, and the genetic algorithm can be used to optimize the process parameters so that the boiler efficiency and NO X The fitness function composed of emissions is optimal, but since the crossover probability and mutation probability parameters are always fixed during the operation process, they cannot be automatically adjusted as needed with the increase of the genetic algebra, which affects the convergence of the algorithm and is difficult to meet multiple working conditions Real-time accuracy under change, even safety

Images