Yan Li

Dr. Yan Li


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
15 May 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
WCWei Cheng
Wei Cheng
FGFeng Gao
Feng Gao
YLYan Li
Yan Li
HZHang Zhang
Hang Zhang
WLWenqiang Li
Wenqiang Li
KWKejun Wu
Kejun Wu
The evolution of the automotive industry demands gearboxes that offer improved specifications in terms of power transfer and shifting performance. The high-quality standards required for transmission component manufacturing processes render it necessary to measure shaft parts. To realize online diameter inspection of shaft parts in the gearbox production line, a machine vision-based non-contact metrology method with Canny–Steger subpixel edge detection is proposed. The interference background was separated from the measured target using ROI technology. Morphological closure operations and bilateral filtering preprocessing were performed on the collected images to achieve filtering and denoising, respectively. With the extraction of pixel-level edges using the Canny operator as a basis, the Steger algorithm was used to detect the subpixel edges. The edges and normal directions are derived from the Hessian matrix. Subsequently, Taylor polynomials are applied to the pixel grayscale in the normal direction to obtain the grayscale distribution function, the extreme values of which are solved to obtain the subpixel edge point positions. The fitting data are employed to evaluate the machining errors of the parts, significantly reducing redundant calculations in the Steger algorithm process and improving the detection speed. The proposed method was validated through synthetic and real experiments. Experimental results demonstrate that the measurement method proposed in this paper can rapidly measure shaft parts. Its diameter measurement accuracy can reach 3 μm, and the repetitive measurement accuracy can reach 2 μm. Compared with pixel-level edge detection, the accuracy has been improved by 60%.

27 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
LLLiu Liu
Liu Liu
FGFeng Gao
Feng Gao
YLYan Li
Yan Li
Owing to the remarkable development of deep learning algorithms, defect detection techniques based on deep neural networks have been extensively applied in industrial production. Most existing surface defect detection models assign equal costs to the classification errors among different defect categories but do not strictly distinguish them. However, various errors can generate a great discrepancy in decision risk or classification costs and then produce a cost-sensitive issue that is crucial to the manufacturing process. To address this engineering challenge, we propose a novel supervised classification cost-sensitive learning method (SCCS) and apply it to improve YOLOv5 as CS-YOLOv5, where the classification loss function of object detection was reconstructed according to a new cost-sensitive learning criterion explained by a label–cost vector selection method. In this way, the classification risk information from a cost matrix is directly introduced into the detection model and fully exploited in training. As a result, the developed approach can make low-risk classification decisions for defect detection. It is applicable for direct cost-sensitive learning based on a cost matrix to implement detection tasks. Using two datasets of a painting surface and a hot-rolled steel strip surface, our CS-YOLOv5 model outperforms the original version with respect to cost under different positive classes, coefficients, and weight ratios, but also maintains effective detection performance measured by mAP and F1 scores.

20 January 2025 in Machines
Verified
Journal Article
Open access
PDF file
CWChangxu Wang
Changxu Wang
YLYan Li
Yan Li
FGFeng Gao
Feng Gao
KWKejun Wu
Kejun Wu
KYKan Yin
Kan Yin
YXYunjiao Xu
Yunjiao Xu
The high-performance alloy, 304 stainless steel, is widely used in various industries. However, its material properties lead to severe tool wear during milling processes, significantly increasing milling force and adversely impacting machining quality and efficiency. Consequently, an accurate milling-force model is crucial for guiding the formulation and optimization of machining parameters. This paper presents a milling-force prediction model for 304 stainless steel that incorporates the effect of tool wear, based on the mechanistic modeling approach. Side-milling experiments on 304 stainless steel were conducted to analyze the relationship between milling force and tool wear, identify the model coefficients, and validate the prediction accuracy of the milling-force model. The results demonstrate that the model accurately predicts the milling forces of worn tools while side milling 304 stainless steel under various machining parameters and tool wear conditions.

20 February 2025 in Journal of Applied Polymer Science
Verified
Journal Article
Closed access
YLYan Li
Yan Li
YYYan Yang
Yan Yang
FGFeng Gao
Feng Gao
FZFan Zhou
Fan Zhou
WCWei Cheng
Wei Cheng

19 October 2022 in Nanotechnology
Verified
Journal Article
Closed access
FZFan Zhou
Fan Zhou
JWJiyuan Wang
Jiyuan Wang
YTYimei Tang
Yimei Tang
SLShu Liu
Shu Liu
YDYanrui Du
Yanrui Du
FGFeng Gao
Feng Gao
In this study, reduced graphene oxide (rGO) were subject to ultrasonic treatment to acquire varied morphologies, and the enzymatic glucose sensors were constructed by coating the rGO onto indium tin oxide electrodes and physically linking glucose oxidase to the rGO coatings. The effects of the surface morphologies of the rGO coatings on the interfacial characteristics and the electro-catalytic capacity of the enzymatic glucose sensors were systematically investigated. It turns out that, the rGO coating with a rough surface is more hydrophilic, and exhibits uniform glucose oxidase adsorption and higher electron migration rate at the solid/liquid interface between the analytical liquid and the working electrode. As a result, the corresponding glucose sensor shows excellent electro-catalytic capacity towards glucose with a broader linear range of 0–10.0 mM, a higher sensitivity of 38.9 μA·mM−1·cm−2, and a lower detection limit of 0.1 μM (signal-to-noise ratio of 3). Additionally, the as-prepared glucose sensor exhibits excellent accuracy for detecting actual blood samples as well as superior resistance to interference from other substances (such as L-phenylalanine, urea, ascorbic acid, uric acid, NaCl, and KCl). These results establish the theoretical and experimental foundation for the application of rGO coating in the field of biosensors.

19 August 2025 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
YTYiran Tang
Yiran Tang
FGFeng Gao
Feng Gao
YLYan Li
Yan Li
YFYuanhao Fan
Yuanhao Fan
ZLZhangyun Li
Zhangyun Li