|
| 摘要: |
| 根据南京炼油厂制氢车间的生产数据，用人工神经网络(ANN)的反向传播(BP)算法对制氢装置转化生产中的水碳比进行预测。提出了适宜的人工神经网络拓扑结构，讨论了BP算法中学习速率、动量系数及过拟合现象对网络的影响，通过生产数据的检验表明，ANN方法能准确地关联和预报制氢装置转化生产中的水碳比，水碳比预测平均相对误差为2．83％。 |
| 关键词: 炼油厂 人工神经网络 氢气 制备工艺 水碳比 |
| DOI： |
| 分类号:TQ116.28 |
| 基金项目:金陵石化公司青年基金资助 (项目编号 :991 3B)。 |
|
| STUDY ON MODEL OF CARBON AND STEAM RATIO IN HYDROGEN PRODUCTION BASED ON ARTIFICIAL NEURAL NETWORK METHOD |
|
Zhang Tao 1 Huo Ning 1 Li Weimin 2 et al
|
| Abstract: |
| According to the hydrogen productiondate base, the Artificial Neural Network(ANN) was used for prediction carbon and steam ratio with Back- Propagation(BP) method. The appropriate topology of ANN was obtained. The learning rate, the momentum factor and ov |
| Key words: artificial neural network, BP algorithm, hydrogen production, carbon and steam ratio |
