Yunfeng LI

Dr. Yunfeng LI


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 November 2017 in Circuit World
Verified
Journal Article
Closed access
YLYunfeng LI
Yunfeng LI
SLShengyang Li
Shengyang Li
Purpose: The purpose of this paper is to propose a defect detection method of bare printed circuit boards (PCB) with high accuracy. Design/methodology/approach: First, bilateral filtering of the PCB image was performed in the uniform color space, and the copper-clad areas were segmented according to the color difference among different areas. Then, according to the chaotic characteristics of the spatial distribution and the gradient direction of the edge pixels on the boundary of the defective areas, the feature vector, which evaluates quantitatively the significant degree of the defect characteristics by using the gradient direction information entropy and the uniform local binary patterns, was constructed. Finally, support vector machine classifier was used for the identification and localization of the PCB defects. Findings: Experimental results show that the proposed algorithm can accurately detect typical defects of the bare PCB, such as short circuit, open circuit, scratches and voids. Originality/value: Considering the limitations of describing all kinds of defects on bare PCB by using single kind of feature, the gradient direction information entropy and the local binary patterns were fused to build a feature vector, which evaluates quantitatively the significant degree of the defect features.

6 April 2016 in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
Verified
Journal Article
Closed access
YLYunfeng LI
Yunfeng LI
DJDi Jiang
Di Jiang
For the two failure modes of a three-row roller slewing bearing, ring fracture and raceway spalling, a method for checking the strength of a slewing bearing through finite element analysis is proposed. This method calculates the internal stress distribution of the bearing rings by using the mixed finite element model with both solid elements and spring elements of the slewing bearing assembly and checks the bearing structural strength by using the maximum internal stress of the bearing rings. The method also calculates the contact stress between the roller and raceways by using the entity contact model between the roller and the raceways; the obtained maximum contact stress is used to check the contact strength of the slewing bearing. The proposed mixed finite element model considers the structural deformation of the bearing rings, and the calculated results can reflect the real situation more accurately than the traditional analytical model with the hypothesis of rigid ring. The proposed method also avoids the solution problem, which has large-scale calculation and difficulty of convergence of the entity finite element model of a slewing bearing, and the calculation efficiency is improved effectively. The calculated results by mixed finite element model are consistent with the failure mode of this type of slewing bearing in engineering practice.

1 January 2022 in Science Progress
Verified
Journal Article
Open access
YLYunfeng LI
Yunfeng LI
PZPengyue Zhang
Pengyue Zhang
Considering that the distinctions among static hand gestures are the difference between fingers sticking out, a method of grouping and classifying hand gestures step by step by using the information of the quantity, direction, position and shape of the outstretched fingers was proposed this paper. Firstly, the gesture region was segmented by using the skin color information of the hand, and the gesture direction was normalized by using the direction information of the gesture contour lines. Secondly, the finger was segmented one by one by using convex decomposition in the hand gesture image based on the convex characteristic of the gesture shape. Thirdly, the features of quantity, direction, position and shape of the segmented fingers were extracted. Lastly, a hierarchical decision classifier embedded with deep sparse autoencoders was constructed. The quantity of fingers was used to divide the gesture images into groups first, then the direction, position and shape features of the fingers were used to subdivide and recognize gestures within each group. The experimental results show that the proposed method is robust as lighting, direction and scale changes and significantly superior to the traditional method both in the recognition rate and the recognition stability.

23 June 2025 in Sensors
Verified
Journal Article
Open access
PDF file
FLFan Li
Fan Li
YLYunfeng LI
Yunfeng LI
DWDongfeng Wang
Dongfeng Wang
To address the challenge of incomplete fault feature extraction in rolling bearing fault diagnosis under small-sample conditions, this paper proposes a Temporal-Graph Convolutional Fusion Network (T-GCFN). The method enhances diagnostic robustness through collaborative extraction and dynamic fusion of features from time-domain and frequency-domain branches. First, Variational Mode Decomposition (VMD) was employed to extract time-domain Intrinsic Mode Functions (IMFs). These were then input into a Temporal Convolutional Network (TCN) to capture multi-scale temporal dependencies. Simultaneously, frequency-domain features obtained via Fast Fourier Transform (FFT) were used to construct a K-Nearest Neighbors (KNN) graph, which was processed by a Graph Convolutional Network (GCN) to identify spatial correlations. Subsequently, a channel attention fusion layer was designed. This layer utilized global max pooling and average pooling to compress spatio-temporal features. A shared Multi-Layer Perceptron (MLP) then established inter-channel dependencies to generate attention weights, enhancing critical features for more complete fault information extraction. Finally, a SoftMax classifier performed end-to-end fault recognition. Experiments demonstrated that the proposed method significantly improved fault recognition accuracy under small-sample scenarios. These results validate the strong adaptability of the T-GCFN mechanism.

12 May 2022 in Advances in Mechanical Engineering
Verified
Journal Article
Open access
YLYunfeng LI
Yunfeng LI
YGYuanan Gao
Yuanan Gao
In order to accurately understand the internal loading state of the single-row tapered roller bearings doubly supporting the main shaft of wind turbine, a 5-DOF mechanical model of such bearing combination in wind turbine was established which considered the axial preload, bearing ring tilt, and roller crown. The positions of the points on the bearing raceways were described mathematically in the Cartesian coordinate system, and the mathematical relationship between the roller-raceway contact deformations and the bearing ring displacements was derived. The effect of bearing ring tilt caused by external loads on the contact load distributions along rollers was considered by dividing the rollers into laminae. The contact stress distribution between roller and raceway was obtained by iterative calculation of the finite length line contact model. The RMSE of the roller load distributions of the upwind bearing and the downwind bearing is 2.25 kN and 3.02 kN respectively. The obtained smallest size necessary for the roller laminae is 1.25% of the roller length. The bearing ring tilt will cause uneven contact load distribution along the roller, and modification of the roller profile improves the load and stress distribution. The machining error leads to the unbalanced contact stress distribution along the roller.

5 October 2015 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
YLYunfeng LI
Yunfeng LI
DJDi Jiang
Di Jiang
Carrying capacity is the most important performance index for slewing bearings. Maximizing the carrying capacity of slewing bearing is one pursuing goal for the bearing designer; this is usually realized by optimizing the design parameters. A method of analyzing the carrying capacity of double-row four-point contact ball slewing bearing by using dynamic carrying capacity surfaces was proposed in this paper. Based on the dynamic load carrying capacity surface of the slewing bearing, the effect of changes of the bearing design parameters, such as axial clearance, raceway groove radius coefficient, and contact angle, on the dynamic carrying capacity of the slewing bearing was researched; the trend and the degree of the effect of the micro changes of the bearing design parameters on the dynamic load carrying capacity of the bearing were discussed, and the results provide the basis for optimizing the design parameter of this type of slewing bearing.