基于支持向量机的大型电厂锅炉飞灰含碳量建模

飞灰含碳量是影响锅炉热效率的一个重要因素,影响燃煤锅炉飞灰含碳量的因素多而且复杂,对锅炉飞灰含碳量特性进行建模预测并结合优化算法实现燃烧优化是降低锅炉飞灰含碳量的有效方法.该文应用支持向量机算法建立了大型四角切圆燃烧锅炉飞灰含碳量特性的模型,并利用飞灰含碳量的热态实炉试验的数据对模型进行了校验,对支持向量机学习算法中参数的选择进行了探讨,获得了最佳学习参数.结果说明支持向量机与其它建模方法相比具有泛化能力好,计算速度快等优点,是锅炉飞灰含碳量特性建模的有效工具.

SUPPORT VECTOR MACHINE MODELING ON THE UNBURNED CARBON IN FLY ASH

Unburned carbon content in the fly ash is a main factor that has great impacts on the boiler efficiency. It was affected by many factors and complicated. Building a model to predict unburned carbon content in the fly ash is a good way to optimize the coal combustion and then reduce unburned carbon content. In this work, a support vector machine model predicting the unburned carbon content in the fly ash of a high capacity boiler was developed and verified. Good predicting performance was achieved with the proper learning parameters. The modeling results show that support vector machine is a good tool for building combustion models and has better generalization ability and higher calculation speed comparing with other modeling approaches.