钴基催化剂F-T合成的人工神经网络模拟

反应温度、压力、空速和原料气H_2/CO比等工艺操作条件对F-T合成生成重质烃的选择性影响很大。以上述操作参数为输入变量,CO的转化率、甲烷在产物烃中的质量分数C_1和重质烃的质量分数C_5~ 为输出变量,采用LM算法建立了钴基催化剂F-T合成的BP神经网络模型,定量预测工艺操作条件对F-T合成的影响规律。预测结果表明,低温有利于重质烃生成,高温下CO的转化率高,但C_1也高,C_5~ 重质烃的选择性较低。压力升高,C_1下降,CO的转化率和C_5~ 增加。C_1随空速的提高而增加,CO的转化率和C_5~ 随空速的升高而下降。低合成气H_2/CO比CO转化率和C_1较低,C_5~ 重质烃高。进一步的实验验证表明,模型具有较高的预测精度,CO转化率和C_5~ 的相对误差小于8%,C_1小于9%。

Artificial neural network simulation of cobalt-based catalyst F-T synthesis

The reaction temperature,pressure,space velocity and H_2/CO molar ratio in feed markedly influence the heavier hydrocar- bon selectivity of Fischer-Tropsch synthesis.Therefore,using operation conditions as input variables,the CO conversion,the selectivi- ty of C_1 and C_5~ as output variables,a BP neural network is constructed by Levenberg-Marquardt algorithm,and wish that quantifica- tionally predict the regulation of operation condition effect for Fischer-Tropsch synthesis.The predict results indicated that lower reac- tion temperature facilitated the synthesis of heavier hydrocarbon,the CO conversion was high and the weight fraction of heavy hydrocar- bon C_5~ low under higher temperature;Increasing pressure,the methane selectivity decreased,the CO conversion and C_5~ increased; With space velocity increasing,the methane selectivity increased,and the CO conversion and C_5~ dropped down;Lower H_2/CO molar ratio in feed caused low CO conversion and methane selectivity,and high C_5~ .Further experimental verification suggested that the con- structed model have higher prediction precision,the relative deviation less than 8% for the CO conversion and C_5~ ,less than 9% for methane.