基于最小二乘-支持向量机的制粉过程煤粉细度软测量模型

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 particle size soft sensor based on the least squares support vector machines algorithm

The particle size of pulverized coal is an important industry parameter in the process of pulverized coal.The particle size in the set scope is helpful to optimize of boiler or gyration kiln combustion efficiency.However the coal particle size can not be effectively controlled due to the lack of on-line instrumentation to measure particle size in real time.The influence factors on the particle size were analyzed in detail to develop a least squares support vector machine soft model to address the difficulties of size measurements with insufficient process data.The soft model was proved validity by experiment of using actual process data.