共被期刊论文引用了2次
您的检索式：您选中1篇文献正在查看引证文献汇总
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Study on Residual Oil HDS Process with Mechanism Model and ANN Model显示文摘Based on the Residual Oil Hydrodesulfurization Treatment Unit (S-RHT), the n-order reaction kinetic model for residual oil HDS reactions and artificial neural network (ANN) model were developed to determine the sulfur content of hydrogenated residual oil. The established ANN model covered 4 input variables, 1 output variable and 1 hidden layer with 15 neurons. The comparison between the results of two models was listed. The results showed that the predicted mean relative errors of the two models with three different sample data were less than 5% and both the two models had good predictive precision and extrapolative feature for the HDS process. The mean relative error of 5 sets of testing data of the ANN model was 1.62%—3.23%, all of which were smaller than that of the common mechanism model (3.47%— 4.13%). It showed that the ANN model was better than the mechanism model both in terms of fitting results and fitting difficulty. The models could be easily applied in practice and could also provide a reference for the further research of residual oil HDS process. | Ma Chengguo Weng Huixin (Research Center of Petroleum Processing, ECUST, Shanghai 200237) | 2009 | China Petroleum Processing & Petrochemical Technology2009，11，1： | 0 |
| 2 | 沥青材料微观组成与宏观性质关联性研究显示文摘为了研究沥青微观组成与宏观性质的关联性,选取10种沥青对其微观组成和宏观性质进行分析,通过红外谱图分析不同沥青官能团结构的区别,利用灰色关联法对影响60℃动力黏度、针入度指数、残留针入度比的微观性质进行关联度排序,并建立BP神经网络模型进行性质预测。结果表明:红外谱图分析不能实现对不同种类沥青的精确分辨;芳香分质量分数对60℃动力黏度和针入度指数的影响程度最大,而胶体不稳定指数是影响残留针入度比的最重要因素;BP神经网络模型的预测值与真实值的拟合效果较好,最小相对误差可低至-0.61%,最大相对误差不高于10%。 | 刘成 范思远 张建峰 么强 | 2023 | 当代化工2023，52，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员