基于集成学习的盐穴造腔预测及工艺参数智能设计
|
|
陈加松,王桂九,白雪峰,段冲,施锡林,张桂民,李小菲,金辉,李金龙
|
Ensemble learning-based prediction of salt cavern leaching and intelligent design of process parameters
|
|
Jiasong CHEN,Guijiu WANG,Xuefeng BAI,Chong DUAN,Xilin SHI,Guimin ZHANG,Xiaofei LI,Hui JIN,Jinlong LI
|
|
| 表 3 盐穴水溶造腔代理模型数据集示例 |
| Tab.3 Example of dataset for salt-cavern solution-mining surrogate model |
|
| 组别 | w(z)/% | $ \cdots $ | 循环 方式 | t/d | Hi/m | Ho/m | Hp/m | $ \cdots $ | V/m3 | Rs(z)/m | | z=2 m | z=4 m | $ \cdots $ | z=0 | $ \cdots $ | z=110 m | | 1 | 95 | 90 | $ \cdots $ | 1 | 118 | 13 | 19 | 31 | $ \cdots $ | 220 211 | 0 | $ \cdots $ | 35.27 | | 2 | 90 | 90 | $ \cdots $ | 1 | 105 | 11 | 17 | 31 | $ \cdots $ | 199 136 | 0 | $ \cdots $ | 14.52 | | 3 | 83 | 88 | $ \cdots $ | 2 | 101 | 12 | 20 | 29 | $ \cdots $ | 207 023 | 0 | $ \cdots $ | 9.24 | | 4 | 75 | 76 | $ \cdots $ | 1 | 104 | 15 | 20 | 31 | $ \cdots $ | 209 561 | 0 | $ \cdots $ | 25.94 | | 5 | 74 | 70 | $ \cdots $ | 1 | 101 | 12 | 18 | 30 | $ \cdots $ | 201 553 | 0 | $ \cdots $ | 17.53 | | 6 | 26 | 30 | $ \cdots $ | 2 | 134 | 12 | 18 | 34 | $ \cdots $ | 206 602 | 0 | $ \cdots $ | 26.21 | | 7 | 38 | 35 | $ \cdots $ | 1 | 114 | 11 | 16 | 29 | $ \cdots $ | 211 482 | 0 | $ \cdots $ | 7.98 |
|
|
|