Wenrui 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
Wenrui Li has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Xiangluan Dong
Shenyang Institute of Engineering
3 shared publicationsBo Sun
State Grid Chaoyang Electric Power Supply Company, State Grid Liaoning Electric Power Supply Co., Ltd
2 shared publications- Dawei Li
Huazhong University of Science and Technology
2 shared publications - Caiyun Chen
Dept. of Intelligent Science and Technology, Xiamen University Tan Kah kee College, China
1 shared publication Fushuai Wang
Faculty of Materials and Engineering, Shenyang Aerospace University, Shenyang, Liaoning, 110136, China
1 shared publicationGuoli Xuan
State Grid Chaoyang Electric Power Supply Company, State Grid Liaoning Electric Power Supply Co., Ltd
1 shared publication
Latest Publications
- Open Access
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1920 (1) , 012106
Study on Shot peening Coverage of Metal Surface Based on Deep Learning
The surface shot peening coverage of industrial parts will affect the performance of the parts. Therefore, it is of great significance for the identification of the metal surface shot peening coverage area and the uncovered area for the metallurgical process. This paper uses the idea of image semantic segmentation, using CCD industrial camera to select and shoot the metal surface of 67%,89% and 98% shot peening coverage. Based on UNet and UNet++ model, the shot peening area is segmented. After training 200 epoch, the network converges and the training accuracy can reach 98.45%. Comparing the two kinds of network training results, using the UNet++ model with good results to predict the selected 18 metal surfaces, the proportion of shot peening coverage area and uncovered area is counted, and then the K-means clustering algorithm is used to classify. The classification accuracy can reach 100%.
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1920 (1) , 012106
Open AccessStudy on Shot peening Coverage of Metal Surface Based on Deep Learning
The surface shot peening coverage of industrial parts will affect the performance of the parts. Therefore, it is of great significance for the identification of the metal surface shot peening coverage area and the uncovered area for the metallurgical process. This paper uses the idea of image semantic segmentation, using CCD industrial camera to select and shoot the metal surface of 67%,89% and 98% shot peening coverage. Based on UNet and UNet++ model, the shot peening area is segmented. After training 200 epoch, the network converges and the training accuracy can reach 98.45%. Comparing the two kinds of network training results, using the UNet++ model with good results to predict the selected 18 metal surfaces, the proportion of shot peening coverage area and uncovered area is counted, and then the K-means clustering algorithm is used to classify. The classification accuracy can reach 100%.
- 2 October 2019
- Published by Springer Nature
- p. 998-1008
Waveform Improvement Analysis of Bridge Rectifier Circuit in Energy Internet Based on Full Feedback Regulation
- 2 October 2019
- Published by Springer Nature
- p. 998-1008
Waveform Improvement Analysis of Bridge Rectifier Circuit in Energy Internet Based on Full Feedback Regulation
- 2 October 2019
- Published by Springer Nature
- p. 147-155
Optimization of UPS Output Waveform Based on Single-Phase Bridge Inverter
- 2 October 2019
- Published by Springer Nature
- p. 147-155
Optimization of UPS Output Waveform Based on Single-Phase Bridge Inverter
- 2 October 2019
- Published by Springer Nature
- p. 1026-1035
Adjusting Control Method of AC Output Synchronization Based on Phase Lock Technology
- 2 October 2019
- Published by Springer Nature
- p. 1026-1035
Adjusting Control Method of AC Output Synchronization Based on Phase Lock Technology
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
3D Outdoor Positioning Based on RSSI
As a key feature of wireless sensor networks, location-based services find wide applications in social networks, e.g., emergency, navigation and marketing. However, most positioning algorithms aim at two-dimensional indoor applications and few have focused on three-dimensional (3D) outdoor applications. To fill in this gap, this paper develops two 3D positioning algorithms based on received signal strength indicator (RSSI). In particular, after obtaining coarse estimates of user position based on least squares (LS) algorithm, the weighted centroid algorithm (WCA) or particle swarm optimization (PSO) is further exploited to refine the estimate. Monte-Carlo simulation and field test results demonstrate that the LS-PSO algorithm outperforms the LS-WCA, with the accuracy of positioning no worse than 5 meters and the relative error in each spatial dimension smaller than 2%.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
3D Outdoor Positioning Based on RSSI
As a key feature of wireless sensor networks, location-based services find wide applications in social networks, e.g., emergency, navigation and marketing. However, most positioning algorithms aim at two-dimensional indoor applications and few have focused on three-dimensional (3D) outdoor applications. To fill in this gap, this paper develops two 3D positioning algorithms based on received signal strength indicator (RSSI). In particular, after obtaining coarse estimates of user position based on least squares (LS) algorithm, the weighted centroid algorithm (WCA) or particle swarm optimization (PSO) is further exploited to refine the estimate. Monte-Carlo simulation and field test results demonstrate that the LS-PSO algorithm outperforms the LS-WCA, with the accuracy of positioning no worse than 5 meters and the relative error in each spatial dimension smaller than 2%.
- 14 July 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Magnetics
- Vol. 52 (12) , 1-7
Analysis on Axial End Flux Leakage and Resonance Characteristic of TFPM Linear Generator for Thermoacoustic Electric Generation System
According to 3-D magnetic circuit of the transverse flux permanent magnet linear generator (TFPMLG), the area of end flux leakage is divided into several zones, and the analytical expression of axial end flux leakage is derived through conformal transformation. The linear machine equivalent stiffness factor is derived through the calculation of detent force. Combining the linear machine with mechanical resonance property of thermoacoustic electric generation system, the computing method on resonance spring parameters of the system is provided. A 3-D finite-element model of TFPMLG is built to analyze the flux leakage distribution. The experimental results of the linear machine verified the validity of detent force and stiffness factor theoretical derivation; the research on axial end flux leakage and resonance spring parameters provides a valuable reference to other types of linear machines.
- 14 July 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Magnetics
- Vol. 52 (12) , 1-7
Analysis on Axial End Flux Leakage and Resonance Characteristic of TFPM Linear Generator for Thermoacoustic Electric Generation System
According to 3-D magnetic circuit of the transverse flux permanent magnet linear generator (TFPMLG), the area of end flux leakage is divided into several zones, and the analytical expression of axial end flux leakage is derived through conformal transformation. The linear machine equivalent stiffness factor is derived through the calculation of detent force. Combining the linear machine with mechanical resonance property of thermoacoustic electric generation system, the computing method on resonance spring parameters of the system is provided. A 3-D finite-element model of TFPMLG is built to analyze the flux leakage distribution. The experimental results of the linear machine verified the validity of detent force and stiffness factor theoretical derivation; the research on axial end flux leakage and resonance spring parameters provides a valuable reference to other types of linear machines.