基于变尺度混沌蚁群算法的飞灰中的碳质量分数优化

为了降低燃煤锅炉飞灰中的碳质量分数,利用支持向回归(SVR)建立了大型四角切圆燃烧锅炉的碳质量分数模型.利用大样本量的热态实炉碳质量分数实验数据对模型进行了训练和验证,利用变尺度混沌蚁群算法结合该模型对锅炉的运行参数进行优化.计算结果表明:SVR模型具有很好的泛化性和预测精度;变尺度蚁群算法能实现全局寻优,降低飞灰中的碳质量分数,而且具有很高的稳定性和鲁棒性,其快速的收敛寻优能力也非常适于在线应用;支持向量机与变尺度蚁群算法的结合使用可以有效地实现燃烧优化,降低飞灰中的碳质量分数是控制锅炉飞灰中碳质量分数的有效工具.

Application of scaleable chaotic ant colony algorithm in control of unburned carbon in fly ash

 In order to control the unburned carbon in fly ash of the coal fired boiler, support vector regression (SVR) was employed to establish a mathematic model to predict the characteristics of unburned carbon in fly ash in large capacity corner fired boilers. A large number of field test data from a full scale operating boiler was used to train and validate the SVR model. A scaleable chaotic ant colony optimization (SCACO) was combined with carbon content of fly ash model to optimize the operating parameters of the boiler. The computational results show that the generalization and accuracy of SVR are very good. SCACO reduces carbon content of fly ash with high stability and robustness. Its fast convergence suits for online applications. The hybrid algorithm combining SVR and SCACO provides a effective way to control the unburned carbon in fly ash.