论文部分内容阅读
在电厂燃煤机组中,一次风用于煤粉输送和锅炉燃烧,直接关系到炉膛内的实际燃烧工况,适当的一次风量对于磨煤机乃至整台机组的正常运行具有重要意义。然而受现场多种因素的影响,现有测量方法得到的一次风量误差很大。针对这一问题,基于最小二乘支持向量回归机算法建立了风量软测量模型,对辅助变量的选取及数据预处理方法进行了分析和讨论,并采用PSO算法对LSSVM软测量模型参数进行优化。以某电厂DCS历史数据中选取的数据作为训练样本和测试样本,对风量软测量模型进行了实验验证,结果表明该方法得到的预测值能够很好的跟踪实际风量的变化,且计算简便、预测速度快,具有较好的应用前景。
In power plant coal-fired units, the primary air is used for coal conveying and boiler combustion, and is directly related to the actual combustion conditions in the furnace. The proper primary air flow is of great significance for the normal operation of the coal mill and the entire unit. However, due to the influence of various factors on the site, the error of the primary air flow obtained by the existing measurement method is very large. In order to solve this problem, an air volume soft sensor model based on least-squares support vector regression is established. The selection of auxiliary variables and data preprocessing are analyzed and discussed. The parameters of LSSVM soft sensor model are optimized by PSO algorithm. The data selected from the historical data of a power plant is used as a training sample and a test sample to verify the air volume soft sensor model. The results show that the predicted value of the method can track the actual air volume well, and the calculation is simple and convenient. The prediction Fast, with good application prospects.