Dawei Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dawei Shen has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Dongxing Pei
State Key Laboratory of Dynamic Measurement Technology, North University of China, Taiyuan 030051, Shanxi, China
3 shared publications- Tiehua Ma
State Key Laboratory of Dynamic Measurement Technology, North University of China, Taiyuan 030051, China
2 shared publications - Bin Jiao
School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China
1 shared publication - Chuanmeng Sun
School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China
1 shared publication Jin Ma
Shanxi Vocational & Technical College of Finance & Trade, Taiyuan, Shanxi 030031, China
1 shared publication- Jing Zhang
Shanxi Vocational & Technical College of Finance & Trade, Taiyuan, Shanxi 030031, China
1 shared publication
Latest Publications
- Open Access
- 12 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (10) , 5411
Downhole Coal–Rock Recognition Based on Joint Migration and Enhanced Multidimensional Full-Scale Visual Features
The accurate identification of coal and rock at the mining face is often hindered by adverse underground imaging conditions, including poor lighting and strong reflectivity. To tackle these issues, this work introduces a recognition framework specifically designed for underground environments, leveraging joint migration and enhancement of multidimensional and full-scale visual representations. A Transformer-based architecture is employed to capture global dependencies within the image and perform reflectance component denoising. Additionally, a multi-scale luminance adjustment module is integrated to merge features across perceptual ranges, mitigating localized brightness anomalies such as overexposure. The model is structured around an encoder–decoder backbone, enhanced by a full-scale connectivity mechanism, a residual attention block with dilated convolution, Res2Block elements, and a composite loss function. These components collectively support precise pixel-level segmentation of coal–rock imagery. Experimental evaluations reveal that the proposed luminance module achieves a PSNR of 21.288 and an SSIM of 0.783, outperforming standard enhancement methods like RetinexNet and RRDNet. The segmentation framework achieves a MIoU of 97.99% and an MPA of 99.28%, surpassing U-Net by 2.21 and 1.53 percentage points, respectively.
- 12 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (10) , 5411
Open AccessDownhole Coal–Rock Recognition Based on Joint Migration and Enhanced Multidimensional Full-Scale Visual Features
The accurate identification of coal and rock at the mining face is often hindered by adverse underground imaging conditions, including poor lighting and strong reflectivity. To tackle these issues, this work introduces a recognition framework specifically designed for underground environments, leveraging joint migration and enhancement of multidimensional and full-scale visual representations. A Transformer-based architecture is employed to capture global dependencies within the image and perform reflectance component denoising. Additionally, a multi-scale luminance adjustment module is integrated to merge features across perceptual ranges, mitigating localized brightness anomalies such as overexposure. The model is structured around an encoder–decoder backbone, enhanced by a full-scale connectivity mechanism, a residual attention block with dilated convolution, Res2Block elements, and a composite loss function. These components collectively support precise pixel-level segmentation of coal–rock imagery. Experimental evaluations reveal that the proposed luminance module achieves a PSNR of 21.288 and an SSIM of 0.783, outperforming standard enhancement methods like RetinexNet and RRDNet. The segmentation framework achieves a MIoU of 97.99% and an MPA of 99.28%, surpassing U-Net by 2.21 and 1.53 percentage points, respectively.
- Open Access
- 30 September 2022
- Published by Hindawi Limited in Mathematical Problems in Engineering
- Vol. 2022, 1-8
Design and Simulation of Multichannel Dynamic Measurement Control System
The circuit system designed in this paper uses FPGA and single-chip microcomputer as the main chips. It uses VHDL language programming and performs functional simulation and verification of the core control program through ModelSim software, and finally, a storage-type dynamic measurement and control system with one-to-multiple channels, adjustable trigger modes, and optional sampling frequency is realized. At the same time, the system is further optimized in terms of power consumption and volume. The storage measurement and control system can successfully record eight-channel dynamic voltage signals, and the relative error of the experimental results is less than 2 through the simulation trigger experiment and Hopkinson bar experiment loading.
- 30 September 2022
- Published by Hindawi Limited in Mathematical Problems in Engineering
- Vol. 2022, 1-8
Open AccessDesign and Simulation of Multichannel Dynamic Measurement Control System
The circuit system designed in this paper uses FPGA and single-chip microcomputer as the main chips. It uses VHDL language programming and performs functional simulation and verification of the core control program through ModelSim software, and finally, a storage-type dynamic measurement and control system with one-to-multiple channels, adjustable trigger modes, and optional sampling frequency is realized. At the same time, the system is further optimized in terms of power consumption and volume. The storage measurement and control system can successfully record eight-channel dynamic voltage signals, and the relative error of the experimental results is less than 2 through the simulation trigger experiment and Hopkinson bar experiment loading.
- Open Access
- 7 April 2022
- Published by Hindawi Limited in Mobile Information Systems
- Vol. 2022, 1-11
An Abnormal Signal Processing Method for Sensors Using Convolution Neural Network
The combination of sensor and neural network (NN) is an important development direction for intelligent sensors. This paper discusses the application of NN in sensor signal processing, introduces the basic principles, and illustrates the application method with examples. Based on the analysis of sensors abnormal signal processing, a diagnostic scheme based on CNN is proposed. At each current moment, NN is trained by the latest historical dataset of fixed length to complete the forecast of the next moment. The confidence interval is determined by the models residual of NN. Moreover, this paper proposes a signal noise reduction and compression method of multisensor system using the CNN. A multisensor sequence of noisy output signal and targets true value are used as samples for network training, and the trained network is tested with test samples. The effectiveness of this method is verified by simulation of several typical function approximations. The results strongly suggest the advantages of CNN method for sensor abnormal signal processing and provide a solid foundation for the reliable use of sensors in such type of problems.
- 7 April 2022
- Published by Hindawi Limited in Mobile Information Systems
- Vol. 2022, 1-11
Open AccessAn Abnormal Signal Processing Method for Sensors Using Convolution Neural Network
The combination of sensor and neural network (NN) is an important development direction for intelligent sensors. This paper discusses the application of NN in sensor signal processing, introduces the basic principles, and illustrates the application method with examples. Based on the analysis of sensors abnormal signal processing, a diagnostic scheme based on CNN is proposed. At each current moment, NN is trained by the latest historical dataset of fixed length to complete the forecast of the next moment. The confidence interval is determined by the models residual of NN. Moreover, this paper proposes a signal noise reduction and compression method of multisensor system using the CNN. A multisensor sequence of noisy output signal and targets true value are used as samples for network training, and the trained network is tested with test samples. The effectiveness of this method is verified by simulation of several typical function approximations. The results strongly suggest the advantages of CNN method for sensor abnormal signal processing and provide a solid foundation for the reliable use of sensors in such type of problems.
- Open Access
- 10 March 2022
- Published by Hindawi Limited in Scientific Programming
- Vol. 2022, 1-12
Structure Strength Dynamic Strain Measurement Acquisition System Based on Data Fusion
Strain measurement technology plays an irreplaceable role in measuring the force change characteristics of mechanical components and monitoring important engineering structures. In structural health monitoring, dynamic stress and strain testing is the main way to determine its overall fatigue, and excessive stress will seriously affect the strength of the structure, causing the structure to deform or even break, which will affect the reliability of the experiment and the use of workpieces, so it is of great significance to carry out dynamic stress and strain tests on the structure. Resistance strain measurement technology is widely used in the civil engineering industry, but the principles of modern physics technology are unknown to many practitioners. Data fusion technology or information fusion technology is also called multisensor fusion technology. Using computer technology to automatically analyze and integrate the data processing process of the detection data from multiple sensors according to time sequence and certain criteria, it can complete the required decision-making and judgment.
- 10 March 2022
- Published by Hindawi Limited in Scientific Programming
- Vol. 2022, 1-12
Open AccessStructure Strength Dynamic Strain Measurement Acquisition System Based on Data Fusion
Strain measurement technology plays an irreplaceable role in measuring the force change characteristics of mechanical components and monitoring important engineering structures. In structural health monitoring, dynamic stress and strain testing is the main way to determine its overall fatigue, and excessive stress will seriously affect the strength of the structure, causing the structure to deform or even break, which will affect the reliability of the experiment and the use of workpieces, so it is of great significance to carry out dynamic stress and strain tests on the structure. Resistance strain measurement technology is widely used in the civil engineering industry, but the principles of modern physics technology are unknown to many practitioners. Data fusion technology or information fusion technology is also called multisensor fusion technology. Using computer technology to automatically analyze and integrate the data processing process of the detection data from multiple sensors according to time sequence and certain criteria, it can complete the required decision-making and judgment.
- Open Access
- 9 February 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-9
Design of MultiChannel Parallel Dynamic Testing Virtual Instrument Based on Dynamic Measurement
With the rapid advancement of virtual instrument technology, converting the data measurement and control platform to a virtual one has become fashionable. This study focuses on dynamic measurement in order to create a multichannel parallel dynamic testing virtual instrument and then test the instruments performance. System login, user management, database storage, query and compression, data processing and real-time display, multifunctional analysis, remote access, and report generation modules have all been designed and implemented. A dynamic measurement uncertainty evaluation method based on quasi-Monte Carlo (MC) method is proposed in light of the common phenomenon that static is used instead of dynamic in the current evaluation process of dynamic measurement uncertainty. For this example, the actual results show that the algorithm produces very reliable and stable calculation results.
- 9 February 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-9
Open AccessDesign of MultiChannel Parallel Dynamic Testing Virtual Instrument Based on Dynamic Measurement
With the rapid advancement of virtual instrument technology, converting the data measurement and control platform to a virtual one has become fashionable. This study focuses on dynamic measurement in order to create a multichannel parallel dynamic testing virtual instrument and then test the instruments performance. System login, user management, database storage, query and compression, data processing and real-time display, multifunctional analysis, remote access, and report generation modules have all been designed and implemented. A dynamic measurement uncertainty evaluation method based on quasi-Monte Carlo (MC) method is proposed in light of the common phenomenon that static is used instead of dynamic in the current evaluation process of dynamic measurement uncertainty. For this example, the actual results show that the algorithm produces very reliable and stable calculation results.