Papers
1
Total Citations
2
H-Index
1
About
Linyi Xiang is a rising researcher at the forefront of computational thermal management, specializing in reduced-order modeling and recurrent neural networks for high-performance electronic systems. Their most-cited work, "Reduced-order-driven recurrent neural network for ultra-fast thermal field simulation in high-heat-flux electronic systems" (2025), introduces a groundbreaking approach that dramatically accelerates thermal field predictions—achieving near real-time simulation speeds without sacrificing accuracy. This innovation directly addresses a critical bottleneck in designing next-generation electronics, where excessive heat dissipation threatens reliability and performance. Although early in their career, Xiang’s work has already garnered attention (2 citations), signaling its potential to reshape thermal simulation practices. By merging machine learning with physical modeling, Xiang is pioneering methods that enable engineers to explore complex thermal behaviors in seconds rather than hours, paving the way for more efficient cooling solutions and robust device architectures. Their research sits at the intersection of artificial intelligence, heat transfer, and electronic design automation, promising to accelerate innovation in high-heat-flux systems—from power electronics to data centers.
Research Focus
Key Achievements
Top Papers
- 1