| 基于人工神经网络的稀土合金铸铁腐蚀性能预测 |
| |
| 引用本文： | 王玉荣,乌日根. 基于人工神经网络的稀土合金铸铁腐蚀性能预测[J]. 稀土, 2012, 33(3): 70-73 |
| |
| 作者姓名： | 王玉荣 乌日根 |
| |
| 作者单位： | 包头职业技术学院人文与艺术设计系,内蒙古包头,014030 |
| |
| 基金项目： | 内蒙古自治区高等学校科学技术研究项目 |
| |
| 摘 要： | 通过静态质量损失法腐蚀试验获取BP神经网络的样本数据,利用MATLAB的工具箱函数建立了拓扑结构为5×8×10×1的BP神经网络,并对网络模型的预测精度进行探讨和研究。结果表明,在样本集和训练条件下,5×8×10×1 BP网络对稀土合金铸铁碱腐蚀深度的预测精度较高,较好的解决主要合金成分、腐蚀时间、介质温度与静态腐蚀深度之间的非线性关系,可用于稀土合金铸铁在烧碱液中的静态腐蚀性能的预测分析和研究。
|
| 关 键 词： | BP神经网络 稀土 腐蚀深度 静态腐蚀 预测 |
Corrosion Prediction of Rare Earth Alloy Cast Iron Based on Artificial Neural Network |
| |
| WANG Yu-rong , WU Ri-gen. Corrosion Prediction of Rare Earth Alloy Cast Iron Based on Artificial Neural Network[J]. Chinese Rare Earths, 2012, 33(3): 70-73 |
| |
| Authors: | WANG Yu-rong WU Ri-gen |
| |
| Affiliation: | (Humanities and Artist Design Department,Baotou Vocational Technical College,Baotou 014030,China) |
| |
| Abstract: | The sample data of BP neural network were measured by the static condition hydrometer method,the 5×8×10×1 BP neural network model was established by the toolbox function of MATLAB,and the prediction precision of network model was discussed and researched.The results show that under this sample set and training condition,5×8×10×1 BP neural network has a higher prediction precision of rare earth alloy cast iron alkali corrosion depth,and it also resolves the non-linear relationship between main components of rare earth alloy cast iron,corrosion time,medium temperature and static corrosion depth. |
| |
| Keywords: | BP neural network rare earth corrosion depth static condition prediction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
