Tianle Yin

Tianle Yin

Auto-generated profile, based on publicly available information

Tianle Yin

College of Sciences, Inner Mongolia University of Technology, Hohhot, People’s Republic of China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 August 2023 in Physics of Fluids
Verified
Journal Article
Open access
PDF file
TYTianle Yin
Tianle Yin
YJYucheng Ji
Yucheng Ji
JPJing Pang
Jing Pang
In this article, the variable coefficient (2 + 1)-dimensional extended cylindrical Kadomtsev–Petviashvili (cKP) equation describing Rossby waves was derived from the quasi-geostrophic potential vorticity equation. It is difficult for the variable coefficient cKP equation with dissipation to calculate the exact solution. For obtaining the exact solution, a new transformation was constructed for the first time to reduce the extended cKP equation to the extended KP equation. We emphasize that the exact solution, and not just approximate solution, in Rossby waves flow field can be obtained when dissipation is included. The exact lump and interaction solutions with dissipative effect are given according to the modified Hirota bilinear method, and physics for the evolution of Rossby waves is analyzed based on the obtained solutions. When the dissipative parameter μ0 increases, the structure of the amplitude A changes in the spatial scale y. And when the dissipative parameter increases to a certain value, the structure of Rossby waves tends to be stable. It is pointed out that the dissipative parameter μ0 determines not only the amplitude A of Rossby waves but also structures of Rossby waves flow field, with μ0 acting on the spatial scale y and the timescale t.

9 January 2025 in Chinese Journal of Physics
Verified
Journal Article
Closed access
TYTianle Yin
Tianle Yin
HDHui Dong
Hui Dong
WWWeiqing Wang
Weiqing Wang
JPJing Pang
Jing Pang

1 September 2024 in Chaos: An Interdisciplinary Journal of Nonlinear Science
Verified
Journal Article
Closed access
PDF file
TYTianle Yin
Tianle Yin
YDYajun Du
Yajun Du
WWWeiqing Wang
Weiqing Wang
JPJing Pang
Jing Pang
ZYZhenya Yan
Zhenya Yan
Starting from the classical quasi-geostrophic potential vorticity equation with equal depth two-layer fluid, the coupled cylindrical Kadomtsev–Petviashvili (KP) equations with variable coefficients for Rossby waves are studied. To be more general, the phase velocity is considered an indefinite integral about time and improves the analysis procedure. So the variable coefficients are obtained and some previous studies are reasonably explained. The cylindrical wave theory is therewith utilized to reduce the coupled cylindrical KP equations with variable coefficients, and based on the modified Hirota bilinear method, the lump solutions and interaction solutions are found. Through numerical simulations, the Rossby lump waves on both sides of the y axis move closer to the center, and their amplitude gradually decreases and tends to flatten with the generalized Rossby parameter growth. In the Rossby waves flow field, the dipole structures propagate to the east and lead to the appearance of the compress phenomenon during barotropic–baroclinic interaction. It is possibly useful for further theoretical research on atmospheric phenomena.

1 March 2025 in Physics of Fluids
Verified
Journal Article
Closed access
WWWeiqing Wang
Weiqing Wang
TYTianle Yin
Tianle Yin
JPJing Pang
Jing Pang
Computational fluid dynamics (CFD) is crucial in various fields but is computationally expensive and time-consuming, largely due to the complex nonlinear partial differential terms that complicate its equations. A data-driven surrogate model integrating Convolutional Neural Networks and Transformer, named UTransNet, is proposed to effectively approximate solutions for a two-dimensional incompressible non-uniform steady laminar flow that have traditionally been solved by mesh-dependent numerical methods. The encoder module, based on depthwise separable convolution, extracts the local geometric features within the flow region. Subsequently, the attention mechanism of the Transformer integrates these features, enabling the model to capture global information. Utilizing the decoder module constructed by deconvolution, the model restores the dimension of the flow region. The integration of local feature extraction and global perception capabilities enables the UTransNet to predict the velocity and pressure fields more effectively. Experimental results show that the total mean square error is reduced by about a factor of 12 compared with previous works. Also, the proposed model achieves a speedup of over 3 orders of magnitude over the CFD solver on Central Processing Unit (CPU) or Graphics Processing Unit. Qualitative and quantitative analyses reveal a high level of similarity between the predicted and ground-truth data.

17 March 2026 in Chaos, Solitons & Fractals
Verified
Journal Article
Closed access
TYTianle Yin
Tianle Yin
FCFeng Chen
Feng Chen
YZYanni Zhang
Yanni Zhang
KWKexing Wu
Kexing Wu

1 December 2025 in Physica Scripta
Verified
Journal Article
Closed access
WWWeiqing Wang
Weiqing Wang
TYTianle Yin
Tianle Yin
YLYue Liu
Yue Liu
JPJing Pang
Jing Pang
Fluid flow exhibits strong nonlinearity, and traditional solutions based on computational fluid dynamics (CFD) are limited by high computational costs. To efficiently model complex fluid dynamics, this study proposes a Fourier neural operator network (FNONet) to approximate solutions for 2D incompressible non-uniform steady laminar flows around obstacles. FNONet transforms flow geometry into Fourier space via discrete Fourier transform (DFT), parameterizes integral kernels using a neural network, and reconstructs velocity and pressure fields through hybrid frequency-spatial computations. A pressure gradient-constrained data-driven loss function is introduced to incorporate spatial-domain errors and frequency-domain pressure gradient constraints, thereby enhancing prediction accuracy near fluid-solid interfaces. Experiments demonstrate that the total mean squared error (MSE) of FNONet is over 20 times lower than that of convolutional neural network (CNN) based framework and 1.5 times lower than that of CNN-Transformer based framework. Compared with traditional CFD solvers, FNONet achieves a prediction speedup of over 3 orders of magnitude on central processing units (CPUs) and 4 orders of magnitude on graphics processing units (GPUs). The robustness and generalization of the model to unseen geometries are validated through qualitative visual analysis and quantitative error metrics on test datasets, providing a promising data-driven approach for CFD.