Lei Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lei Han has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Taochuan Zhang
College of Mechanical and Electrical Engineering, Foshan Polytechnic, Foshan, China
2 shared publications Cheng Lin
School of Automobile and Transportation Engineering Guangdong Polytechnic Normal University Guangzhou China
1 shared publication- Chunmei Duan
School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang, China
1 shared publication - Chunmei Duan
Guangdong Engineering Technology Research Center of Ocean Equipment and Manufacturing, Zhanjiang, 524088, China
1 shared publication - Fujun Gou
Key Laboratory of Radiation Physics and Technology of the Ministry of Education, Institute of Nuclear Science and Technology, Sichuan University, Chengdu 610064, China
1 shared publication - Huilin Tan
College of Information Science and Engineering, Shaoyang University, Shaoyang, China
1 shared publication
Latest Publications
- Open Access
- 7 August 2025
- Published by MathDoc/Centre Mersenne in Comptes Rendus Mécanique
- Vol. 353 (G1) , 953-988
Predicting stress–strain constitutive relationships: a deep learning approach based on multi-head attention mechanism and long short-term memory networks
The stress–strain constitutive relationship of materials is a critical indicator for assessing their mechanical properties and serves as a vital bridge connecting microstructures with macroscopic mechanical behaviors. This study focuses on 106 metal alloy materials, employing the finite element method to establish uniaxial tensile numerical models, thereby simulating and obtaining a comprehensive dataset of stress–strain relationship curves. Innovatively, this research proposes a MA-LSTM-DLnet prediction model that integrates multi-head attention mechanisms with long short-term memory networks, based on deep learning methodologies. The model utilizes conventional key parameters such as material strain, yield strength, tensile strength, elastic modulus, density, strength coefficient, and stress as input features to construct a multi-dimensional training dataset. It particularly explores the learning capabilities and predictive performance of the MA-LSTM-DLnet model under both complete and limited feature datasets. The results demonstrate that the trained MA-LSTM-DLnet model can accurately predict the stress–strain constitutive relationship curves of new materials by merely acquiring conventional physical parameters like yield strength, tensile strength, and elastic modulus, with a similarity exceeding 95% compared to test data. Compared to traditional empirical formulas and numerical simulation methods, the main innovation of this study lies in eliminating key parameters that are difficult to determine in mathematical models (such as the strength coefficient in the Ludwik isotropic hardening model), significantly reducing repetitive work dependent on experiments to obtain constitutive relationships, and achieving efficient and precise material performance evaluation.
- 7 August 2025
- Published by MathDoc/Centre Mersenne in Comptes Rendus Mécanique
- Vol. 353 (G1) , 953-988
Open AccessPredicting stress–strain constitutive relationships: a deep learning approach based on multi-head attention mechanism and long short-term memory networks
The stress–strain constitutive relationship of materials is a critical indicator for assessing their mechanical properties and serves as a vital bridge connecting microstructures with macroscopic mechanical behaviors. This study focuses on 106 metal alloy materials, employing the finite element method to establish uniaxial tensile numerical models, thereby simulating and obtaining a comprehensive dataset of stress–strain relationship curves. Innovatively, this research proposes a MA-LSTM-DLnet prediction model that integrates multi-head attention mechanisms with long short-term memory networks, based on deep learning methodologies. The model utilizes conventional key parameters such as material strain, yield strength, tensile strength, elastic modulus, density, strength coefficient, and stress as input features to construct a multi-dimensional training dataset. It particularly explores the learning capabilities and predictive performance of the MA-LSTM-DLnet model under both complete and limited feature datasets. The results demonstrate that the trained MA-LSTM-DLnet model can accurately predict the stress–strain constitutive relationship curves of new materials by merely acquiring conventional physical parameters like yield strength, tensile strength, and elastic modulus, with a similarity exceeding 95% compared to test data. Compared to traditional empirical formulas and numerical simulation methods, the main innovation of this study lies in eliminating key parameters that are difficult to determine in mathematical models (such as the strength coefficient in the Ludwik isotropic hardening model), significantly reducing repetitive work dependent on experiments to obtain constitutive relationships, and achieving efficient and precise material performance evaluation.
- Open Access
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 134312-134324
Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
Product quality control is an important component of PET preform production process. In order to improve the accuracy and reliability of PET preform detection, reduce the cost of product quality defects, and improve the overall level of product quality, this paper proposes a surface defect detection method for PET preform based on multi-scale feature fusion. Multi-scale features fusion combines features from different scales to produce more accurate and robust feature representations, which improve the accuracy, stability and adaptability of PET preform detection model. This feature processing model constructs a three-branch network, generating feature maps of different sizes. Then, the low-level feature, the middle-level feature and the high-level feature are fused to obtain a PET preform feature map based on multi-scale feature fusion by using a maximum value fusion strategy. The original image and feature map of the PET preform are respectively input into the deep convolutional neural network for feature extraction and fusion. And finally the fusion features are input into the ECOC-SVM to achieve surface defect classification of the PET preform. The machine vision platform is designed for collecting and detecting PET preform data. By importing the model designed in this paper, surface defect recognition and defect category judgment of PET preform can be achieved. Through experimental data analysis, the higher testing detection accuracy of this method is 98.8%, with an average testing accuracy of 97.1%.
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 134312-134324
Open AccessResearch on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
Product quality control is an important component of PET preform production process. In order to improve the accuracy and reliability of PET preform detection, reduce the cost of product quality defects, and improve the overall level of product quality, this paper proposes a surface defect detection method for PET preform based on multi-scale feature fusion. Multi-scale features fusion combines features from different scales to produce more accurate and robust feature representations, which improve the accuracy, stability and adaptability of PET preform detection model. This feature processing model constructs a three-branch network, generating feature maps of different sizes. Then, the low-level feature, the middle-level feature and the high-level feature are fused to obtain a PET preform feature map based on multi-scale feature fusion by using a maximum value fusion strategy. The original image and feature map of the PET preform are respectively input into the deep convolutional neural network for feature extraction and fusion. And finally the fusion features are input into the ECOC-SVM to achieve surface defect classification of the PET preform. The machine vision platform is designed for collecting and detecting PET preform data. By importing the model designed in this paper, surface defect recognition and defect category judgment of PET preform can be achieved. Through experimental data analysis, the higher testing detection accuracy of this method is 98.8%, with an average testing accuracy of 97.1%.
- 18 October 2023
- Published by Wiley in Polymers for Advanced Technologies
- Vol. 35 (1)
Long‐term application of core spun fabric strain sensor manufactured via dip coating for large deformation monitoring
In this study, we fabricated strain sensors using a dip‐coating method on spandex fabric utilizing a mixed solvent of tetrahydrofuran/N,N‐dimethylformamide and carbon black. Scanning electron microscopy images demonstrated a positive correlation between the amount of adhered Carbon black (CB) particles and coating time. Thermogravimetric analysis revealed the thermodynamic behavior of the sensor as gradually heated up to 650°. Mechanical analysis indicated that the reported sensors exhibited a higher elongation at break compared to the original spandex fabric, but with a slight decrease in strength. Moreover, the dissipated energy of each fabric shows a stabilizing tendency after 10 cycles during a 300% stretching‐releasing cyclic tests, where no significant changes observed until the 50th cycle, demonstrating an excellent mechanical repeatability of the fabric sensors. In terms of sensing performance, the sensor exhibited a high sensing range of up to 300%, with the maximum sensitivity reaching 16. Furthermore, we conducted cyclic stretching tests up to 200% strain to characterize the long‐term stability of the fabric's sensing ability. The results demonstrated that our reported method enables a low‐cost and efficient fabrication of sensors with excellent performance.
- 18 October 2023
- Published by Wiley in Polymers for Advanced Technologies
- Vol. 35 (1)
Long‐term application of core spun fabric strain sensor manufactured via dip coating for large deformation monitoring
In this study, we fabricated strain sensors using a dip‐coating method on spandex fabric utilizing a mixed solvent of tetrahydrofuran/N,N‐dimethylformamide and carbon black. Scanning electron microscopy images demonstrated a positive correlation between the amount of adhered Carbon black (CB) particles and coating time. Thermogravimetric analysis revealed the thermodynamic behavior of the sensor as gradually heated up to 650°. Mechanical analysis indicated that the reported sensors exhibited a higher elongation at break compared to the original spandex fabric, but with a slight decrease in strength. Moreover, the dissipated energy of each fabric shows a stabilizing tendency after 10 cycles during a 300% stretching‐releasing cyclic tests, where no significant changes observed until the 50th cycle, demonstrating an excellent mechanical repeatability of the fabric sensors. In terms of sensing performance, the sensor exhibited a high sensing range of up to 300%, with the maximum sensitivity reaching 16. Furthermore, we conducted cyclic stretching tests up to 200% strain to characterize the long‐term stability of the fabric's sensing ability. The results demonstrated that our reported method enables a low‐cost and efficient fabrication of sensors with excellent performance.
- 1 October 2017
- Published by Elsevier in Fusion Engineering and Design
- Vol. 121, 308-312
Enhanced erosion of lithium surface with capillary porous system
- 1 October 2017
- Published by Elsevier in Fusion Engineering and Design
- Vol. 121, 308-312
Enhanced erosion of lithium surface with capillary porous system