Generative adversarial networks for dual-modality electrical tomography in multi-phase flow measurement

Abstract In many multi-phase flows, the online measurement and monitoring of phase fractions as well as distributions play a vital role in determining the process efficiency and safety. The dual-modality electrical capacitance tomography (ECT) and electromagnetic tomography (EMT) technique provides an efficient measure to estimate the distribution of electromagnetic property in rapidly changing multi-phase flows. A generative adversarial network (GAN) is designed to solve the fusion problem of ECT and EMT in the gas-liquid–solid (G-L-S) three-phase flow measurement. The fusion model incorporates the features of dual-modality measurements and images to generate the electromagnetic property in high precision, by which the accurate phase volume can be derived. Furthermore, a simulation approach is proposed to provide the sufficient measurement samples that approximate the real three-phase flow measurement. In the numerical study, the fluidization process of a G-L-S fluidized bed (GLSFB) reactor is simulated and measured by the models of ECT and EMT. The simulation validation on samples from GLSFB and experiments on the three-phase flow setup demonstrate the high accuracy of electromagnetic property reconstruction and generalization ability of fusion model that suitable for various flow regimes. The errors of calculated phase fraction are less than 0.15 in both simulations and experiments.

[1]  H Scharfetter,et al.  Sensitivity maps and system requirements for magnetic induction tomography using a planar gradiometer. , 2001, Physiological measurement.

[2]  Manuchehr Soleimani,et al.  ITS Reconstruction Tool-Suite: An inverse algorithm package for industrial process tomography , 2014 .

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[5]  Fatin Aliah Phang,et al.  Single-Plane Dual-Modality Tomography for Multiphase Flow Imaging by Integrating Electrical Capacitance and Ultrasonic Sensors , 2017, IEEE Sensors Journal.

[6]  Changde Du,et al.  Semi-supervised cross-modal image generation with generative adversarial networks , 2020, Pattern Recognit..

[7]  Christopher E. Zuccarelli,et al.  Slurry bubble column measurements using advanced electrical capacitance volume tomography sensors , 2019, Powder Technology.

[8]  H. F. Morrison,et al.  Monitoring subsurface changes over time with cross-well electromagnetic tomographyt1 , 1995 .

[9]  F. Teixeira,et al.  Toward Electrical Capacitance Tomography of Water-Dominated Multiphase Vertical Flows , 2018, IEEE Sensors Journal.

[10]  Yuxuan Yang,et al.  A Novel Multiplex Network-Based Sensor Information Fusion Model and Its Application to Industrial Multiphase Flow System , 2018, IEEE Transactions on Industrial Informatics.

[11]  Wuqiang Yang,et al.  Adaptive calibration of a capacitance tomography system for imaging water droplet distribution , 2004 .

[12]  Manuchehr Soleimani,et al.  Dual modality ECT–MIT multi-phase flow imaging , 2015 .

[13]  C. O. Vandu,et al.  Large Bubble Sizes and Rise Velocities in a Bubble Column Slurry Reactor , 2004 .

[14]  Zheng-Hong Luo,et al.  CFD simulations of gas–liquid–solid flow in fluidized bed reactors — A review , 2016 .

[15]  J L Mueller,et al.  2D D-bar reconstructions of human chest and tank data using an improved approximation to the scattering transform. , 2010, Physiological measurement.

[16]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[17]  Qiang Wang,et al.  Fuzzy Logic Based Multi-Dimensional Image Fusion for Gas–Oil-Water Flows With Dual-Modality Electrical Tomography , 2020, IEEE Transactions on Instrumentation and Measurement.

[18]  Lihui Peng,et al.  Image reconstruction algorithms for electrical capacitance tomography , 2003 .

[19]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[20]  Lihui Peng,et al.  A Deep Learning Compensated Back Projection for Image Reconstruction of Electrical Capacitance Tomography , 2020, IEEE Sensors Journal.

[21]  D. Gidaspow.  Multiphase Flow and Fluidization: Continuum and Kinetic Theory Descriptions , 1994 .

[22]  F. Teixeira,et al.  Exploiting the Maxwell-Wagner-Sillars Effect for Displacement-Current Phase Tomography of Two-Phase Flows , 2017, IEEE Sensors Journal.

[23]  Lijun Xu,et al.  Dual-Modality Electrical Tomography for Flame Monitoring , 2018, IEEE Sensors Journal.

[24]  Mi Wang,et al.  Visualization of Gas–Oil–Water Flow in Horizontal Pipeline Using Dual-Modality Electrical Tomographic Systems , 2017, IEEE Sensors Journal.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Ezzeddine Zagrouba,et al.  Convolutional neural network-based multimodal image fusion via similarity learning in the shearlet domain , 2018, Neural Computing and Applications.

[27]  S. Savithri,et al.  CFD simulation of hydrodynamics of gas–liquid–solid fluidised bed reactor , 2009 .

[28]  R. Sun,et al.  Improvements in thermo-mechanical and rheological properties of SiO2/epoxy composites using different types of SiO2 , 2015, Journal of Materials Science: Materials in Electronics.

[29]  Huaxiang Wang,et al.  A Dual-Modality Integrated Sensor for Electrical Capacitance Tomography and Electromagnetic Tomography , 2019, IEEE Sensors Journal.

[30]  B. Belyaev,et al.  Electrodynamic Calculation of Effective Electromagnetic Parameters of a Dielectric Medium with Metallic Nanoparticles of a Given Size , 2018, Journal of Experimental and Theoretical Physics.

[31]  Christopher E. Zuccarelli,et al.  Toward Multiphase Flow Decomposition Based on Electrical Capacitance Tomography Sensors , 2017, IEEE Sensors Journal.

[32]  Yan Han,et al.  Electrical resistance tomography with conditional generative adversarial networks , 2020, Measurement Science and Technology.

[33]  Stefano Mandija,et al.  Investigating the challenges and generalizability of deep learning brain conductivity mapping , 2020, Physics in medicine and biology.

[34]  Zhun Wei,et al.  Induced-Current Learning Method for Nonlinear Reconstructions in Electrical Impedance Tomography , 2020, IEEE Transactions on Medical Imaging.

[35]  Dinggang Shen,et al.  3D Auto-Context-Based Locality Adaptive Multi-Modality GANs for PET Synthesis , 2019, IEEE Transactions on Medical Imaging.

[36]  Huaxiang Wang,et al.  Data fusion in dual-mode tomography for imaging oil–gas two-phase flow , 2014 .

[37]  V. Buwa,et al.  Dense gas–liquid–solid flow in a slurry bubble column: Measurements of dynamic characteristics, gas volume fraction and bubble size distribution , 2017 .

[38]  Abdul Ghafoor,et al.  MRI and PET Image Fusion Using Fuzzy Logic and Image Local Features , 2014, TheScientificWorldJournal.

[39]  Seong-Whan Lee,et al.  Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis , 2014, NeuroImage.

[40]  Mario Lucic,et al.  Are GANs Created Equal? A Large-Scale Study , 2017, NeurIPS.

[41]  Huaxiang Wang,et al.  A review on image reconstruction algorithms for electrical capacitance/resistance tomography , 2016 .