改进BP神经网络在气液两相流流型识别中的应用
Application of improved BP neural network in identification of air-water two-phase flow patterns
查看参考文献10篇
文摘
|
采用统计理论与分形理论相结合的方法对水平管内空气-水两相流的压差波动信号进行分析,得到了压差均值、标准差、偏斜度、能量份额、盒维数、关联维数和Hurst指数7个参数,并将上述参数作为流型的特征向量输入自适应学习率的改进BP神经网络,通过对训练样本的学习,网络可以实现对未知流型的客观识别.仿真结果表明:统计参数与分形参数相结合得到的流型特征向量可以很好地反映各流型之间的差异,网络识别率高达93%,并且改进后的BP网络具有收敛速度快、不易陷入局部极小的优点. |
其他语种文摘
|
The pressure difference fluctuation signals of the air-water two-phase flow in a horizontal pipe were analyzed'by statistical and fractal theory. Seven parameters, i. e. the averaged value of the pressure difference, standard deviation, skewness, energy ratio, box dimension, correlation dimension and Hurst index were obtained and be used as the characteristic vector of an improved BP neural network with self-adapted learning ratio. Learning form training samples, the network could accomplish the objective identification of the unknown flow patterns. The simulated results showed that the flow pattern characteristic vector which was obtained by statistical and fractal parameters could reflect the differen.ce between various flow patterns and the recognition possibility of the network could reached up to abo ut 9 3 percent. Moreover, the improved BP neural network had the merits of fast convergence for simulation avoidance of local minimum. |
来源
|
化工学报
,2005,56(1):110-115 【核心库】
|
关键词
|
流型识别
;
分形参数
;
统计参数
;
BP网络
|
地址
|
1.
东北电力学院, 吉林, 吉林, 071003
2.
(保定)华北电力大学, 河北, 保定, 071003
3.
东北电力学院, 吉林, 吉林, 132012
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
0438-1157 |
学科
|
力学 |
文献收藏号
|
CSCD:1905180
|
参考文献 共
10
共1页
|
1.
Mi Y. Vertical two-phase flow recognition using advanced instrumentation and neural networks.
Nuclear Engineering and Design,1998,184:409-420
|
被引
17
次
|
|
|
|
2.
吴浩江. 改进BP神经网络在流型智能识别中的应用.
西安交通大学学报,2000,34(1):22-25
|
被引
9
次
|
|
|
|
3.
白博峰. 基于反传神经网络和压差波动识别气液两相流流型.
化工学报,2000,51(12):848-851
|
被引
9
次
|
|
|
|
4.
Cai Y. Application of chaos theory in identification of two-phase flow patterns and transitions in a small horizontal rectangular channel.
ASME J. Fluid Engineering,1996,118(2):383-390
|
被引
13
次
|
|
|
|
5.
金宁德. 基于Kolmogorov熵时间序列分析的垂直上升管中油水两相流流型表征.
化工学报,2003,54(7):936-941
|
被引
6
次
|
|
|
|
6.
李勇. Operation Performance Diagnosis Technology and Its Application for Steam Turbine(汽轮机运行性能诊断技术及其应用).
汽轮机运行性能诊断技术及其应用,1999:91-120
|
被引
1
次
|
|
|
|
7.
孙斌. [thesis](学位论文).
Statistical characteristic of different pressure fluctuation of gas-liquid two-phase flow pattern in horizontal tube:(学位论文),2002
|
被引
1
次
|
|
|
|
8.
李后强. Fractal Theory and Its Application in Molecule Science (分形理论及其在分子科学中的应用).
分形理论及其在分子科学中的应用,1997:191
|
被引
4
次
|
|
|
|
9.
谢应齐. Mathematical Method of Nonlinear Dynamics(非线性动力学数学方法).
非线性动力学数学方法,2001:160
|
被引
1
次
|
|
|
|
10.
高大启. On structures of supervised linear basis function feed forward three-layered neural networks.
电路与系统学报,1997,2(3):31-37
|
被引
4
次
|
|
|
|
|