基于ACO-LSSVM燃煤碳元素分析的锅炉CO2排放量计算

针对生产实际中无法对燃煤组分进行在线检测分析的问题,建立了基于最小二乘支持向量机的燃煤的碳含量预测模型.以工业锅炉燃煤的相关工业分析数据作为模型的输入,并采用蚁群算法对最小二乘支持向量机相关参数进行寻优以提高模型的建模精度.应用该模型对福建地区工业锅炉燃煤的碳元素含量进行预测,预测结果的最大误差为1.18%,平均误差为0.64%.和传统多元逐步回归预测方法相比,该预测模型具有较高的预测精度,为工业锅炉二氧化碳排放量的科学计算奠定了基础.

Calculation of CO2 emissions in boilers based on ACO-LSSVM method for carbon element analysis of coal

The carbon content of coal is one of the important parameters in calculating emissions of carbon dioxide in boilers. Since the element analysis of coal is not used in actual production, an analytical model of the carbon content of coal was established. Ant colony algorithm optimization is used to optimize least-squares support vector machine parameter and the value of the industrial analysis of coal was used as the input of the model. Finally the optimized regularization parameter and the Gaussian kernel function of least squares support vector machine are 84.136 and 146.269 respectively. This method was used to predict the carbon content of coal that comes from Fujian region, the maximum error and average error of the prediction results are respectively 1.18% and 0.64%. Comparing proposed method with multivariate stepwise regression method, the results show that this method has higher simulation accuracy. The above carbon element analysis method was used to calculate boilers emissions of carbon dioxide. By discussing the access ways and means of variables, a carbon emissions calculation method was established.