摘要
锅炉氧量是大型燃煤机组送风系统控制的重要参数,其设定值是否合理对锅炉效率和NOx排放浓度有直接影响。为更科学合理地确定锅炉氧量设定值,提出了一种基于改进PSO和双隐层BP网络的锅炉氧量优化策略。借助某1000MW火电机组历史运行数据,建立以机组主要参数及氧量为输入、锅炉效率和NOx排放为输出的双隐层BP网络模型。为更快的搜索到最优氧量,提出一种引入变异机制的混沌简化粒子群算法。采用Gauss/mouse混沌映射增加初始种群的多样性,在位置更新过程中引入非线性递增惯性权重和高斯变异机制,提高算法跳出局部最优的能力。以双隐层BP网络模型为基础构建适应度函数寻优得到最优氧量设定值,实验结果表明改进算法具有更好的收敛速度和精度,可以高效准确地预测当前工况下的氧量最佳值,为锅炉优化运行提供指导。
Boiler oxygen is an important parameter of air supply system control for large coal-fired units,whether the set value is reasonable has a direct impact on boiler efficiency and NOx emission concentration.In order to determine the oxygen set value more scientifically and reasonably,an optimization strategy of boiler oxygen was proposed based on improved PSO and double-hidden-layer BP network.Based on the historical data of a 1000MW unit,a double-hidden-layer BP network model was established,which takes the main parameters of the unit and oxygen content as the input,and boiler efficiency and NOx emission as the output.Gauss/mouse chaotic map was used to increase the diversity of the initial population,the dynamically adjusted inertia weight and Gauss mutation mechanism were introduced in the process of position updating to improve the ability of the algorithm to jump out of the local optimization.Taking the net model as function,the optimal oxygen set value of the boiler was obtained.The results show that the proposed method has better stability,and can predict the optimal oxygen efficiently.
作者
马良玉
王永军
左晓桐
MA Liang-yu;WANG Yong-jun;ZUO Xiao-tong(School of Control and Computer Engineering,North China University of Electric Power,Baoding Hebei 071003,China)
出处
《计算机仿真》
北大核心
2020年第11期87-91,193,共6页
Computer Simulation
关键词
混沌映射
变异机制
双隐层
锅炉效率
氮氧化物排放
氧量设定值
Chaotic map
Mutation mechanism
Double-hidden-layer
Boiler efficiency
NOx emission
Set value of oxygen content
