最小RBF网进化优选算法在燃煤着火特性预测中的应用

Application of the least RBF network evolution selected arithmetic in prediction of igniting characteristics

煤粉的着火特性是影响煤粉锅炉安全运行的主要因素之一,为保证锅炉的安全经济运行,往往需要准确的预测煤粉的着火特性。然而着火特性和煤质之间的内在关系是复杂的非线性关系,用某个单一煤质指标、人为经验或经验计算公式往往不能准确地描述。为了解决这一问题,利用最小RBF网进化优选算法,以大量的煤质分析数据和热天平试验数据为基础,建立了煤粉着火温度的预测模型。结果表明,利用最小RBF网进化优选算法可以达到很高的预测精度。

The coal＇s characteristic of ignition is one of the very important factors affecting the boilers＇ operation. It always needs to predict the characteristic of ignition exactly for boilers＇ safety operation. But it is complex nonlinear correlation between inner-relation of coal quality and igniting characteristic, which cannot be described exactly by certain single coal quality index, people＇s experience or the empiric formulas. For the sake of solving this problem, the least RBF network evolution selected arithmetic is adopted in this article. Based on mass data of coal analysis and thermo gravimetric analysis, a model for predicting coal＇s characteristic of ignition is established. The prediction result shows that high precision of prediction can be achieved by using the least RBF network evolution selected arithmetic.