Shao-Fei Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shao-Fei Ren has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- A-Man Zhang
Sanya Nanhai Innovation and Development Base of Harbin Engineering University
1 shared publication Chen-Xing Qu
Harbin Engineering University
1 shared publication- Guo-Fei Zhang1 shared publication
- Hao Chen1 shared publication
N. N. Liu
Harbin Engineering University College of Shipbuilding Engineering 145, Nantong Street, Harbin 150001, China
1 shared publicationP. Cui
Harbin Engineering University College of Shipbuilding Engineering 145, Nantong Street, Harbin 150001, China
1 shared publication
Latest Publications
- 1 August 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (8)
Bubble collapse patterns recognition and flow field prediction based on machine learning
A machine learning method is proposed to predict the collapse patterns and flow field state of underwater explosion bubbles subjected to the vertical sidewall and free surface, which can overcome the limitations of high costs of traditional experimental tests and long computation times of numerical simulations. The dataset was obtained by the boundary element method, including the cases of the bubble with different buoyancy parameters at different distances from the free surface and vertical sidewall. Due to the strong geometric nonlinearity of the bubble influenced by boundary, three classification models are adopted to identify the collapse patterns of bubbles, which are support vector machines, K nearest neighbor, and decision tree. Meanwhile, an ensemble learning (EL) model based on the three classification models is adopted to enhance the prediction accuracy. Furthermore, three regression models, which are deep neural network (DNN), extreme learning machine (ELM), and random forest (RF), were adopted and compared to predict flow field information around the bubble. The results show that EL exhibits better robustness to the distribution and proportion of samples when identifying collapse patterns. Meanwhile, compared with ELM and RF, DNN demonstrates stronger performance in capturing nonlinear relationships, especially in regions where the bubble curvature changes abruptly. Moreover, a learning rate decay strategy is proposed to effectively suppress the phenomenon of loss oscillation in the training process of DNN based on adaptive activation functions.
- 1 August 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (8)
Bubble collapse patterns recognition and flow field prediction based on machine learning
A machine learning method is proposed to predict the collapse patterns and flow field state of underwater explosion bubbles subjected to the vertical sidewall and free surface, which can overcome the limitations of high costs of traditional experimental tests and long computation times of numerical simulations. The dataset was obtained by the boundary element method, including the cases of the bubble with different buoyancy parameters at different distances from the free surface and vertical sidewall. Due to the strong geometric nonlinearity of the bubble influenced by boundary, three classification models are adopted to identify the collapse patterns of bubbles, which are support vector machines, K nearest neighbor, and decision tree. Meanwhile, an ensemble learning (EL) model based on the three classification models is adopted to enhance the prediction accuracy. Furthermore, three regression models, which are deep neural network (DNN), extreme learning machine (ELM), and random forest (RF), were adopted and compared to predict flow field information around the bubble. The results show that EL exhibits better robustness to the distribution and proportion of samples when identifying collapse patterns. Meanwhile, compared with ELM and RF, DNN demonstrates stronger performance in capturing nonlinear relationships, especially in regions where the bubble curvature changes abruptly. Moreover, a learning rate decay strategy is proposed to effectively suppress the phenomenon of loss oscillation in the training process of DNN based on adaptive activation functions.
- 1 May 2017
- Published by AIP Publishing in Physics of Fluids
- Vol. 29 (5)
Study on the interactions between two identical oscillation bubbles and a free surface in a tank
A boundary element method based on the incompressible potential flow theory is adopted to investigate the interaction between two identical oscillating bubbles and a free surface in a tank. An axisymmetric numerical model is established, and certain numerical techniques are proposed to address coefficient matrix singularity and fluid-structure intersection. Experiments with spark-generated bubbles in a cylindrical tank recorded by a high-speed camera are conducted, and the numerical results are validated. On this basis, a typical case of bubbles interacting with a free surface in a tank with relatively small inter-bubble and bubble-free surface distances is carefully studied. A crown-shaped water column at the free surface is observed both numerically and experimentally. The maximum volume of the lower bubble is found to be much larger than that of the upper one. The effects of the inter-bubble and bubble-wall distances on bubble dynamics and free surface motion are analyzed. The results can provide a useful reference for underwater explosion experiments in the confined fluid field.
- 1 May 2017
- Published by AIP Publishing in Physics of Fluids
- Vol. 29 (5)
Study on the interactions between two identical oscillation bubbles and a free surface in a tank
A boundary element method based on the incompressible potential flow theory is adopted to investigate the interaction between two identical oscillating bubbles and a free surface in a tank. An axisymmetric numerical model is established, and certain numerical techniques are proposed to address coefficient matrix singularity and fluid-structure intersection. Experiments with spark-generated bubbles in a cylindrical tank recorded by a high-speed camera are conducted, and the numerical results are validated. On this basis, a typical case of bubbles interacting with a free surface in a tank with relatively small inter-bubble and bubble-free surface distances is carefully studied. A crown-shaped water column at the free surface is observed both numerically and experimentally. The maximum volume of the lower bubble is found to be much larger than that of the upper one. The effects of the inter-bubble and bubble-wall distances on bubble dynamics and free surface motion are analyzed. The results can provide a useful reference for underwater explosion experiments in the confined fluid field.