Estimation of Reference Voltages for Time-difference Electrical Impedance Tomography

Hao Yu, Xingchen Wan, Zhongxu Dong, Zhixi Zhang, Jiabin Jia

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Electrical impedance tomography (EIT), as a merging technology, has been widely used in the industrial and clinical fields. However, the causes of the uncertainty of measuring reference voltages, which are affected by medium temperature, measurement errors, and reference conductivity distribution that varies with the patient's posture, have brought obstacles to applying EIT in industry and medicine. In this article, two methods: the multiple measurements (MMs) method and the deep learning method, convolutional neural network (CNN) are proposed to establish the nonlinear mapping between measurement voltages and reference voltages. The novelty of this article is first adopting the deep learning method to estimate the reference voltages from measurement voltages for the time-difference EIT. Both static experiments - water tank experiments and dynamic experiments - two-phase flow experiments were carried out. Compared with the two existing estimation methods: best homogeneous (BH) approximation and measurement-scale feature (MSF), and the proposed MM method, the deep learning method shows excellent results in quantitative analysis of the relative errors (REs) of reference voltages and ground truth. In addition, the CNN method displays a better performance in qualitative analysis in terms of the reconstructed tomographic images. The study shows the potential to real-time estimate the reference voltages for time-difference EIT in the industrial and medical fields.

Original languageEnglish
Article number4506710
JournalIEEE Transactions on Instrumentation and Measurement
Early online date28 Oct 2022
Publication statusE-pub ahead of print - 28 Oct 2022

Keywords / Materials (for Non-textual outputs)

  • Conductivity
  • Conductivity reconstruction
  • Deep learning
  • Electrical impedance tomography
  • Estimation
  • Image reconstruction
  • Temperature measurement
  • Voltage measurement
  • convolutional neural network (CNN)
  • deep learning
  • electrical impedance tomography (EIT)
  • reference voltages


Dive into the research topics of 'Estimation of Reference Voltages for Time-difference Electrical Impedance Tomography'. Together they form a unique fingerprint.

Cite this