基于GA-BP的转化反应甲烷含量软测量建模

Soft Sensing Modeling of Methane Content in Conversion Reaction Based on GA-BP

以炼油厂制氢装置为研究对象,通过对制氢转化炉的工艺过程以及控制过程的分析,结合智能控制理论,利用遗传算法GA优化神经网络,提出了基于遗传算法优化BP神经网络和基于遗传算法优化RBF神经网络的2种转化炉软测量模型。通过对比,确定了基于遗传算法优化BP神经网络的转化炉软测量模型,该模型能比较准确地预测转化炉中产生的转化气中甲烷的含量。

The refinery hydrogen plant as the object of study by of hydrogen manufacturing furnace operation and control process analysis,with the theory of intelligent control. Using genetic algorithm to optimize neural network. Based on genetic algorithm optimization BP neural network and genetic algorithm optimization RBF neural network of two kinds of soft sensor model of transformation. By contrast,determine the based on genetic algorithm optimized BP neural network conversion furnace in soft measurement model,the model can accurately predict conversion the content of methane convension gas generated in the furnace.