Deqiang Mu

Prof. Deqiang Mu

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
27 February 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RSruiyang Sun
ruiyang Sun
EZEnzhong Zhang
Enzhong Zhang
DMDeqiang Mu
Deqiang Mu
SJShijun Ji
Shijun Ji
ZZZiqiang Zhang
Ziqiang Zhang
ZFZheng Fu
Zheng Fu
In order to solve the problem of the traditional iterative closest point algorithm (ICPA), which requires a high initial position of point cloud and improves the speed and accuracy of point cloud registration, a new registration method is proposed in this paper. Firstly, the rough registration method is optimized. As for the extraction of the feature points, a new method of feature point extraction is adopted, which can better keep the features of the original point cloud. At the same time, the traditional point cloud filtering method is improved, and a voxel idea is introduced to filter the point cloud. The edge length data of the voxels is determined by the density, and the experimentally verified noise removal rates for the 3D cloud data are 95.3%, 98.6%, and 93.5%, respectively. Secondly, a precise registration method that combines the curvature feature and fast point feature histogram (FPFH) is proposed in the precise registration stage, and the algorithm is analyzed experimentally. Finally, the two point cloud data sets Stanford bunny and free-form surface are analyzed and verified, and it is concluded that this method can reduce the error by about 40.16% and 36.27%, respectively, and improve the iteration times by about 42.9% and 37.14%, respectively.

7 May 2024 in Measurement
Verified
Journal Article
Closed access
ZSZekai Si
Zekai Si
SSSumei Si
Sumei Si
DMDeqiang Mu
Deqiang Mu

15 April 2024 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
ZSZekai Si
Zekai Si
SSSumei Si
Sumei Si
DMDeqiang Mu
Deqiang Mu

1 October 2021 in Energies
Verified
Journal Article
Open access
PDF file
SXShen Xiao
Shen Xiao
HHHaitao Han
Haitao Han
YLYancheng Li
Yancheng Li
CYChang-xiang Yan
Chang-xiang Yan
DMDeqiang Mu
Deqiang Mu
In this paper, to improve the heat dissipation efficiency of a radiator for focal plane assemblies, a topology optimization method is introduced into the design process. For the realization of the optimization, an objective of maximal thermal stiffness concerning the radiator is formulated. The topology optimization is performed under the same mass constraint of 2.05 kg as the initial design. To improve the manufacturability of topology optimization result, an inverse design is conducted to reconstruct a new model. In transient thermal simulation, the average maximal temperature on focal plane assemblies with a reconstructed radiator is 8.626 °C, while the average maximal temperature with the initial design is 9.793 °C. Compared to the initial design, a decrease of 1.167 °C on maximal temperature is achieved. As the heat dissipation efficiency of the proposed radiator design is improved compared to the initial design, it is meaningful in future applications.

6 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
SSSumei Si
Sumei Si
DMDeqiang Mu
Deqiang Mu
HTHailiang Tang
Hailiang Tang
In grinding machining, monitoring grinding wheel wear is essential for ensuring process quality wear and reducing production costs. This paper presents a hybrid CBiGRUPE model to predict grinding wheel wear, which integrates the advantages of convolutional neural networks (CNNs), bidirectional gated recurrent unit (BiGRU), and the Performer encoder. Time-domain features are extracted from the spindle motor current signals of a surface grinding machine. The structure and hyperparameters of CBiGRUPE are optimized using Bayesian optimization. Experimental validation of the model demonstrates superior performance, with mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) values of 3.041, 3.927, and 0.920, respectively. Compared to models like CNN, BiGRU, and Transformer, the CBiGRUPE model offers more accurate and stable wear predictions. This paper also discusses the advantages and limitations of various models for estimating grinding wheel wear, emphasizing the effectiveness of the proposed approach. This study establishes a foundation for compensating wheel wear and accurately determining the optimal dressing time.

6 August 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SSSumei Si
Sumei Si
ZSZekai Si
Zekai Si
DMDeqiang Mu
Deqiang Mu
HTHailiang Tang
Hailiang Tang
The grinding wheel wear significantly affects machining efficiency and machining quality. Consequently, the grinding wheel wear assessment model PMSCNN derived from the Convolutional Neural Network (CNN) and the Transformer model is presented. Firstly, the grinding wheel spindle motor current signal is measured using a current sensor. Then, the time domain features are computed for the current signal obtained after median filtering. The importance of the features is analyzed using the gradient boosting regressor. The four features that have a relatively large impact on the model prediction results are selected based on the importance scores. Finally, the accuracy of the PMSCNN model is confirmed by employing these four features. It is found that the predicted values have a good similarity to the real wear trend, and average values of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination R2 of the cross-validated prediction findings are 3.028, 3.938 and 0.919. It is explained in detail that each module improves the model utilizing modular analysis. The PMSCNN model can extract wear-related patterns and information from the current signal and obtain good prediction accuracy.