Xueyi Li

Dr. Xueyi Li

orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
1 January 2013 in The Scientific World Journal
Verified
Journal Article
Open access
PDF file
XLXueyi Li
Xueyi Li
BHBinbing Huang
Binbing Huang
GMGuoying Ma
Guoying Ma
QZQingliang Zeng
Qingliang Zeng
The mechanism of cutting process of roadheader with cutting head was researched, and the influences of properties of coal and rock on cutting load were deeply analyzed. Aimed at the defects of traditional calculation method of cutting load on fully expressing the complex cutting process of cutting head, the method of finite element simulation was proposed to simulate the dynamic cutting process. Aimed at the characteristics of coal and rock which affect the cutting load, several simulations with different firmness coefficient were taken repeatedly, and the relationship between three‐axis force and firmness coefficient was derived. A comparative analysis of cutting pick load between simulation results and theoretical formula was carried out, and a consistency was achieved. Then cutting process with a total cutting head was carried out on this basis. The results show that the simulation analysis not only provides a reliable guarantee for the accurate calculation of the cutting head load and improves the efficiency of the cutting head cutting test but also offers a basis for selection of cutting head with different geological conditions of coal or rock.

25 March 2010 in Materialwissenschaft und Werkstofftechnik
Verified
Journal Article
Closed access
PDF file
XLXueyi Li
Xueyi Li
ZDZ. Du
Z. Du
HFH. Fu
H. Fu
ZFZ. Feng
Z. Feng
HZH. Zhao
H. Zhao

22 October 2015 in Materialwissenschaft und Werkstofftechnik
Verified
Journal Article
Closed access
PDF file
XLXueyi Li
Xueyi Li
JHJ. Hou
J. Hou
YQY. Qu
Y. Qu
HFH. Fu
H. Fu

1 January 2018 in Advances in Materials Science and Engineering
Verified
Journal Article
Open access
PDF file
GZGuopeng Zhang
Guopeng Zhang
XLXueyi Li
Xueyi Li
NWNingning Wang
Ningning Wang
QZQingliang Zeng
Qingliang Zeng
XSXiao Shen
Xiao Shen
There are some issues that should be solved like load shock, vibration, and uneven load distribution during transmission of involute spur gears. However, common modification methods such as axial modification as well as profile modification could not solve these problems once for all. Hence, a novel method of comprehensive modification was proposed, and the evaluation methodology of transmission performance was drawn up too. Changing modification parameters can control transmission performance of gear unit, which can generate many different modification ways. Besides, based on the orthogonal experiment method and evaluation methodology, optimal modification ways can be chosen for gear pairs working in different conditions. Taking a set of spur gear pair as an example, an ideal modification way was obtained. In addition, analysis results verified that conducting comprehensive modification could enhance the meshing performance once for all.

24 May 2024 in Electronics
Verified
Journal Article
Open access
PDF file
SDShuhui Ding
Shuhui Ding
ZGZhongyuan Guo
Zhongyuan Guo
XCXiaolong Chen
Xiaolong Chen
XLXueyi Li
Xueyi Li
FMFai Ma
Fai Ma
The online detection of surface defects in irregularly shaped products such as rawhide sticks, a kind of pet food, is still a challenge for the food industry. Developing deep learning-based detection algorithms requires a diverse defect database, which is crucial for artificial intelligence applications. Acquiring a sufficient amount of realistic defect data is challenging, especially during the beginning of product production, due to the occasional nature of defects and the associated costs. Herein, we present a novel image data augmentation method, which is used to generate a sufficient number of defect images. A Deep Convolution Generation Adversarial Network (DCGAN) model based on a Residual Block (ResB) and Hybrid Attention Mechanism (HAM) is proposed to generate massive defect images for the training of deep learning models. Based on a DCGAN, a ResB and a HAM are utilized as the generator and discriminator in a deep learning model. The Wasserstein distance with a gradient penalty is used to calculate the loss function so as to update the model training parameters and improve the quality of the generated image and the stability of the model by extracting deep image features and strengthening the important feature information. The approach is validated by generating enhanced defect image data and conducting a comparison with other methods, such as a DCGAN and WGAN-GP, on a rawhide stick experimental dataset.

12 July 2017 in International Journal of Emerging Technologies in Learning (iJET)
Verified
Journal Article
Open access
PDF file
XLXueyi Li
Xueyi Li
JWJunying Wei
Junying Wei
SDShuhui Ding
Shuhui Ding
QWQuanwei Wang
Quanwei Wang
Mechanical design course covers various contents, and most of them are complex theoretical knowledge. However, current teaching modes in China mainly combine textbook with PPT (PowerPoint) created in advance. This monotonous mode cause students to lose interests in their curriculum, and knowledge becomes difficult to gain. To improve teaching effectiveness, we propose a novel teaching mode by applying simulation technology to a particular mechanical design course. Using the chapter of gear transmission as an example, we also introduce a specific approach. Comparing traditional modes with the proposed mode, we demonstrate that combining simulation analysis technology with the content of mechanical design course can enrich the teaching process and improve students’ learning interests. The proposed approach can also help students analyze and solve problems with relevant knowledge and enhance their practical abilities. Thus, these students can satisfy the requirements of modern society for mechanical engineering graduates.