Abstract:

In order to improve the prediction accuracy of the entrained-bed gasifier's outlet results under the conditions of coal type changes and process parameter fluctuations, a mechanism model, a generalized regression neural network (GRNN) model and a hybrid model are used to model the gasifier. The hybrid model constructed by GRNN model and mechanism model, combined with two different coal samples to analyze the prediction results of the three models. The results show that the three models can simulate the gasification process well. The prediction errors of the hybrid model regarding gasification temperature and the contents of CO, CO₂ and H₂ are 0.18% and 0.25%, 1.72% and 0.43% when the coal type is fixed. Compared with the mechanism model and the GRNN model, the error of hybrid model is smaller. When the coal type is changed, the prediction of the outlet gas result of the hybird model is the closest to the actual production data, and the error is 0.81% and 0.11%, 2.53% and 0.42% respectively. It is proved that the hybrid model can effectively simulate the gasification process under the conditions of coal type changes and process parameter fluctuations, which greatly improves the prediction accuracy of the mechanism model and the GRNN model.

Key words: entrained-bed gasifier, mechanism model, generalized regression neural network, hybrid model

摘要：

为了提高在煤质改变及工艺参数波动条件下气流床气化炉出口结果的预测精度，分别采用机理模型、广义回归神经网络（GRNN）模型以及混合模型对气化炉进行建模，其中混合模型由GRNN模型和机理模型构建，结合两种不同的煤样对三种模型的预测结果进行分析。结果表明：三种模型均可以较好地对气化过程进行模拟；其中在煤种固定的情况下混合模型关于气化温度和CO、CO₂及H₂含量的预测误差为0.18%和0.25%、1.72%及0.43%，与机理模型和GRNN模型相比误差更小；在煤种改变的情况下混合模型关于出口气体结果的预测最接近实际生产数据，误差为0.81%和0.11%、2.53%及0.42%。证明混合模型在煤种改变及工艺参数波动条件下可以有效地对气化过程进行模拟，在很大程度上提高了机理模型和GRNN模型的预测精度。

关键词: 气流床气化炉, 机理建模, 广义回归神经网络, 混合模型