Content of COMPUTATIONAL PROGRAMS FOR PHYSICS in our journal

Published in last 1 year |  In last 2 years |  In last 3 years |  All Please wait a minute... For selected: Download citations EndNote Ris BibTeX Toggle thumbnails Select SolarDesign: An online photovoltaic device simulation and design platform Wei E. I. Sha(沙威), Xiaoyu Wang(王啸宇), Wenchao Chen(陈文超), Yuhao Fu(付钰豪), Lijun Zhang(张立军), Liang Tian(田亮), Minshen Lin(林敏慎), Shudi Jiao(焦书迪), Ting Xu(徐婷), Tiange Sun(孙天歌), and Dongxue Liu(刘冬雪) Chin. Phys. B, 2025, 34 (1): 018801.   DOI: 10.1088/1674-1056/ad9017 Abstract （521）   HTML （3）    PDF （871KB）（297）       Knowledge map    SolarDesign (https://solardesign.cn/) is an online photovoltaic device simulation and design platform that provides engineering modeling analysis for crystalline silicon solar cells, as well as emerging high-efficiency solar cells such as organic, perovskite, and tandem cells. The platform offers user-updatable libraries of basic photovoltaic materials and devices, device-level multi-physics simulations involving optical-electrical-thermal interactions, and circuit-level compact model simulations based on detailed balance theory. Employing internationally advanced numerical methods, the platform accurately, rapidly, and efficiently solves optical absorption, electrical transport, and compact circuit models. It achieves multi-level photovoltaic simulation technology from "materials to devices to circuits" with fully independent intellectual property rights. Compared to commercial softwares, the platform achieves high accuracy and improves speed by more than an order of magnitude. Additionally, it can simulate unique electrical transport processes in emerging solar cells, such as quantum tunneling, exciton dissociation, and ion migration. Select Literature classification and its applications in condensed matter physics and materials science by natural language processing Siyuan Wu(吴思远), Tiannian Zhu(朱天念), Sijia Tu(涂思佳), Ruijuan Xiao(肖睿娟), Jie Yuan(袁洁), Quansheng Wu(吴泉生), Hong Li(李泓), and Hongming Weng(翁红明) Chin. Phys. B, 2024, 33 (5): 050704.   DOI: 10.1088/1674-1056/ad3c30 Abstract （400）   HTML （7）    PDF （681KB）（223）       Knowledge map    The exponential growth of literature is constraining researchers' access to comprehensive information in related fields. While natural language processing (NLP) may offer an effective solution to literature classification, it remains hindered by the lack of labelled dataset. In this article, we introduce a novel method for generating literature classification models through semi-supervised learning, which can generate labelled dataset iteratively with limited human input. We apply this method to train NLP models for classifying literatures related to several research directions, i.e., battery, superconductor, topological material, and artificial intelligence (AI) in materials science. The trained NLP `battery' model applied on a larger dataset different from the training and testing dataset can achieve F1 score of 0.738, which indicates the accuracy and reliability of this scheme. Furthermore, our approach demonstrates that even with insufficient data, the not-well-trained model in the first few cycles can identify the relationships among different research fields and facilitate the discovery and understanding of interdisciplinary directions. Select Quafu-Qcover: Explore combinatorial optimization problems on cloud-based quantum computers Hong-Ze Xu(许宏泽), Wei-Feng Zhuang(庄伟峰), Zheng-An Wang(王正安), Kai-Xuan Huang(黄凯旋), Yun-Hao Shi(时运豪), Wei-Guo Ma(马卫国), Tian-Ming Li(李天铭), Chi-Tong Chen(陈驰通), Kai Xu(许凯), Yu-Long Feng(冯玉龙), Pei Liu(刘培), Mo Chen(陈墨), Shang-Shu Li(李尚书), Zhi-Peng Yang(杨智鹏), Chen Qian(钱辰), Yu-Xin Jin(靳羽欣), Yun-Heng Ma(马运恒), Xiao Xiao(肖骁), Peng Qian(钱鹏), Yanwu Gu(顾炎武), Xu-Dan Chai(柴绪丹), Ya-Nan Pu(普亚南), Yi-Peng Zhang(张翼鹏), Shi-Jie Wei(魏世杰), Jin-Feng Zeng(增进峰), Hang Li(李行), Gui-Lu Long(龙桂鲁), Yirong Jin(金贻荣), Haifeng Yu(于海峰), Heng Fan(范桁), Dong E. Liu(刘东), and Meng-Jun Hu(胡孟军) Chin. Phys. B, 2024, 33 (5): 050302.   DOI: 10.1088/1674-1056/ad18ab Abstract （400）   HTML （3）    PDF （2109KB）（473）       Knowledge map    We introduce Quafu-Qcover, an open-source cloud-based software package developed for solving combinatorial optimization problems using quantum simulators and hardware backends. Quafu-Qcover provides a standardized and comprehensive workflow that utilizes the quantum approximate optimization algorithm (QAOA). It facilitates the automatic conversion of the original problem into a quadratic unconstrained binary optimization (QUBO) model and its corresponding Ising model, which can be subsequently transformed into a weight graph. The core of Qcover relies on a graph decomposition-based classical algorithm, which efficiently derives the optimal parameters for the shallow QAOA circuit. Quafu-Qcover incorporates a dedicated compiler capable of translating QAOA circuits into physical quantum circuits that can be executed on Quafu cloud quantum computers. Compared to a general-purpose compiler, our compiler demonstrates the ability to generate shorter circuit depths, while also exhibiting superior speed performance. Additionally, the Qcover compiler has the capability to dynamically create a library of qubits coupling substructures in real-time, utilizing the most recent calibration data from the superconducting quantum devices. This ensures that computational tasks can be assigned to connected physical qubits with the highest fidelity. The Quafu-Qcover allows us to retrieve quantum computing sampling results using a task ID at any time, enabling asynchronous processing. Moreover, it incorporates modules for results preprocessing and visualization, facilitating an intuitive display of solutions for combinatorial optimization problems. We hope that Quafu-Qcover can serve as an instructive illustration for how to explore application problems on the Quafu cloud quantum computers. Select ScatterX: A software for fast processing of high-throughput small-angle scattering data Fei Xie(谢飞), Mei Xie(解梅), Baoyu Song(宋宝玉), Qiaoyu Guo(郭桥雨), and Xuechen Jiao(焦学琛) Chin. Phys. B, 2024, 33 (12): 120101.   DOI: 10.1088/1674-1056/ad8b36 Abstract （381）   HTML （4）    PDF （7088KB）（231）       Knowledge map    Scattering experiments become increasingly popular in modern scientific research, including the areas of materials, biology, chemistry, physics, etc. Besides, various types of scattering facilities have been developed recently, such as lab-based x-ray scattering equipment, national synchrotron facilities and large neutron facilities. These above-mentioned trends bring up fast-increasing data amounts of scattering data, as well as different scattering types (x-ray, neutron, laser and even microwaves). To help researchers process and analyze scattering data more efficiently, we developed a general and model-free scattering data analysis software based on matrix operation, which has the unique advantage of high throughput scattering data processing, analysis and visualization. To maximize generality and efficiency, data processing is performed based on a three-dimensional matrix, where scattering curves are saved as matrices or vectors, rather than the traditional definition of paired values. It can not only realize image batch processing, background subtraction and correction, but also analyze data according to scattering theory and model, such as radius of gyration, fractal dimension and other physical quantities. In the aspect of visualization, the software allows the modify the color maps of two-dimensional scattering images and the gradual color variation of one-dimensional curves to suit efficient data communications. In all, this new software can work as a stand-alone platform for researchers to process, analyze and visualize scattering data from different research facilities without considering different file types or formats. All codes in this manuscript are open-sourced and can be easily implemented in matrix-based software, such as MATLAB, Python and Igor. Select FL-Online: An x-ray crystallographic web-server for atomic-scale structure analysis of biomolecule Bintang Wang(王宾堂), Tongxin Niu(牛彤欣), Haifu Fan(范海福), and Wei Ding(丁玮) Chin. Phys. B, 2024, 33 (7): 076104.   DOI: 10.1088/1674-1056/ad47e5 Abstract （374）   HTML （0）    PDF （920KB）（227）       Knowledge map    FL-Online (http://fanlab.ac.cn) is an out-of-box modern web service featuring a user-friendly interface and simplified parameters, providing academic users with access to a series of online programs for biomolecular crystallography, including SAPI-online, OASIS-online, C-IPCAS-online and a series of upcoming software releases. Meanwhile, it is a highly scalable and maintainable web application framework that provides a powerful and flexible solution for academic web development needs. All the codes are open-source under MIT licenses in GitHub. Select Identifying important nodes of hypergraph: An improved PageRank algorithm Yu-Hao Piao(朴宇豪), Jun-Yi Wang(王俊义), and Ke-Zan Li(李科赞) Chin. Phys. B, 2025, 34 (4): 048902.   DOI: 10.1088/1674-1056/adb269 Abstract （363）   HTML （2）    PDF （871KB）（456）       Knowledge map    Hypergraphs can accurately capture complex higher-order relationships, but it is challenging to identify their important nodes. In this paper, an improved PageRank (ImPageRank) algorithm is designed to identify important nodes in a directed hypergraph. The algorithm introduces the Jaccard similarity of directed hypergraphs. By comparing the numbers of common neighbors between nodes with the total number of their neighbors, the Jaccard similarity measure takes into account the similarity between nodes that are not directly connected, and can reflect the potential correlation between nodes. An improved susceptible-infected (SI) model in directed hypergraph is proposed, which considers nonlinear propagation mode and more realistic propagation mechanism. In addition, some important node evaluation methods are transferred from undirected hypergraphs and applied to directed hypergraphs. Finally, the ImPageRank algorithm is used to evaluate the performance of the SI model, network robustness and monotonicity. Simulations of real networks demonstrate the excellent performance of the proposed algorithm and provide a powerful framework for identifying important nodes in directed hypergraphs. Select MicroMagnetic.jl: A Julia package for micromagnetic and atomistic simulations with GPU support Weiwei Wang(王伟伟), Boyao Lyu(吕伯尧), Lingyao Kong(孔令尧), Hans Fangohr, and Haifeng Du(杜海峰) Chin. Phys. B, 2024, 33 (10): 107508.   DOI: 10.1088/1674-1056/ad766f Abstract （356）   HTML （4）    PDF （919KB）（245）       Knowledge map    MicroMagnetic.jl is an open-source Julia package for micromagnetic and atomistic simulations. Using the features of the Julia programming language, MicroMagnetic.jl supports CPU and various GPU platforms, including NVIDIA, AMD, Intel, and Apple GPUs. Moreover, MicroMagnetic.jl supports Monte Carlo simulations for atomistic models and implements the nudged-elastic-band method for energy barrier computations. With built-in support for double and single precision modes and a design allowing easy extensibility to add new features, MicroMagnetic.jl provides a versatile toolset for researchers in micromagnetics and atomistic simulations. Select Analysis of pseudo-random number generators in QMC-SSE method Dong-Xu Liu(刘东旭), Wei Xu(徐维), and Xue-Feng Zhang(张学锋) Chin. Phys. B, 2024, 33 (3): 037509.   DOI: 10.1088/1674-1056/ad1e69 Abstract （307）   HTML （10）    PDF （514KB）（383）       Knowledge map    In the quantum Monte Carlo (QMC) method, the pseudo-random number generator (PRNG) plays a crucial role in determining the computation time. However, the hidden structure of the PRNG may lead to serious issues such as the breakdown of the Markov process. Here, we systematically analyze the performance of different PRNGs on the widely used QMC method known as the stochastic series expansion (SSE) algorithm. To quantitatively compare them, we introduce a quantity called QMC efficiency that can effectively reflect the efficiency of the algorithms. After testing several representative observables of the Heisenberg model in one and two dimensions, we recommend the linear congruential generator as the best choice of PRNG. Our work not only helps improve the performance of the SSE method but also sheds light on the other Markov-chain-based numerical algorithms. Select DSAS: A new macromolecular substructure solution program based on the modified phase-retrieval algorithm Xingke Fu(付兴科), Zhenxi Tan(谭振希), Zhi Geng(耿直), Qian Liu(刘茜), and Wei Ding(丁玮) Chin. Phys. B, 2024, 33 (5): 056102.   DOI: 10.1088/1674-1056/ad3c33 Abstract （298）   HTML （2）    PDF （1091KB）（344）       Knowledge map    Considering the pivotal role of single-wavelength anomalous diffraction (SAD) in macromolecular crystallography, our objective was to introduce {DSAS}, a novel program designed for efficient anomalous scattering substructure determination. DSAS stands out with its core components: a modified phase-retrieval algorithm and automated parameter tuning. The software boasts an intuitive graphical user interface (GUI), facilitating seamless input of essential data and real-time monitoring. Extensive testing on DSAS has involved diverse datasets, encompassing proteins, nucleic acids, and various anomalous scatters such as sulfur (S), selenium (Se), metals, and halogens. The results confirm {DSAS}'s exceptional performance in accurately determining heavy atom positions, making it a highly effective tool in the field. Select Charge self-consistent dynamical mean field theory calculations in combination with linear combination of numerical atomic orbitals framework based density functional theory Xin Qu(瞿鑫), Peng Xu(许鹏), Zhiyong Liu(刘志勇), Jintao Wang(王金涛), Fei Wang(王飞), Wei Huang(黄威), Zhongxin Li(李忠星), Weichang Xu(徐卫昌), and Xinguo Ren(任新国) Chin. Phys. B, 2024, 33 (10): 107106.   DOI: 10.1088/1674-1056/ad6558 Abstract （285）   HTML （8）    PDF （840KB）（680）       Knowledge map    We present a formalism of charge self-consistent dynamical mean field theory (DMFT) in combination with density functional theory (DFT) within the linear combination of numerical atomic orbitals (LCNAO) framework. We implemented the charge self-consistent $\rm DFT+DMFT$ formalism by interfacing a full-potential all-electron DFT code with three hybridization expansion-based continuous-time quantum Monte Carlo impurity solvers. The benchmarks on several 3d, 4f and 5f strongly correlated electron systems validated our formalism and implementation. Furthermore, within the LCANO framework, our formalism is general and the code architecture is extensible, so it can work as a bridge merging different LCNAO DFT packages and impurity solvers to do charge self-consistent $\rm DFT+DMFT$ calculations. Select Model-free prediction of chaotic dynamics with parameter-aware reservoir computing Jianmin Guo(郭建敏), Yao Du(杜瑶), Haibo Luo(罗海波), Xuan Wang(王晅), Yizhen Yu(于一真), and Xingang Wang(王新刚) Chin. Phys. B, 2025, 34 (4): 040505.   DOI: 10.1088/1674-1056/adb733 Abstract （256）   HTML （3）    PDF （12791KB）（323）       Knowledge map    Model-free, data-driven prediction of chaotic motions is a long-standing challenge in nonlinear science. Stimulated by the recent progress in machine learning, considerable attention has been given to the inference of chaos by the technique of reservoir computing (RC). In particular, by incorporating a parameter-control channel into the standard RC, it is demonstrated that the machine is able to not only replicate the dynamics of the training states, but also infer new dynamics not included in the training set. The new machine-learning scheme, termed parameter-aware RC, opens up new avenues for data-based analysis of chaotic systems, and holds promise for predicting and controlling many real-world complex systems. Here, using typical chaotic systems as examples, we give a comprehensive introduction to this powerful machine-learning technique, including the algorithm, the implementation, the performance, and the open questions calling for further studies. Select A hybrid method integrating Green's function Monte Carlo and projected entangled pair states He-Yu Lin(林赫羽), Rong-Qiang He(贺荣强), Yibin Guo (郭奕斌), and Zhong-Yi Lu(卢仲毅) Chin. Phys. B, 2024, 33 (11): 117504.   DOI: 10.1088/1674-1056/ad84c9 Abstract （248）   HTML （8）    PDF （2198KB）（199）       Knowledge map    This paper introduces a hybrid approach combining Green's function Monte Carlo (GFMC) method with projected entangled pair state (PEPS) ansatz. This hybrid method regards PEPS as a trial state and a guiding wave function in GFMC. By leveraging PEPS's proficiency in capturing quantum state entanglement and GFMC's efficient parallel architecture, the hybrid method is well-suited for the accurate and efficient treatment of frustrated quantum spin systems. As a benchmark, we applied this approach to study the frustrated $J_1$-$J_2$ Heisenberg model on a square lattice with periodic boundary conditions (PBCs). Compared with other numerical methods, our approach integrating PEPS and GFMC shows competitive accuracy in the performance of ground-state energy. This paper provides systematic and comprehensive discussion of the approach of our previous work [Phys. Rev. B 109 235133 (2024)]. Select A program for modeling the RF wave propagation of ICRF antennas utilizing the finite element method Lei-Yu Zhang(张雷宇), Yi-Xuan Li(李屹轩), Ming-Yue Han(韩明月), and Quan-Zhi Zhang(张权治) Chin. Phys. B, 2025, 34 (4): 045201.   DOI: 10.1088/1674-1056/adaccc Abstract （217）   HTML （2）    PDF （1151KB）（323）       Knowledge map    Controlled nuclear fusion represents a significant solution for future clean energy, with ion cyclotron range of frequency (ICRF) heating emerging as one of the most promising technologies for heating the fusion plasma. This study primarily presents a self-developed 2D ion cyclotron resonance antenna electromagnetic field solver (ICRAEMS) code implemented on the MATLAB platform, which solves the electric field wave equation by using the finite element method, establishing perfectly matched layer (PML) boundary conditions, and post-processing the electromagnetic field data. This code can be utilized to facilitate the design and optimization processes of antennas for ICRF heating technology. Furthermore, this study examines the electric field distribution and power spectrum associated with various antenna phases to investigate how different antenna configurations affect the electromagnetic field propagation and coupling characteristics. Select Progressive quantum algorithm for maximum independent set with quantum alternating operator ansatz Xiao-Hui Ni(倪晓慧), Ling-Xiao Li(李凌霄), Yan-Qi Song(宋燕琪), Zheng-Ping Jin(金正平), Su-Juan Qin(秦素娟), and Fei Gao(高飞) Chin. Phys. B, 2025, 34 (7): 070304.   DOI: 10.1088/1674-1056/addd83 Abstract （157）   HTML （0）    PDF （1456KB）（272）       Knowledge map    The quantum alternating operator ansatz algorithm (QAOA+) is widely used for constrained combinatorial optimization problems (CCOPs) due to its ability to construct feasible solution spaces. In this paper, we propose a progressive quantum algorithm (PQA) to reduce qubit requirements for QAOA+ in solving the maximum independent set (MIS) problem. PQA iteratively constructs a subgraph likely to include the MIS solution of the original graph and solves the problem on it to approximate the global solution. Specifically, PQA starts with a small-scale subgraph and progressively expands its graph size utilizing heuristic expansion strategies. After each expansion, PQA solves the MIS problem on the newly generated subgraph using QAOA+. In each run, PQA repeats the expansion and solving process until a predefined stopping condition is reached. Simulation results show that PQA achieves an approximation ratio of 0.95 using only $5.57%$ ($2.17%$) of the qubits and $17.59%$ ($6.43%$) of the runtime compared with directly solving the original problem with QAOA+ on Erdös-Rényi (3-regular) graphs, highlighting the efficiency and scalability of PQA. Select 3D-GTDSE: A GPU-based code for solving 3D-TDSE in Cartesian coordinates Ke Peng(彭科), Aihua Liu(刘爱华), Jun Wang(王俊), and Xi Zhao(赵曦) Chin. Phys. B, 2025, 34 (9): 094203.   DOI: 10.1088/1674-1056/adee00 Abstract （79）   HTML （0）    PDF （1332KB）（26）       Knowledge map    We present a graphics processing units (GPU) parallelization based three-dimensional time-dependent Schrödinger equation (3D-TDSE) code to simulate the interaction between single-active-electron atom/molecule and arbitrary types of laser pulses with either velocity gauge or length gauge in Cartesian coordinates. Split-operator method combined with fast Fourier transforms (FFT) is used to perform the time evolution. Sample applications in different scenarios, such as stationary state energies, photon ionization spectra, attosecond clocks, and high-order harmonic generation (HHG), are given for the hydrogen atom. Repeatable results can be obtained with the benchmark program PCTDSE, which is a 3D-TDSE Fortran solver parallelized using message passing interface (MPI) library. With the help of GPU acceleration and vectorization strategy, our code running on a single NVIDIA 3090 RTX GPU can achieve about 10 times faster computation speed than PCTDSE running on a 144 Intel Xeon CPU cores server with the same accuracy. In addition, 3D-GTDSE can also be modified slightly to simulate non-adiabatic dynamics involving the coupling of nuclear and electronic wave packets, as well as pure nuclear wave packet dynamics in the presence of strong laser fields within 3 dimensions. Additionally, we have also discussed the limitations and shortcomings of our code in utilizing GPU memory. The 3D-GTDSE code provides an alternative tool for studying the ultrafast nonlinear dynamics under strong laser fields. Select Accurate quantum critical points and nonlocal string order parameters in the spin tetrahedron chain Zhi-Yong Wu(吴志勇), Kai-Ming Zhang(张凯铭), and Li-Xiang Cen(岑理相) Chin. Phys. B, 2025, 34 (11): 117502.   DOI: 10.1088/1674-1056/ae0c7c Abstract （47）   HTML （0）    PDF （749KB）（18）       Knowledge map    The ground-state phase diagram and nonlocal order parameters of an infinite spin tetrahedron chain with inhomogeneous exchange couplings are investigated. It is shown that the phase boundaries of the three phases in the model can be determined precisely, in line with the precision of its ground-state energy. Numerical calculations using the regularized time-evolving block decimation (rTEBD) algorithm yield the locations of the two quantum critical points with an accuracy about $10$ digits. Moreover, we explain how to calculate the parity-associated string order for the output wave function obtained through the rTEBD procedure, which not only reveals the presence of long-range correlations but also identifies the symmetry-protected topological order within the intermediate phase of the model. Select VASPilot: MCP-facilitated multi-agent intelligence for autonomous VASP simulations Jiaxuan Liu(刘家轩), Tiannian Zhu(朱天念), Caiyuan Ye(叶财渊), Zhong Fang(方忠), Hongming Weng(翁红明), and Quansheng Wu(吴泉生) Chin. Phys. B, 2025, 34 (11): 117106.   DOI: 10.1088/1674-1056/ae0681 Abstract （37）   HTML （0）    PDF （1799KB）（6）       Knowledge map    Density-functional-theory (DFT) simulations with the Vienna Ab initio Simulation Package (VASP) are indispensable in computational materials science but often require extensive manual setup, monitoring, and postprocessing. Here, we introduce VASPilot, an open-source platform that fully automates VASP workflows via a multi-agent architecture built on the CrewAI framework and a standardized model context protocol (MCP). VASPilot's agent suite handles every stage of a VASP study from retrieving crystal structures and generating input files to submitting Slurm jobs, parsing error messages, and dynamically adjusting parameters for seamless restarts. A lightweight Quart-based web interface provides intuitive task submission, real-time progress tracking, and drill-down access to execution logs, structure visualizations, and plots. We validated VASPilot on both routine and advanced benchmarks: automated band-structure and density-of-states calculations (including on-the-fly symmetry corrections), plane-wave cutoff convergence tests, lattice-constant optimizations with various van der Waals corrections, and cross-material band-gap comparisons for transition-metal dichalcogenides. In all cases, VASPilot completed the missions reliably and without manual intervention. Moreover, its modular design allows easy extension to other DFT codes simply by deploying the appropriate MCP server. By offloading technical overhead, VASPilot enables researchers to focus on scientific discovery and accelerates high-throughput computational materials research. Select Improved physics-informed neural networks incorporating lattice Boltzmann method optimized by tanh robust weight initialization Chenghui Yang(杨程晖), Minglei Shan(单鸣雷), Mengyu Feng(冯梦宇), Ling Kuai(蒯玲), Yu Yang(杨雨), Cheng Yin(殷澄), and Qingbang Han(韩庆邦) Chin. Phys. B, 2025, 34 (11): 110701.   DOI: 10.1088/1674-1056/adfc43 Abstract （37）   HTML （0）    PDF （2549KB）（10）       Knowledge map    Physics-informed neural networks (PINNs) have shown considerable promise for performing numerical simulations in fluid mechanics. They provide mesh-free, end-to-end approaches by embedding physical laws into their loss functions. However, when addressing complex flow problems, PINNs still face some challenges such as activation saturation and vanishing gradients in deep network training, leading to slow convergence and insufficient prediction accuracy. We present physics-informed neural networks incorporating lattice Boltzmann method optimized by tanh robust weight initialization (T-PINN-LBM) to address these challenges. This approach fuses the mesoscopic lattice Boltzmann model with the automatic differentiation framework of PINNs. It also implements a tanh robust weight initialization method derived from fixed point analysis. This model effectively mitigates activation and gradient decay in deep networks, improving convergence speed and data efficiency in multiscale flow simulations. We validate the effectiveness of the model on the classical arithmetic example of lid-driven cavity flow. Compared to the traditional Xavier initialized PINN and PINN-LBM, T-PINN-LBM reduces the mean absolute error (MAE) by one order of magnitude at the same network depth and maintains stable convergence in deeper networks. The results demonstrate that this model can accurately capture complex flow structures without prior data, providing a new feasible pathway for data-free driven fluid simulation.