Xiaolei Fang
Papers
2
Total Citations
8
H-Index
2
About
Xiaolei Fang is a rising authority in intelligent manufacturing and industrial diagnostics, whose work bridges the gap between physical system interpretability and deep learning robustness. His primary research focuses on fault diagnosis (FD) for industrial robots (IRs) and manufacturing system authentication—areas critical to modern smart factories. Fang’s most significant contribution is the development of a Deep Complex Wavelet Denoising Network, which addresses three persistent challenges in industrial FD: strong noise interference, imbalanced fault samples, and the lack of physical interpretation in black-box models. By leveraging complex wavelet transforms, his network preserves phase information and provides denoising that is both mathematically principled and diagnostically transparent. This work, published in 2025, has already garnered 3 citations for its novel approach to feature exploitation under scarce fault conditions. Fang also co-developed an unobservable fingerprinting system for authenticating manufacturing machines (2023, 5 citations), introducing a hardware-agnostic security layer that prevents counterfeiting in production lines. His achievements demonstrate a rare ability to combine theoretical signal processing with practical industrial deployment. For students and researchers, Fang’s work exemplifies how interpretable AI can solve real-world manufacturing constraints—noise, data scarcity, and security—without sacrificing performance.
Research Focus
Key Achievements
Top Papers
- 1
- 2