I am a PhD researcher in Intelligent Manufacturing Ecosystem at the XJTLU, with an interdisciplinary background spanning thermal-fluid engineering, computational modeling, artificial intelligence, and automation. My doctoral research focuses on the topology optimization of additively manufactured microchannel heat exchangers under manufacturability constraints, and more broadly on the development of reliable, scalable, and engineering-oriented methods for complex thermal-fluid systems.

My research combines high-fidelity physics-based simulation, experimental validation, and data-driven learning. I have developed automated CFD workflows that support parametric geometry generation, standardized case setup, batch simulation, and automated post-processing, and I use machine learning surrogate models to accelerate thermohydraulic prediction, design screening, and optimization across broad operating and geometric spaces. This work has led to peer-reviewed outputs in heat exchanger modeling, microchannel performance prediction, and validated fin geometric design frameworks.

More recently, I have been extending this line of work toward intelligent engineering agents and digital-twin-enabled decision systems. In particular, I am interested in LLM-enabled CAE agents that can translate natural-language engineering intent into structured simulation tasks, retrieve domain knowledge and physical constraints, decompose large-scale optimization problems into executable subtasks, and coordinate multi-agent workflows across CAD generation, meshing, solver monitoring, and result analysis. My long-term goal is to develop trustworthy industrial intelligence agents that combine digital twins, time-series intelligence, and constraint-aware reasoning to support safe, explainable, and reproducible engineering optimization and control.