Minghang Zhao
Papers
1
Total Citations
84
H-Index
1
About
Minghang Zhao is a leading researcher in intelligent fault diagnosis and machine learning for industrial systems, with a focus on addressing data imbalance challenges in critical infrastructure. His work centers on developing advanced data augmentation and feature learning techniques to improve the reliability of condition monitoring for high-value assets like gas turbines. His most-cited paper, "Feature-level SMOTE: Augmenting fault samples in learnable feature space for imbalanced fault diagnosis of gas turbines" (2023, 84 citations), introduces a novel approach that synthesizes fault samples directly within a learnable feature space, significantly enhancing diagnostic accuracy when fault data is scarce. This contribution is pivotal for real-world applications where failure data is rare but safety-critical. Zhao’s research bridges the gap between theoretical machine learning and practical engineering, offering robust solutions for predictive maintenance. His work has been widely recognized, with this paper alone garnering substantial citations, reflecting its impact on both academia and industry. By tackling imbalanced datasets head-on, Zhao empowers engineers to detect faults earlier and more reliably, advancing the frontier of intelligent industrial monitoring.
Research Focus
Key Achievements
Top Papers
- 1