欢迎访问我的个人学术主页!我是王志超博士,现任淮阴师范学院 人工智能与自动化学院 助理教授(讲师),于 2026 年 9 月入职。此前,我于 2026 年和 2022 年在国防科技大学计算机学院分别获得计算机科学与技术工学博士学位及电子信息硕士学位,博士期间师从刘杰教授、莫则尧教授和陈新海教授;本科毕业于西北工业大学(NWPU,2020年)。
我的主要研究方向为科学智能(AI for Science, AI4S),特别是面向计算流体力学的科学智能方法(AI for CFD)。重点围绕智能化网格生成、自适应运动与质量优化展开研究,探索图神经网络(GNNs)、强化学习(RL)以及无监督学习技术如何突破复杂几何物理仿真中的核心瓶颈难题。
招生与科研合作(Openings & Collaborations):
学生招募与科研指导:热忱欢迎对科学智能(AI4S)、智能流体计算(AI for CFD)以及几何深度学习具有浓厚学术兴趣的本科生与研究生加入课题组!优先欢迎具备扎实数学基础或熟练编程能力(如 PyTorch / C++ / Linux)的同学联系。课题组将提供系统性的科研指导、算力支撑与顶会顶刊论文撰写培养。
产学研与工程合作:除了学术前沿探索,我始终致力于推动 AI 算法与工程实际问题的高效对接。非常欢迎高校同行、科研院所、工业界伙伴及自主 CAE 软件研发团队在智能网格生成与修复、流体仿真加速、专用神经网络求解器等方向开展深入技术合作与联合研发。欢迎通过邮件随时沟通探讨!
🔥 最新动态 (Recent News)
- 2026.09 🏛️ 正式入职淮阴师范学院 人工智能与自动化学院担任助理教授(讲师)!
- 2026.06 🎓 顺利完成博士学位论文答辩,毕业于国防科技大学计算机学院!
- 2026.03 🎉 细粒度网格质量智能评估算法论文被 IJCNN 2026 (CCF-C) 正式录用!
- 2026.01 🚀 大语言模型流体求解器预印本论文 LLM4Fluid 正式发布于 arXiv:2601.21681。
- 2026.01 📄 泛化感知结构网格平滑论文发表于流体力学知名期刊 Computers & Fluids。
- 2025.10 💡 无先验强化学习网格优化模型论文 GNNRL-Smoothing 发表在权威期刊 Neural Networks (中科院二区 Top, CCF-B, IF 6.3)!
- 2025.09 🔥 基于 M-均匀损失的无监督网格运动网络 UGM2N 被国际顶级机器学习会议 NeurIPS 2025 (CCF-A) 正式录用!
- 2025.02 ✈️ 论文《基于无监督学习的飞行器表面网格平滑方法》发表于航空航天权威顶刊《航空学报》。
- 2025.01 🏆 获评国防科技大学“校级优秀学员”及研究生学业二等奖学金。
💡 重点研究方向 (Research Highlights)
📚 代表性学术成果 (Selected Publications)
@article{wang2026afin,
title = { A Fine-Grained Intelligent Mesh Quality Evaluation Algorithm Based on Neural Networks },
author = { Zhichao Wang and colleagues },
journal = { 2026 International Joint Conference on Neural Networks (IJCNN) },
year = { 2026 }
}@article{wang2026gener,
title = { Generalization-Aware Structured Mesh Smoothing via Graph Neural Networks },
author = { Zhichao Wang and colleagues },
journal = { Computers & Fluids },
year = { 2026 },
url = { https://doi.org/10.1016/j.compfluid.2025.106895 }
}@article{wang2026llm4f,
title = { LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics },
author = { Zhichao Wang and colleagues },
journal = { arXiv:2601.21681 },
year = { 2026 },
url = { https://arxiv.org/abs/2601.21681 }
}@article{wang2025gnnrl,
title = { GNNRL-Smoothing: A prior-free reinforcement learning model for mesh optimization },
author = { Zhichao Wang and colleagues },
journal = { Neural Networks },
year = { 2025 },
url = { https://doi.org/10.1016/j.neunet.2025.108235 }
}@article{wang2025ugm2n,
title = { UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss },
author = { Zhichao Wang and colleagues },
journal = { Advances in Neural Information Processing Systems (NeurIPS 2025) },
year = { 2025 },
url = { https://openreview.net/forum?id=UspcIEkK0y&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DNeurIPS.cc%2F2025%2FConference%2FAuthors%23your-submissions) }
}@article{wang2025aneu,
title = { A neural network approach for unstructured mesh quality evaluation },
author = { Zhichao Wang and colleagues },
journal = { Engineering Computations },
year = { 2025 },
url = { https://doi.org/10.1108/EC-XX-XXXX-XXXX }
}@article{wang2025anin,
title = { An intelligent mesh-smoothing method with graph neural networks },
author = { Zhichao Wang and colleagues },
journal = { Frontiers of Information Technology & Electronic Engineering },
year = { 2025 },
url = { https://doi.org/10.1631/FITEE.2400123 }
}@article{wang2025asur,
title = { A surface mesh smoothing method for aircraft based on unsupervised learning },
author = { Zhichao Wang and colleagues },
journal = { Acta Aeronautica et Astronautica Sinica },
year = { 2025 }
}@article{wang2024towar,
title = { Towards a new paradigm in intelligence-driven computational fluid dynamics simulations },
author = { Zhichao Wang and colleagues },
journal = { Engineering Applications of Computational Fluid Mechanics },
year = { 2024 },
url = { https://doi.org/10.1080/19942060.2024.2407005 }
}@article{wang2024accel,
title = { Accelerating aerodynamic design optimization based on graph convolutional neural network },
author = { Zhichao Wang and colleagues },
journal = { International Journal of Modern Physics C },
year = { 2024 }
}@article{wang2023st-pi,
title = { ST-PINN: A self-training physics-informed neural network for partial differential equations },
author = { Zhichao Wang and colleagues },
journal = { 2023 International Joint Conference on Neural Networks (IJCNN) },
year = { 2023 }
}@article{wang2022aneu,
title = { A neural network-based mesh quality indicator for three-dimensional cylinder modelling },
author = { Zhichao Wang and colleagues },
journal = { Entropy },
year = { 2022 },
url = { https://doi.org/10.3390/e24091245 }
}@article{wang2022evalu,
title = { Evaluating mesh quality with graph neural networks },
author = { Zhichao Wang and colleagues },
journal = { Engineering with Computers },
year = { 2022 },
url = { https://doi.org/10.1007/s00366-021-01487-6 }
}查看全部论文成果列表 (Full Publications) →
💼 工作经历与教育背景 (Experience & Education)
- 助理教授(讲师)淮阴师范学院 人工智能与自动化学院 | 2026.09 – 至今
- 计算机科学与技术 工学博士国防科技大学 计算机学院 | 2023 – 2026导师:刘杰教授、莫则尧教授、陈新海教授 | 研究方向:科学智能 (AI4S)、智能网格生成与几何优化
- 电子信息 工程硕士国防科技大学 计算机学院 | 2020 – 2022
- 机械电子工程 工学学士西北工业大学(NWPU) 机电学院 | 2016 – 2020
🏆 荣誉与奖项 (Honors & Awards)
- 校级优秀学员国防科技大学, 2025
- 研究生学业二等奖学金国防科技大学, 2025
- 院级优秀学员国防科技大学 计算机学院, 2025
- 国家奖学金 (前 1%)中华人民共和国教育部 & 西北工业大学, 2017
🤝 学术兼职与学术服务 (Service & Activities)
国际权威 SCI 期刊受邀审稿人 (Journal Reviewer):
- Computer Methods in Applied Mechanics and Engineering (CMAME)
- Neural Networks
- Aerospace Science and Technology (AST)
- Engineering Applications of Artificial Intelligence (EAAI)
- Simulation Modelling Practice and Theory (SMPT)
学术会议报告与交流:
- 口头报告: 第一届全国智能流体力学大会, 2024
- 口头报告: 2023 全国网格生成与应用研讨会 (MEGAS 2023), 2023
- 参会交流: 第二届中国空气动力学大会, 2023
课程助教:
- 《大学计算机》本科生核心基础课, 国防科技大学, 2024 & 2025