Application Of Quantum Adaptive BSA Algorithm In Boiler Parameter Tuning And Optimization

As an indispensable part of the modern energy supply chain,boilers have attracted many scholars to do research.In recent years,both in the boiler efficiency or in the boiler combustion of nitrogen oxides caused by the impact of the environment.Facing the everdecreasing coal resources,circulating fluidized bed boilers have a more significant advantage in saving raw materials than conventional boilers.In contrast,its structure and work process are more complex,so it is difficult to use the traditional modeling methods to establish its mathematical model.However,the study of artificial intelligence algorithms has facilitated the modeling of circulating fluidized bed.In this paper,in order to optimize the boiler parameters,the improved algorithm of the birds and fast learning network are used to model a 300 MW circulating fluidized bed boiler in a thermal power plant.More detailes is as follows:Firstly,the quantum behavior combined with the bird swarm algorithm and the adaptive coefficient are used for improve the bird swarm algorithm.Compared with the basic bird swarm algorithm,the difference algorithm and the particle swarm algorithm,the results show that the improved bird swarm algorithm has better optimization accuracy and faster convergence rate.Secondly,the improved bird swarm algorithm is used to set the boiler parameters.In order to solve the boiler parameter tuning problem,a comprehensive model of NOx emission and thermal efficiency of boiler combustion is established by using the fast learning network with the field operation data of the boiler as the input quantity and setting the weight and threshold of the fast learning network.The experimental results show that the improved bird swarm algorithm has better generalization ability and data searching ability.Finally,the improved bird swarm algorithm is used to optimize the boiler,and the optimization is divided into two parts: in the single target optimization with nitrogen oxide emission and thermal efficiency as output respectively,and multi-objective optimization with both as output.The experimental results show that after optimization the concentration of nitrogen oxides emission is reduced and the thermal efficiency of the boiler is improved.It is shown that the improved bird swarm algorithm has high precision and generalization ability in the boiler parameter setting and optimization,which reflects its practical value.