| 用BP神经网络预测延迟焦化产品收率 |
| |
| 引用本文： | 朱英娣,赵德智,祝云燕,酒巧娜. 用BP神经网络预测延迟焦化产品收率[J]. 炼油技术与工程, 2011, 41(1): 50-52 |
| |
| 作者姓名： | 朱英娣 赵德智 祝云燕 酒巧娜 |
| |
| 作者单位： | 辽宁石油化工大学石油化工学院,辽宁省抚顺市,113001 |
| |
| 摘 要： | 针对传统的焦化产品收率预测方法准确性较差的实际情况,用Matlab编程构造了3层前馈BP神经网络,采用带动量的批处理梯度下降法来训练网络,并用所得模型对已知样本数据进行预测.结果表明,运用BP神经网络对焦化产品收率能够进行准确预测,最大相对误差为3.33%.与传统的预测模型相比,该网络模型的预测精准度更高.
|
| 关 键 词： | 延迟焦化 产品收率 Matlab6.5 BP神经网络 预测 |
Application of BP neural network in prediction of product yields of delayed coking |
| |
| Zhu Yingdi,Zhao Dezhi,Zhu Yunyan,Jiu Qiaona. Application of BP neural network in prediction of product yields of delayed coking[J]. Petroleum Refinery Engineering, 2011, 41(1): 50-52 |
| |
| Authors: | Zhu Yingdi Zhao Dezhi Zhu Yunyan Jiu Qiaona |
| |
| Affiliation: | Zhu Yingdi,Zhao Dezhi,Zhu Yunyan,Jiu Qiaona (School of petrochemical Technology,Liaoning University of Petroleum and Chemical Technology,Fushun Liaoning 113001) |
| |
| Abstract: | The accuracy is very low in the prediction of product yields of delayed coking process with conventional mathematic model.A 3 forward-feed BP neural network was constructed with Matlab,the network was trained based on train gradient descent method,and the modeling was performed on the known sample data.The result shows:the BP neural network can efficiently predict the coke make with high accuracy. The highest relative error is 3.33%.As compared with the conventional prediction model,the BP model offers a hi... |
| |
| Keywords: | Matlab6.5 |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
