CIESC Journal ›› 2024, Vol. 75 ›› Issue (3): 847-857.DOI: 10.11949/0438-1157.20231038

• Fluid dynamics and transport phenomena • Previous Articles     Next Articles

Unsupervised-feature extraction of gas-liquid two-phase flow pattern based on convolutional autoencoder: principle and application

Sirui CHEN1(), Jingliang BI2, Lei WANG1, Yuanyuan LI3, Gui LU3()   

  1. 1.College of Mathematics and Physics, North China Electric Power University, Beijing 102206, China
    2.Nuclear Power Institute of China, Chengdu 610213, Sichuan, China
    3.School of Energy, Power and Mechanical Engineering, North China Electric Power University, Beijing 102206, China
  • Received:2023-10-07 Revised:2023-12-29 Online:2024-05-11 Published:2024-03-25
  • Contact: Gui LU

气液两相流流型特征无监督提取的卷积自编码器:机理及应用

陈思睿1(), 毕景良2, 王雷1, 李元媛3, 陆规3()   

  1. 1.华北电力大学数理学院,北京 102206
    2.中国核动力研究设计院,四川 成都 610213
    3.华北电力大学能源动力与机械工程学院,北京 102206
  • 通讯作者: 陆规
  • 作者简介:陈思睿(1999—),女,硕士研究生, chen_Echo277@163.com
  • 基金资助:
    国家自然科学基金面上项目(12005217);中央高校基本业务费专项(2022JG006)

Abstract:

In two-phase flow measurements, the accurate identification of the flow pattern is the basis for the measurement of pressure drop, heat transfer and other thermal parameters. Traditional two-phase flow methods have limited applicability under different operating conditions due to the limitations of test conditions and data. Artificial intelligence algorithms can take into account both efficiency and accuracy, but the feature extraction method is still the difficulty in its identification. The accurate identification of flow patterns is of great significance for interpreting data, improving models, and improving application effects. Therefore, this paper proposes a feature extraction method based on unsupervised learning of convolutional autoencoder, which inputs the extracted features into random forest, support vector machine, and back propagation neural network classifiers for classification, respectively. The experimental results show that the recognition accuracy for all four stream types reaches more than 99%, which indicates that the convolutional autoencoder feature extraction method can significantly improve the accuracy of the classification algorithm, has good compatibility with different classifiers, and also provides help for the feature extraction method for subsequent popular recognition.

Key words: gas-liquid flow, bubble, neural networks, algorithm

摘要:

在气液两相流的测量中,流型的准确识别是压降、换热等热工参数测量的基础。传统的两相流方法由于试验条件和数据的局限性使得在不同工况下的适用性有限。人工智能算法可以同时兼顾效率和精度,但特征提取方法仍是识别的难点。流型的准确识别对于解释数据,改进模型,以及提高应用效果方面具有重要意义。因此提出了一种基于卷积自编码器的无监督学习的特征提取方法,将特征提取后分别输入到随机森林,支持向量机以及前馈神经网络分类器中进行分类。实验结果表明,对四种流型的识别精度都达到了99%以上,说明卷积自编码器特征提取方法能显著地提高分类算法的准确率,对不同的分类器具有很好的兼容性,也为今后流型识别的特征提取方法提供了帮助。

关键词: 气液两相流, 气泡, 神经网络, 算法

CLC Number: