Junjie Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junjie Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Jingming Cao
School of Automation and Intelligence, Beijing Jiaotong University, Beijing, China
6 shared publications - Ze Liu
School of Automation and Intelligence, Beijing Jiaotong University, Beijing, China
6 shared publications - Zewen Wan
School of Automation and Intelligence, Beijing Jiaotong University
4 shared publications - Dingyi Ma
School of Automation and Intelligence, Beijing Jiaotong University, Beijing, PR China
3 shared publications - Yizhou Zhou
School of Automation and Intelligence, Beijing Jiaotong University, Beijing, PR China
3 shared publications - Ziao Zhang
School of Automation and Intelligence, Beijing Jiaotong University
2 shared publications
Latest Publications
- 30 September 2025
- Published by Springer Nature in Analog Integrated Circuits and Signal Processing
- Vol. 125 (2) , 1-15
A novel direct calculation algorithm using Taylor expansion in FPGA for DDS signal quality enhancement
- 30 September 2025
- Published by Springer Nature in Analog Integrated Circuits and Signal Processing
- Vol. 125 (2) , 1-15
A novel direct calculation algorithm using Taylor expansion in FPGA for DDS signal quality enhancement
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-9
Suppression of Electromagnetic Edge Effect in Planar Electromagnetic Tomography
Electromagnetic tomography (EMT) is a non-destructive testing method based on boundary measurement value projection to reconstruct the distribution of electrical parameters. Planar EMT can meet the requirements of metal plane defect monitoring, but there is an electromagnetic edge effect at the edge of the metal plane. Magnetic field distortion and magnetic leakage cause the coil excitation-detection performance to change, destroying the consistency of the coil array and reducing the image reconstruction quality. To solve this problem, the characteristics of the shielding layer, which guides the magnetic field, are utilised to suppress the electromagnetic edge effect. First, the equivalent magnetic circuit model of planar EMT is introduced, and the relationship between the boundary measurement value, sensitivity matrix, and shielding layer is derived. Then, by combining simulation and experiment, the effects of ferrite and aluminum shielding layers on the edge effect, and the effects of shielding layers of different thicknesses and positions on planar EMT, are compared. The results demonstrate that aluminum, as a shielding layer, can effectively suppress the edge effect and improve image reconstruction accuracy.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-9
Suppression of Electromagnetic Edge Effect in Planar Electromagnetic Tomography
Electromagnetic tomography (EMT) is a non-destructive testing method based on boundary measurement value projection to reconstruct the distribution of electrical parameters. Planar EMT can meet the requirements of metal plane defect monitoring, but there is an electromagnetic edge effect at the edge of the metal plane. Magnetic field distortion and magnetic leakage cause the coil excitation-detection performance to change, destroying the consistency of the coil array and reducing the image reconstruction quality. To solve this problem, the characteristics of the shielding layer, which guides the magnetic field, are utilised to suppress the electromagnetic edge effect. First, the equivalent magnetic circuit model of planar EMT is introduced, and the relationship between the boundary measurement value, sensitivity matrix, and shielding layer is derived. Then, by combining simulation and experiment, the effects of ferrite and aluminum shielding layers on the edge effect, and the effects of shielding layers of different thicknesses and positions on planar EMT, are compared. The results demonstrate that aluminum, as a shielding layer, can effectively suppress the edge effect and improve image reconstruction accuracy.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Adaptive Measurement for High-Speed Electromagnetic Tomography via Deep Reinforcement Learning
Electromagnetic tomography (EMT) is an advanced non-invasive imaging technique that is sensitive to conductive and magnetic materials, offering significant potential for metal non-destructive testing. To overcome the challenges associated with measuring a large number of electromagnetic features in high-speed EMT imaging, we propose a novel adaptive measurement method based on deep reinforcement learning. The AMEMT-Net decision model is designed to dynamically optimize the measurement sequence and prioritize the key features that most significantly contribute to the imaging process. Since EMT’s electromagnetic features in EMT are not entirely independent, the proposed method enables high-quality imaging without requiring all features, thus improving detection speed. Using a 24-coil planar EMT system as a case study, we evaluated the method’s performance in metal defect imaging through electromagnetic finite element simulations and FPGA-based practical experiments. The results show that, when using the Tikhonov image reconstruction method, AMEMT-Net requires only 10% of the electromagnetic features to achieve over 85% of the correlation coefficient compared to using all features. This reduces the EMT imaging time to just 21% of that required by traditional methods and makes image reconstruction less sensitive to noise. This study demonstrates the effectiveness of the proposed adaptive measurement method, providing an innovative approach for the development of high-speed EMT.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Adaptive Measurement for High-Speed Electromagnetic Tomography via Deep Reinforcement Learning
Electromagnetic tomography (EMT) is an advanced non-invasive imaging technique that is sensitive to conductive and magnetic materials, offering significant potential for metal non-destructive testing. To overcome the challenges associated with measuring a large number of electromagnetic features in high-speed EMT imaging, we propose a novel adaptive measurement method based on deep reinforcement learning. The AMEMT-Net decision model is designed to dynamically optimize the measurement sequence and prioritize the key features that most significantly contribute to the imaging process. Since EMT’s electromagnetic features in EMT are not entirely independent, the proposed method enables high-quality imaging without requiring all features, thus improving detection speed. Using a 24-coil planar EMT system as a case study, we evaluated the method’s performance in metal defect imaging through electromagnetic finite element simulations and FPGA-based practical experiments. The results show that, when using the Tikhonov image reconstruction method, AMEMT-Net requires only 10% of the electromagnetic features to achieve over 85% of the correlation coefficient compared to using all features. This reduces the EMT imaging time to just 21% of that required by traditional methods and makes image reconstruction less sensitive to noise. This study demonstrates the effectiveness of the proposed adaptive measurement method, providing an innovative approach for the development of high-speed EMT.
- Open Access
- 26 May 2025
- Published by Springer Nature in Research Square
A Novel Direct Calculation Algorithm using Taylor Expansion in FPGA for DDS Signal Quality Enhancement
The precision measurement of capacitance necessitates the utilisation of a precision capacitance bridge, wherein a sine signal serves as a reference. Consequently, the precision of the sine signal is of paramount importance for the precision measurement of capacitance. In the conventional method of generating a sine signal , a look-up table is employed as the data source. However, the look-up table approach necessitates an excessive amount of read-only memory space to fulfil the requirements of high-precision scenarios. In this paper, we proposes an novel algorithm based on Taylor expansion to calculate the sine function. This algorithm doesn’t use any read-only storage space. Compared with the Coordinate Rotation Digital Computer algorithm in computer, it is based on the pipelined architecture to balance latency and digital signal processor resource consumption. For the Lagrange residual term error problem of Taylor expansion, the optimization algorithm using trigonometric periodicity and the complementary algorithm of sine and cosine functions is proposed. To evaluate the accuracy of the sine function generated by the algorithm, direct digital synthesis and digital to analog converter outputs are utilized to improve the accuracy and enhance the total harmonic distortion as compared to the conventional algorithm.
- 26 May 2025
- Published by Springer Nature in Research Square
Open AccessA Novel Direct Calculation Algorithm using Taylor Expansion in FPGA for DDS Signal Quality Enhancement
The precision measurement of capacitance necessitates the utilisation of a precision capacitance bridge, wherein a sine signal serves as a reference. Consequently, the precision of the sine signal is of paramount importance for the precision measurement of capacitance. In the conventional method of generating a sine signal , a look-up table is employed as the data source. However, the look-up table approach necessitates an excessive amount of read-only memory space to fulfil the requirements of high-precision scenarios. In this paper, we proposes an novel algorithm based on Taylor expansion to calculate the sine function. This algorithm doesn’t use any read-only storage space. Compared with the Coordinate Rotation Digital Computer algorithm in computer, it is based on the pipelined architecture to balance latency and digital signal processor resource consumption. For the Lagrange residual term error problem of Taylor expansion, the optimization algorithm using trigonometric periodicity and the complementary algorithm of sine and cosine functions is proposed. To evaluate the accuracy of the sine function generated by the algorithm, direct digital synthesis and digital to analog converter outputs are utilized to improve the accuracy and enhance the total harmonic distortion as compared to the conventional algorithm.
- 14 September 2024
- Published by Elsevier in Measurement
- Vol. 241
Research on FPC coils with limited turns in planar electromagnetic tomography
- 14 September 2024
- Published by Elsevier in Measurement
- Vol. 241
Research on FPC coils with limited turns in planar electromagnetic tomography