【摘要】 采用神经网络方法 ,构造了一个催化裂解产品产率的BP神经网络 ,并利用Levenberg Marquardt算法来提高收敛速度及克服局部极值。模型预测结果液化石油气、汽油、柴油、丙烯和焦炭加损失产率的误差分别为 1.8% ,2 .4% ,5 .7% ,5 .8% ,6.3 % ,能够满足工业应用需求。更多还原

【Abstract】 Based on artificial neural networks,a model predicting yields of DCC products was established.The model used Levenberg Marquardt algorithm to promote convergence and handle part extremism.The results showed that average errors of LPG,gasoline,diesel,propylene,coke plus loss are 1.8%,2.4%,5.7%,5.8%,6.3% respectively,meeting the commercial requirements.更多还原