| 基于BP神经网络的钢液终点磷含量预测模型 |
| |
| 引用本文： | 徐辉 李旭 张军红 苏小利. 基于BP神经网络的钢液终点磷含量预测模型[J]. 鞍山科技大学学报, 2007, 30(2): 128-130,135 |
| |
| 作者姓名： | 徐辉 李旭 张军红 苏小利 |
| |
| 作者单位： | [1]辽宁科技大学材料科学与工程学院,辽宁鞍山114051 [2]鞍钢新轧钢公司第二炼钢厂,辽宁鞍山114002 |
| |
| 摘 要： | 磷含量是描述钢液质量的一个重要的含量。结合遗传算法（GA）和误差反馈型神经网络（BP）,建立了优化的GA-BP神经网络预测模型,预测转炉炼钢过程钢液终点磷含量。对现场收集的数据进行仿真学习,结果表明,该预测模型收敛速度快,具有较高的预测精度,平均绝对误差可达到0.002 7%。随着训练样本的增加和模型结构的进一步优化和完善,将具有很好的应用前景。
|
| 关 键 词： | 遗传算法 BP神经网络 磷含量 预测 |
| 文章编号： | 1672-4410（2007）02-0128-04 |
| 收稿时间： | 2007-01-08 |
| 修稿时间： | 2007-01-08 |
Prediction model of phosphorus content in molten steel based on BP neural network |
| |
| XU Hui , LI Xu , ZHANG Jun-hong , SU Xiao-li. Prediction model of phosphorus content in molten steel based on BP neural network[J]. Journal of Anshan University of Science and Technology, 2007, 30(2): 128-130,135 |
| |
| Authors: | XU Hui LI Xu ZHANG Jun-hong SU Xiao-li |
| |
| Affiliation: | 1. School of Material Science and Engineering, University of Science and Techology Liaoning, Anshan 114051, China; 2. No. 2 Steelmaking Plant of Angang New Steel Co, Ltd, Anshan 114002, China |
| |
| Abstract: | Phosphorus is an important element to describe molten steel quality.Building a model is necessary to predict phosphorus content.Combined Genetic Algorithms(GA) and back-propagation neural network(BP),an optimized GA-BP model was established to predict phosphorus content.Some data were chosen to train the network model.The results show that the convergence rate was faster,the model had higher accuracy,the average absolute error can reach 0.002 7%.With the increase of training samples and optimization of model structure,this model will have a good applicaton prospect. |
| |
| Keywords: | genetic algorithms back-propagation neural network silicon content prediction |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
