教育背景

博士 202207 北京大学 工学院

学士 201707 山东大学 控制科学与工程学院

工作履历

202207-202406  清华大学核研院401室 博士后

202407-至今  清华大学核研院401室 助理研究员

研究领域

核电厂操纵员运行支持系统、大语言模型技术与工程应用、运行信号监督与故障诊断、复杂系统智能控制与优化、强化学习与智能决策

学术成果

文章：

Zhang, T., Cheng, Z., Dong, Z., & Huang, X. (2025). Coordinated Control Optimization of Nuclear Steam Supply Systems via Multi-Agent Reinforcement Learning. Energies, 18(9), 2223.

Zhang, T., Dong, Z., & Huang, X. (2024). Multi-objective optimization of thermal power and outlet steam temperature for a nuclear steam supply system with deep reinforcement learning. Energy, 286, 129526.

Zhang, T., Jia, Q., Guo, C., & Huang, X. (2023). Abnormal event detection in nuclear power plants via attention networks. Energies, 16(18), 6745.

Zhang, T., Yue, L., Wang, C., Sun, J., Zhang, S., Wei, A., & Xie, G. (2022). Leveraging imitation learning on pose regulation problem of a robotic fish. IEEE Transactions on Neural Networks and Learning Systems, 35(3), 4232-4245.

Zhang, T., Tian, R., Yang, H., Wang, C., Sun, J., Zhang, S., & Xie, G. (2022). From simulation to reality: A learning framework for fish-like robots to perform control tasks. IEEE Transactions on Robotics, 38(6), 3861-3878.

Zhang, T., Xiao, J., Li, L., Wang, C., & Xie, G. (2021). Toward Coordination Control of Multiple Fish-Like Robots: Real-Time Vision-Based Pose Estimation and Tracking via Deep Neural Networks. IEEE CAA J. Autom. Sinica, 8(12), 1964-1976.

Zhang, T., Li, Y., Wang, C., Xie, G., & Lu, Z. (2021, July). Fop: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning. In International conference on machine learning (pp. 12491-12500). PMLR.

Zhang, T., Li, Y., Li, S., Ye, Q., Wang, C., & Xie, G. (2021, May). Decentralized circle formation control for fish-like robots in the real-world via reinforcement learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 8814-8820). IEEE.

Zhang, T., Tian, R., Wang, C., & Xie, G. (2020). Path-following control of fish-like robots: A deep reinforcement learning approach. IFAC-PapersOnLine, 53(2), 8163-8168.