Benyuan Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Benyuan Sun has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Hangyu Zhong
Sino-European Institute of Aviation Engineering, Civil Aviation University of China, Tianjin, China
6 shared publications - Long Ma
Civil Aviation University of China
3 shared publications - Yu Zhao
Sino-European Institute of Aviation Engineering, Civil Aviation University of China, Tianjin, China
3 shared publications - Huaxiang Wang
School of Electrical and Information Engineering, Tianjin University, Tianjin, China
2 shared publications Huaxiang Wang
1 shared publication- Xiaoguang Huang
State Grid Info and Telecom Group, Beijing, China
1 shared publication
Latest Publications
- 13 January 2026
- Published by Elsevier in Measurement
- Vol. 265
Fine-tuning deep Calderón for absolute imaging with electrical impedance tomography
- 13 January 2026
- Published by Elsevier in Measurement
- Vol. 265
Fine-tuning deep Calderón for absolute imaging with electrical impedance tomography
- 16 June 2024
- Published by Elsevier in Measurement
- Vol. 236
Sensitivity-matrix-independent electrical impedance tomography: Damage detection for composite materials
- 16 June 2024
- Published by Elsevier in Measurement
- Vol. 236
Sensitivity-matrix-independent electrical impedance tomography: Damage detection for composite materials
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
Calderón’s Method-Guided Deep Neural Network for Electrical Impedance Tomography
Electrical impedance tomography (EIT) is a non-invasive, cost-effective and structurally simple technology that enables applications in many fields by measuring changes in electrical parameters. However, the nonlinearity and ill-posedness of the EIT image reconstruction process hinder the complete recovery of the electrical parameters of the field from the measured data, making it still challenging. A Calderón’s method-guided deep neural network (CGDNN) which consists of Calderón’s method as a preliminary imaging module and deep neural network as an image segmentation module is proposed in this paper. The preliminary imaging module of CGDNN avoids the computation of sensitivity matrix and provides a fast and stable nonlinear mapping from measurement data to reconstruction images to facilitate image-to-image mapping by deep neural networks. The preliminary imaging module and the image segmentation module are connected by multi-channel to avoid the manual selection of optimal pre-image. In order to obtain more accurate reconstruction results, a network structure of multi-level U-Net with dense skip connections is applied. Simulation data and experimental data are used to evaluate the feasibility and effectiveness of CGDNN. The results show that CGDNN can obtain high-quality electrical properties distribution images quickly and accurately compared with traditional methods and deep learning image reconstruction methods.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
Calderón’s Method-Guided Deep Neural Network for Electrical Impedance Tomography
Electrical impedance tomography (EIT) is a non-invasive, cost-effective and structurally simple technology that enables applications in many fields by measuring changes in electrical parameters. However, the nonlinearity and ill-posedness of the EIT image reconstruction process hinder the complete recovery of the electrical parameters of the field from the measured data, making it still challenging. A Calderón’s method-guided deep neural network (CGDNN) which consists of Calderón’s method as a preliminary imaging module and deep neural network as an image segmentation module is proposed in this paper. The preliminary imaging module of CGDNN avoids the computation of sensitivity matrix and provides a fast and stable nonlinear mapping from measurement data to reconstruction images to facilitate image-to-image mapping by deep neural networks. The preliminary imaging module and the image segmentation module are connected by multi-channel to avoid the manual selection of optimal pre-image. In order to obtain more accurate reconstruction results, a network structure of multi-level U-Net with dense skip connections is applied. Simulation data and experimental data are used to evaluate the feasibility and effectiveness of CGDNN. The results show that CGDNN can obtain high-quality electrical properties distribution images quickly and accurately compared with traditional methods and deep learning image reconstruction methods.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21610-21619
A New Method for Electrical Impedance Tomography With Incomplete Electrode Array
The possibility to design wearable devices based on Electrical Impedance Tomography (EIT) has recently given a boost to this technology. However, the coverage of the sensor array will vary with the size difference of the measured object, resulting in an incomplete measurement set. If this measurement set is directly invested in the solution of the inverse problem, the imaging quality will be significantly degraded. In this case, it is necessary to take measures to reduce the impact of missing measurement data on reconstruction. In this paper, a new method (MinR-DFF) is proposed which provides a novel solution to the problem of local measurement information loss due to incomplete electrode arrays and achieves high-quality image reconstruction. The effectiveness of the proposed method is verified by numerical simulation and solid-liquid two-phase experiment. By using this method, the correct images of the phantoms are successfully recovered with incomplete electrode array and both the correlation coefficients and the relative errors do not differ from the results using the complete measurement set by more than 5%.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21610-21619
A New Method for Electrical Impedance Tomography With Incomplete Electrode Array
The possibility to design wearable devices based on Electrical Impedance Tomography (EIT) has recently given a boost to this technology. However, the coverage of the sensor array will vary with the size difference of the measured object, resulting in an incomplete measurement set. If this measurement set is directly invested in the solution of the inverse problem, the imaging quality will be significantly degraded. In this case, it is necessary to take measures to reduce the impact of missing measurement data on reconstruction. In this paper, a new method (MinR-DFF) is proposed which provides a novel solution to the problem of local measurement information loss due to incomplete electrode arrays and achieves high-quality image reconstruction. The effectiveness of the proposed method is verified by numerical simulation and solid-liquid two-phase experiment. By using this method, the correct images of the phantoms are successfully recovered with incomplete electrode array and both the correlation coefficients and the relative errors do not differ from the results using the complete measurement set by more than 5%.
- Open Access
- 1 July 2023
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 94 (7)
Numerical analysis of aerospace plate damage via 3D electrical impedance tomography
The carbon fiber reinforced plastic (CFRP) is widely used in the aerospace industry due to its high strength and lightweight characteristics, making it crucial to ensure the reliability of these materials. This has led to an increasing focus on research on the health monitoring technologies of aerospace materials. Electrical impedance tomography (EIT) is a non-invasive and cost-effective technology that has the potential to realize real-time health monitoring of materials by measuring changes in electrical parameters. This paper investigates the application of EIT for direct 3D reconstruction of damage in CFRP laminates with significant conductivity anisotropy distribution. Based on the corrected sensitivity matrix formula, the direct 3D image reconstruction method combined with the fast iterative shrinkage-thresholding algorithm (FISTA) is proposed to achieve damage imaging of CFRP laminates in the inverse problem. The fast convergence of the FISTA makes it possible to solve complex inverse problems. The numerical simulation results indicate that, compared with 2D EIT, the proposed method is more capable of providing damage information, especially in the depth direction. This research plays a constructive role in realizing 3D image reconstruction of CFRP material damage and has significant implications for improving the reliability and safety of CFRP materials in aerospace applications.
- 1 July 2023
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 94 (7)
Open AccessNumerical analysis of aerospace plate damage via 3D electrical impedance tomography
The carbon fiber reinforced plastic (CFRP) is widely used in the aerospace industry due to its high strength and lightweight characteristics, making it crucial to ensure the reliability of these materials. This has led to an increasing focus on research on the health monitoring technologies of aerospace materials. Electrical impedance tomography (EIT) is a non-invasive and cost-effective technology that has the potential to realize real-time health monitoring of materials by measuring changes in electrical parameters. This paper investigates the application of EIT for direct 3D reconstruction of damage in CFRP laminates with significant conductivity anisotropy distribution. Based on the corrected sensitivity matrix formula, the direct 3D image reconstruction method combined with the fast iterative shrinkage-thresholding algorithm (FISTA) is proposed to achieve damage imaging of CFRP laminates in the inverse problem. The fast convergence of the FISTA makes it possible to solve complex inverse problems. The numerical simulation results indicate that, compared with 2D EIT, the proposed method is more capable of providing damage information, especially in the depth direction. This research plays a constructive role in realizing 3D image reconstruction of CFRP material damage and has significant implications for improving the reliability and safety of CFRP materials in aerospace applications.