Huajun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Huajun Li has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
Sau-Lon James Hu
University of Rhode Island
6 shared publications- Sau-Lon James Hu
University of Rhode Island
5 shared publications Gengshen Liu
Ocean University of China
4 shared publications- Guangyu Liu
Key Laboratory of IoT and Information Fusion Technology of Zhejiang Province, School of Automation, Hangzhou Dianzi University, 2nd Street 1, Hangzhou, 310018, Zhejiang, China
3 shared publications - Shanen Yu
School of Automation, Hangzhou Dianzi University, Hangzhou, China
3 shared publications Bingchen Liang
College of Engineering, Ocean University of China, Qingdao, China
2 shared publications
Latest Publications
- Open Access
- 1 April 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (2) , 72-82
RESE-CNN: Residual Squeeze-and-Excitation Network for High-Contrast Optical Tomography Reconstruction
Optical tomography, a critical component of process tomography, is an important tool for determining the absorption coefficient of cross-sectional media, with significant applications in multi-phase flow analysis, chemical processing, and combustion studies. However, the precise reconstruction of these media distributions is a major challenge. In this work, a sophisticated optical tomography (OT) system coupled with an innovative reconstruction algorithm is presented. The system architecture includes 25 light sources and 25 strategically placed fan-beam receivers. We present a convolutional neural network (CNN) with an encode-decode configuration, augmented by residual connections and a squeeze-and-excitation (SE) attention mechanism. Initial evaluations performed using MATLAB simulations showed the algorithm's superior performance compared to existing methods, with notable improvements in relative error (RE) and correlation coefficient metrics. Subsequent practical experiments validated these findings and emphasized the efficiency of the residual and SE components in improving reconstruction accuracy. While this study focuses on high-contrast binary scenarios, the proposed RESE-CNN framework provides a basic architecture for future extensions to weakly absorbing and scattering media where nonlinear reconstruction problems dominate.
- 1 April 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (2) , 72-82
Open AccessRESE-CNN: Residual Squeeze-and-Excitation Network for High-Contrast Optical Tomography Reconstruction
Optical tomography, a critical component of process tomography, is an important tool for determining the absorption coefficient of cross-sectional media, with significant applications in multi-phase flow analysis, chemical processing, and combustion studies. However, the precise reconstruction of these media distributions is a major challenge. In this work, a sophisticated optical tomography (OT) system coupled with an innovative reconstruction algorithm is presented. The system architecture includes 25 light sources and 25 strategically placed fan-beam receivers. We present a convolutional neural network (CNN) with an encode-decode configuration, augmented by residual connections and a squeeze-and-excitation (SE) attention mechanism. Initial evaluations performed using MATLAB simulations showed the algorithm's superior performance compared to existing methods, with notable improvements in relative error (RE) and correlation coefficient metrics. Subsequent practical experiments validated these findings and emphasized the efficiency of the residual and SE components in improving reconstruction accuracy. While this study focuses on high-contrast binary scenarios, the proposed RESE-CNN framework provides a basic architecture for future extensions to weakly absorbing and scattering media where nonlinear reconstruction problems dominate.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (24) , 41825-41835
Sensor Configuration Optimization in Optical Tomography: A Genetic Algorithm Approach
The sensor configuration in optical tomography systems determines the detection of the region of interest (ROI) and reconstruction performance. This work investigates the configuration optimization using Genetic Algorithm (GA) to enhance reconstruction performance. The angular arrangement of emitters and receivers is combined in a vector for optimization. Parameters independent of prior target information including sensitivity uniformity, orthogonal degree, and sinogram space deviation are considered in the fitness functions. To increase the number of probing beams, the beam number is also considered. Simulations are conducted to evaluate the performance of the optimized configurations compared to regular configurations. A practical tomography system is developed based on the optimal result using fan-beam lasers, and its effectiveness is verified. This optimization provides useful insights and helps improve reconstruction performance.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (24) , 41825-41835
Sensor Configuration Optimization in Optical Tomography: A Genetic Algorithm Approach
The sensor configuration in optical tomography systems determines the detection of the region of interest (ROI) and reconstruction performance. This work investigates the configuration optimization using Genetic Algorithm (GA) to enhance reconstruction performance. The angular arrangement of emitters and receivers is combined in a vector for optimization. Parameters independent of prior target information including sensitivity uniformity, orthogonal degree, and sinogram space deviation are considered in the fitness functions. To increase the number of probing beams, the beam number is also considered. Simulations are conducted to evaluate the performance of the optimized configurations compared to regular configurations. A practical tomography system is developed based on the optimal result using fan-beam lasers, and its effectiveness is verified. This optimization provides useful insights and helps improve reconstruction performance.
- Open Access
Distributed Optical Measurement System for Plate Fin Heat Exchanger
The acquirement of the flow information in plate-fin heat exchanger (PFHE) is limited by its metal structure and complex flow condition. This work develops a new distributed optical measurement system to obtain flow information and boiling intensity. The system utilizes numerous optical fibers installed at the surface of the PFHE to detect optical signals. The attenuation and fluctuation of the signals reflect the variation of the gas-liquid interfaces and can be further used to estimate the boiling intensity. Practical experiments of flow boiling in PFHE with different heating fluxes have been carried out. The results verify that the measurement system can obtain the flow condition. Meanwhile, according to the results, the boiling development in PFHE can be divided into four stages with the increase in the heating flux, including the unboiling stage, initiation stage, boiling developing stage, and fully developed stage.
Open AccessDistributed Optical Measurement System for Plate Fin Heat Exchanger
The acquirement of the flow information in plate-fin heat exchanger (PFHE) is limited by its metal structure and complex flow condition. This work develops a new distributed optical measurement system to obtain flow information and boiling intensity. The system utilizes numerous optical fibers installed at the surface of the PFHE to detect optical signals. The attenuation and fluctuation of the signals reflect the variation of the gas-liquid interfaces and can be further used to estimate the boiling intensity. Practical experiments of flow boiling in PFHE with different heating fluxes have been carried out. The results verify that the measurement system can obtain the flow condition. Meanwhile, according to the results, the boiling development in PFHE can be divided into four stages with the increase in the heating flux, including the unboiling stage, initiation stage, boiling developing stage, and fully developed stage.
- 1 January 2023
- Published by China Engineering Science Press Co. Ltd. in Strategic Study of CAE
- Vol. 25 (3) , 33
Development Strategy for Marine Scientific Equipment and Technologies
Marine scientific research; deep-sea equipment; polar marine equipment; marine observation system; intellectualization; equipment development
- 1 January 2023
- Published by China Engineering Science Press Co. Ltd. in Strategic Study of CAE
- Vol. 25 (3) , 33
Development Strategy for Marine Scientific Equipment and Technologies
Marine scientific research; deep-sea equipment; polar marine equipment; marine observation system; intellectualization; equipment development
- 24 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-10
Configuration Optimization of Optical Tomography Based on Fan-Beam Lasers
Sensor configuration of optical tomography refers to the arrangement of laser emitters and light receivers, which is a key factor for reconstruction performance. This work proposes an optimization method for the tomography configuration based on fan-beam lasers. First, the angular arrangement of the emitters and receivers is organized into a vector. Then, the uniformity coefficient of the sensitivity map is selected as the predictor of the reconstruction performance. Its effectiveness has been investigated and verified in this work. Finally, a genetic algorithm (GA) is used to search for the optimal solution of the vector. The fitness function of GA is the uniformity coefficient. The number of the emitters and receivers is both predetermined as 25 according to our previous work. The optimized solution provided by GA is an irregular configuration with a uniformity coefficient of 0.295. Reconstruction for randomly generated distributions and some specific distributions has been conducted. The reconstruction results verify the superiority of the optimized configuration over other random and regular configurations. The optimized configuration can reconstruct practical distribution effectively with the mean error of 16.9%, and the “soft-edge” and “hard-edge” phantoms can be clearly reconstructed. Meanwhile, a practical tomography system is developed based on the optimized configuration and its effectiveness has also been verified according to static experiments.
- 24 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-10
Configuration Optimization of Optical Tomography Based on Fan-Beam Lasers
Sensor configuration of optical tomography refers to the arrangement of laser emitters and light receivers, which is a key factor for reconstruction performance. This work proposes an optimization method for the tomography configuration based on fan-beam lasers. First, the angular arrangement of the emitters and receivers is organized into a vector. Then, the uniformity coefficient of the sensitivity map is selected as the predictor of the reconstruction performance. Its effectiveness has been investigated and verified in this work. Finally, a genetic algorithm (GA) is used to search for the optimal solution of the vector. The fitness function of GA is the uniformity coefficient. The number of the emitters and receivers is both predetermined as 25 according to our previous work. The optimized solution provided by GA is an irregular configuration with a uniformity coefficient of 0.295. Reconstruction for randomly generated distributions and some specific distributions has been conducted. The reconstruction results verify the superiority of the optimized configuration over other random and regular configurations. The optimized configuration can reconstruct practical distribution effectively with the mean error of 16.9%, and the “soft-edge” and “hard-edge” phantoms can be clearly reconstructed. Meanwhile, a practical tomography system is developed based on the optimized configuration and its effectiveness has also been verified according to static experiments.
- 18 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (19) , 18718-18725
Development of Optical Tomography System Based on Fan-Beam Lasers
The sensor configuration and the sensitivity matrix are two key factors for the optical tomography system. In this work, these two factors are investigated to develop an optical tomography system. First, different sensor configurations are investigated, and their reconstruction performance is estimated. The regular configuration with 25 laser emitters and 25 detectors is selected due to its high reconstruction accuracy and simple structure. Meanwhile, the influence of the pixel grid on the reconstruction performance is also considered. Simulation results indicate that the pixel grid of $50\times50$ is appropriate when the diameter of the region of interest (ROI) is 100 mm, while a denser grid will deteriorate the performance. A practical tomography system is developed based on the $25\times25$ configuration with fan-beam laser diodes and plastic fibers as light detectors. The reconstruction experiments are implemented based on the suggested $50\times50$ pixel grid. Experimental results verify that the effectiveness of the developed system and different distributions can be clearly reconstructed.
- 18 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (19) , 18718-18725
Development of Optical Tomography System Based on Fan-Beam Lasers
The sensor configuration and the sensitivity matrix are two key factors for the optical tomography system. In this work, these two factors are investigated to develop an optical tomography system. First, different sensor configurations are investigated, and their reconstruction performance is estimated. The regular configuration with 25 laser emitters and 25 detectors is selected due to its high reconstruction accuracy and simple structure. Meanwhile, the influence of the pixel grid on the reconstruction performance is also considered. Simulation results indicate that the pixel grid of $50\times50$ is appropriate when the diameter of the region of interest (ROI) is 100 mm, while a denser grid will deteriorate the performance. A practical tomography system is developed based on the $25\times25$ configuration with fan-beam laser diodes and plastic fibers as light detectors. The reconstruction experiments are implemented based on the suggested $50\times50$ pixel grid. Experimental results verify that the effectiveness of the developed system and different distributions can be clearly reconstructed.
- 6 May 2022
- Published by Elsevier in Ocean Engineering
- Vol. 254
Response statistics of monopile OWT to fully nonstationary seismic motion
- 6 May 2022
- Published by Elsevier in Ocean Engineering
- Vol. 254
Response statistics of monopile OWT to fully nonstationary seismic motion
- Open Access
- 1 May 2022
- Published by Springer Nature in Frontiers of Structural and Civil Engineering
- Vol. 16 (5) , 551-563
Demands and challenges for construction of marine infrastructures in China
The oceans are crucial to human civilization. They provide core support for exploitation and utilization of marine space, resources, and energy. Thus, marine infrastructures are vital to a nation’s economic sustainable development. To this end, this article first describes the main challenges in current ocean utilization, and then reviews the China’s ocean engineering progress. As such, six major sectors are evaluated: 1) global climate change and marine environment, 2) comprehensive utilization of marine space, 3) marine transportation infrastructure interconnection, 4) ocean clean energy development and maricultural facilities, 5) ecological crisis and marine engineering countermeasures, and 6) marine infrastructure operation safety and maintenance. Finally, perspectives on future directions of ocean utilization and marine infrastructure construction in China are provided.
- 1 May 2022
- Published by Springer Nature in Frontiers of Structural and Civil Engineering
- Vol. 16 (5) , 551-563
Open AccessDemands and challenges for construction of marine infrastructures in China
The oceans are crucial to human civilization. They provide core support for exploitation and utilization of marine space, resources, and energy. Thus, marine infrastructures are vital to a nation’s economic sustainable development. To this end, this article first describes the main challenges in current ocean utilization, and then reviews the China’s ocean engineering progress. As such, six major sectors are evaluated: 1) global climate change and marine environment, 2) comprehensive utilization of marine space, 3) marine transportation infrastructure interconnection, 4) ocean clean energy development and maricultural facilities, 5) ecological crisis and marine engineering countermeasures, and 6) marine infrastructure operation safety and maintenance. Finally, perspectives on future directions of ocean utilization and marine infrastructure construction in China are provided.
- 5 February 2022
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 108 (2) , 1509-1523
Frequency/Laplace domain methods for computing transient responses of fractional oscillators
- 5 February 2022
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 108 (2) , 1509-1523
Frequency/Laplace domain methods for computing transient responses of fractional oscillators