基于PSO-LSSVM的循环流化床锅炉多目标燃烧优化

Multi-objective Combustion Optimization of Circulating Fluidized Bed Boiler Based on PSO-LSSVM

为了平衡循环流化床(circulating fluidized bed,CFB)锅炉经济性和环保性的关系,实现高效低污染的燃烧,基于粒子群优化(particle swarm optimization,PSO)算法,提出兼顾提高锅炉热效率与降低NO_(x)排放量的多目标燃烧优化方案。首先分析优化目标的影响因素,筛选出相关辅助变量,采用主成分分析法对变量特征集进行降维;然后利用PSO算法优化最小二乘支持向量机(least squares support vector machine,LSSVM)参数,基于训练样本建立CFB锅炉的综合模型,并通过测试样本验证所建立模型的拟合精确度;在明确优化目标函数后,采用PSO算法对模型的可调参数进行寻优,分析锅炉在高、中、低负荷3种工况下的最佳运行参数,以达到多目标燃烧优化的目的。所提优化方案可在保证安全运行的前提下,挖掘CFB锅炉自身的经济和环保潜力。

In order to balance the relationship between the economy and environmental protection of the circulating fluidized bed(CFB)boiler and achieve high-efficiency and low-polluting combustion,this paper proposes a multi-objective combustion optimization scheme based on particle swarm optimization(PSO)algorithm,which takes into account the improvement of boiler thermal efficiency and the reduction of NO_(x) emissions.It firstly analyzes the influencing factors of the optimization objective and screens out relevant auxiliary variables,and then uses the principal component analysis to reduce the dimension of the variable feature set.Afterwards,it adopts the PSO algorithm to optimize the parameters of the least squares support vector machine(LSSVM).It alsobuildsan integrated model of the CFB boiler with training samples,and verifies the accuracy of fitting degree of the model according to the test samples.After clarifying the optimization objective function,the paper uses the PSO algorithm to optimize the adjustable parameters of the model,and analyzes the optimal operating parameters of the boiler under different working conditions of high,medium and low loads to achieve the purpose of multi-objective combustion optimization.It is proved that under the premise of ensuring safe operation,the potential of CFB boiler s own economic and environmental characteristics could be tapped.