摘要
油水两相流的流型影响着流动参数的准确测量以及两相流系统的运行特性。针对电导波动信号的非平稳和非线性特点,采用统计理论、小波包理论和混沌理论相结合的方法对垂直上升管内油水两相流的电导波动信号进行分析,得到了11个反映油水两相流流动特性的特征参数,并将这些参数作为流型特征向量,运用最小二乘支持向量机进行训练并识别流型。实现了一种从不同类型、不同角度提取多个特征的流型识别算法,解决了现有算法中特征提取不足的问题。实验结果表明,这是一种有效的、高精度的识别方法。
Oil-water two-phase flow regimes affect the performance characteristics of such a two-phase system, and the exact measurement of flow parameters. Aimed at the nonlinear and non-stationary characteristics of conductance fluctuation signals, the characteristics of oil-water two phase flow regimes in vertical upward flow pipes was studied by using the statistical method, wavelet packet decomposition and chaotic time series analysis. Eleven parameters reflecting flow characteristics of oil-water two phase flow were extracted and were taken as the feature vectors of flow regimes. The feature vectors were put into least squares support vector machine and trained to realize the flow regimes identification. The proposed algorithm extracts multiple features from different types and perspectives,thus solving the insufficiency of feature extraction in current flow regimes identification methods. Experiment results show that the new algorithm is an effective identification method with high accuracy.
出处
《燕山大学学报》
CAS
2008年第3期258-262,共5页
Journal of Yanshan University
基金
国家高技术研究发展计划资助项目(2007AA06z231)
关键词
流型识别
多特征提取
最小二乘支持向量机
油水两相流
flow regimes identification
multi-feature extraction
least squares support vector machine （LS-SVM）
oil-water two phase flow
