Multitask-Based Temporal-Channelwise CNN for Parameter Prediction of Two-Phase Flows

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Zhongke Gao
  • Linhua Hou
  • Weidong Dang
  • Xinmin Wang
  • Xiong Yang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)6329-6336
Journal / PublicationIEEE Transactions on Industrial Informatics
Volume17
Issue number9
Online published6 Mar 2020
Publication statusPublished - Sep 2021

Abstract

Gas-liquid two-phase flow is of great importance in various industrial processes. How to accurately measure the flow parameters in the gas-liquid two-phase flow remains a challenging problem. In this article, we develop a novel deep learning based soft measure technique to predict the gas void fraction, which is one key parameter in a gas-liquid two-phase flow. We conduct the vertical upward gas-liquid two-phase flow experiments to measure the flow signals by using the four-sector distributed conductance sensor. Then, we design a novel multitask-based temporal-channelwise convolutional neural network (MTCCNN) to predict the gas void fraction. In MTCCNN, we first utilize the decomposed convolutional block to extract temporal dependence and channel connection from fluid data. After further fusion by the dense layer, we apply multitask learning to make full use of the extracted features through both classification branch and gas void fraction prediction branch. We compare our MTCCNN with its variations to demonstrate the proposed improvements. We also present other competitive methods for comparisons, which shows that our MTCCNN presents a better performance in gas void fraction prediction.

Research Area(s)

  • Kernel, Convolution, Feature extraction, Brain modeling, Genetic algorithms, Convolutional neural networks, Convolutional neural network (CNN), deep learning, gas-liquid two-phase flow, soft measuring, ARTIFICIAL NEURAL-NETWORK, VOID-FRACTION, VOLUME FRACTION, MODEL, PATTERN

Citation Format(s)

Multitask-Based Temporal-Channelwise CNN for Parameter Prediction of Two-Phase Flows. / Gao, Zhongke; Hou, Linhua; Dang, Weidong; Wang, Xinmin; Yang, Xiong; Chen, Guanrong.

In: IEEE Transactions on Industrial Informatics, Vol. 17, No. 9, 09.2021, p. 6329-6336.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review