基于SVM的燃煤电站锅炉飞灰含碳量预测

将支持向量机方法引入燃煤电站锅炉飞灰含碳量预测领域．该预测方法很好地建立了燃煤电站锅炉飞灰含碳量特性与运行参数之间的复杂关系模型,并考虑到运行参数之间的耦合性,具有预测能力强、全局最优及泛化性好等优点．将该方法应用于某300 MW燃煤电站锅炉中,经过训练后的SVM模型对检验样本飞灰含碳量进行预测,均方根误差和平均相对误差分别为1．39%和1．30%,相当于BP网络模型的22．20%和21．07%．应用结果表明,支持向量机方法优于多层BP神经网络法,能很好地满足预测要求．

Forecasting Unburned Carbon Content in the Fly Ash from Coal-Fired Utility Boilers Based on SVM

A new algorithm for forecasting the unburned carbon content in the fly ash from coal-fired utility boilers based on the support vector machine (SVM) method is presented.This forecasting method establishes a model to reflect the compli- cated relations between the unburned carbon content characteristics in the fly ash and the operating parameters,with the coupling performance of every parameter considered,It has the advantages of high forecasting accuracy,global optima prop- erty,and more generalized performance.Applied to a 300 MW coal-burning utility boiler,the SVM model which had been trained forecasted the unburned carbon in the fly ash in the test samples set,and got the mean square root error and the mean relative error of 1.39%,and 1.30%,respectively,which are 22.20% and 21.07% of BP network model.These re- sults show that SVM method is more accurate than the BP neural network,and can satisfy the forecasting demand well.