Beizhi Li

Dr. Beizhi Li

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
29 April 2019 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
WGWeicheng Guo
Weicheng Guo
BLBeizhi Li
Beizhi Li
SSShouguo Shen
Shouguo Shen
QZQinzhi Zhou
Qinzhi Zhou

2 December 2019 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
SSShouguo Shen
Shouguo Shen
BLBeizhi Li
Beizhi Li
WGWeicheng Guo
Weicheng Guo

5 April 2019 in Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
Verified
Journal Article
Closed access
PDF file
WGWeicheng Guo
Weicheng Guo
BLBeizhi Li
Beizhi Li
QZQinzhi Zhou
Qinzhi Zhou
Grinding wheel condition is considered as the key factor affecting grinding performance, and therefore, accurate monitoring of wheel wear is necessary to prevent the deterioration of part quality. An intelligent wheel wear monitoring system is introduced in this article to realize processing of grinding signal, extraction of signal features, selection of optimal feature subset, and prediction of wheel wear. Physical information generated during the grinding of C-250 maraging steel is collected by a dynamometer, accelerometer, and acoustic emission sensor, and a large quantity of features in time domain and frequency domain are extracted from the processed grinding signals. To reduce feature redundancy and increase relevancy of feature to wheel wear, a two-stage feature selection approach combining filter and wrapper framework is proposed. The filter preselects individual features by minimum Redundancy Maximum Relevance method, while the wrapper evaluates different feature subsets by the model performance. A deep learning network structure named Long Short-Term Memory network is adopted to develop the wheel wear monitoring model and is compared with a conventional machine learning algorithm, Random Forest. The results have shown that the two-stage feature selection method is able to provide the globally optimal feature subset for the model. Long Short-Term Memory model achieves an R2 of 0.994 and a root-mean-square error of 0.240 with four features, while Random Forest model obtains an R2 of 0.980 and a root-mean-square error of 0.463 with seven features, which indicates that Long Short-Term Memory model is capable of predicting wheel wear more accurately even with less features.

7 December 2018 in Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
Verified
Journal Article
Closed access
JPJingzhu Pang
Jingzhu Pang
Chongjun WuChongjun Wu
Chongjun Wu
YSYiming Shen
Yiming Shen
SLSiqi Liu
Siqi Liu
QWQingxia Wang
Qingxia Wang
BLBeizhi Li
Beizhi Li
The grinding heat is generally partitioned into the workpiece, wheel, chips and fluid in grinding process. The total amount of heat flux entering into the workpiece greatly affects the final workpiece surface temperature, which may cause undesirable workpiece burn. Moreover, the variable grinding chip thickness and fluid injection speed along the grinding contact zone could substantially change the specific energy and the shape of the heat source correspondingly. In this article, a Weibull heat flux distribution model for both dry and wet grinding temperature prediction was proposed by analyzing two key parameters: energy partition Rw and shape parameter k. The value of Rw was obtained by considering the real contact length, the active grits number and the average grit radius r0 on the basis of traditional formulas. The relationship between shape parameters k and useful flow was established by a FLUENT simulation of the convective grinding fluid applied in grinding contact zone with wheel-workpiece minimum clearance. The grinding temperature and grinding force experiments were conducted on a grinding machine MGKS1332/H to validate the proposed heat flux model. The calculated workpiece surface temperature distribution was obtained by using the experimental heat flux obtained by the reverse algorithm, and the error between calculated temperature and experimental temperature was analyzed. With the monitored force signals and the proposed temperature prediction model, the grinding temperature for both dry and wet grinding can be predicted, which will be helpful to the optimization and control of temperature in grinding process.

30 March 2019 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
SSShouguo Shen
Shouguo Shen
BLBeizhi Li
Beizhi Li
WGWeicheng Guo
Weicheng Guo

13 July 2017 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
WLWei Li
Wei Li
BLBeizhi Li
Beizhi Li
JYJianguo Yang
Jianguo Yang