|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2003年10 期
| 標題 |
| 基于BP-SA混合優(yōu)化策略的鐵路貨運量時間序列預測(25 卷) |
| 英文標題 |
| Forecast on Temporal Sequence of Railway Freight Transport Volume based on BP-SA Mixing and Optimizing Solution |
| 摘要 |
| 鐵路貨運量的時間序列預測可以看為一個從輸入到輸出的非線性影射。神經網絡尤其是BP神經網絡，被廣泛用于非線性逼近問題。但是，BP算法訓練神經網絡速度慢、易陷入局部極值。而模擬退火算法（SA）具有很好的全局尋優(yōu)性。因而提出混合優(yōu)化策略，即將反向傳播算法（BP）和模擬 |
| 作者 |
| 新聞作者:侯福均，吳祈宗 |
| 關鍵字 |
