论文部分内容阅读
煤粉细度是煤粉磨制过程控制的一个关键工艺指标,保证煤粉细度在一定范围内对于优化锅炉或回转窑的燃烧效率有着重要意义。由于煤粉细度无法在线测量,而离线化验既不能保证实时性,又容易造成煤粉泄漏污染环境,因此难以实现对煤粉细度的有效控制。该文通过对制粉过程中影响煤粉细度的因素进行分析,采用基于最小二乘-支持向量机的方法建立煤粉细度的软测量模型。通过模型误差最小的原则,确定了模型相关参数,解决了样本数量较少,常规软测量方法难以实现的问题。通过现场采集的样本数据进行的实验研究表明了该模型的有效性。
Pulverized coal fineness is a key process index of pulverized coal grinding process control, to ensure the fineness of pulverized coal within a certain range for optimizing the combustion efficiency of the boiler or rotary kiln is of great significance. Because coal fineness can not be measured online, offline testing can not guarantee real-time, but also easily lead to coal pollution pollute the environment, it is difficult to achieve effective control of fineness of coal. In this paper, through the analysis of the factors influencing the fineness of pulverized coal in the milling process, a soft measurement model based on the least squares support vector machine is established. Through the principle of minimizing the model error, the related parameters of the model were determined, which solved the problem of small sample size and difficult realization of the conventional soft-sensing method. The experimental study on the sample data collected in the field shows the validity of the model.