Zhiguo Zeng
Papers
2
Total Citations
11
H-Index
2
About
Zhiguo Zeng is a researcher working at the intersection of digital twins, fault diagnosis, and intelligent systems monitoring. His work addresses one of the most pressing challenges in modern industrial AI: the scarcity of labeled failure data needed to train reliable deep learning models. By leveraging digital twin technology, Zeng has pioneered approaches that use simulated environments to generate synthetic training data, reducing dependence on costly and difficult-to-obtain real-world failure observations. His 2025 paper introducing a domain adaptation neural network for digital twin-supported fault diagnosis tackles the critical sim-to-real gap, developing methods that maintain strong performance even when simulation and real-world conditions diverge — work that has already attracted 6 citations since publication. A complementary study proposing digital twins to support system-level condition monitoring has similarly gained early traction with 5 citations. Though his most-cited work is recent, the rapid uptake reflects growing community interest in his solutions to practical deployment barriers in data-driven diagnostics. Zeng's contributions are particularly valuable for engineers and researchers seeking robust, scalable fault diagnosis frameworks where historical failure data remains sparse or unavailable.
Research Focus
Key Achievements
Top Papers
- 1
- 2