|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2003年10 期
| 标题 |
| 基于BP-SA混合优化策略的铁路货运量时间序列预测(25 卷) |
| 英文标题 |
| Forecast on Temporal Sequence of Railway Freight Transport Volume based on BP-SA Mixing and Optimizing Solution |
| 摘要 |
| 铁路货运量的时间序列预测可以看为一个从输入到输出的非线性影射。神经网络尤其是BP神经网络，被广泛用于非线性逼近问题。但是，BP算法训练神经网络速度慢、易陷入局部极值。而模拟退火算法（SA）具有很好的全局寻优性。因而提出混合优化策略，即将反向传播算法（BP）和模拟 |
| 作者 |
| 新闻作者:侯福均，吴祈宗 |
| 关键字 |
