在宽广的实验参数范围内测量了水平管内油气水多相流动时压力和压差信号,对信号的时域、频域、小波尺度域、分形等特征进行了提取与分析,建立了流型的规则识别和模式识别的融合方法.经过实验测试,该方法可以识别出泡状流、分层流、间歇流和环状流,流型识别率高于90%.
参考文献
[1] | Furness R .Future Flow Measurement Has Digital Influence[J].Control Engineering,1996,20:20. |
[2] | Monji H;Matsui G.Flow Pattern Identification of Gasliquid Two-phase Flow Using a Neural Network[A].,1998 |
[3] | Mi Y;Ishii M;Tsoukalas L H .Vertical Two-Phase Flow Identification Using Advanced Instrumentation and Neural Networks[J].Nuclear Engineering and Design,1998,184:409-420. |
[4] | 白博峰,郭烈锦,陈学俊.气液两相流流型BP网络识别[J].计量学报,2001(02):122-127. |
[5] | 白博峰,郭烈锦,陈学俊.基于反传神经网络和压差波动识别气液两相流流型[J].化工学报,2000(06):848. |
[6] | HaoJiang Wu;Fangde Zhou;Yuyuan Wu .Intelligent identification system of flow regime of oil-gas-water multiphase flow[J].International Journal of Multiphase Flow,2001(3):459-475. |
[7] | 白博峰,郭烈锦,赵亮.汽(气)液两相流流型在线识别的研究进展[J].力学进展,2001(03):437-446. |
[8] | 温熙森;胡莺庆;邱静.模式识别与状态监测[M].长沙:国防科技大学出版社,1997:203-232. |
[9] | 康耀红.数据融合理论与应用[M].西安:西安电子科技大学出版社,1997:1-10. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分:
-
10%
-
20%
-
30%
-
40%
-
50%