Xuewu Dai

About

Xuewu Dai is a leading researcher in model-based fault detection and observer theory for dynamic control systems. His work centers on developing advanced observer architectures—particularly generalized proportional–integral observers (GPIOs)—to achieve robust, early detection of sensor and actuator faults in systems plagued by periodic disturbances. Dai’s major contributions include the design of a disturbance decoupling GPIO (DD-GPIO) that isolates sensor faults from external semistationary disturbances, significantly improving detection reliability in industrial wireless sensor actuator networks. His research has garnered over 40 citations, with his 2022 DD-GPIO paper alone receiving 23 citations, reflecting its impact on the field. Notably, Dai has also pioneered the integration of observer theory with deep learning, as demonstrated in his 2025 work on an observer-driven temporal graph convolutional network (OD-TGCN) for detecting incipient, low-amplitude faults that conventional methods miss. By bridging classical observer design with modern data-driven techniques, Dai is shaping the next generation of fault diagnosis systems for safety-critical applications.

Research Focus

Key Achievements

Top Papers

1. 1
   A Disturbance Decoupling Generalized Proportional–Integral Observer Design for Robust Sensor Fault Detection

   23 citations · 2022
2. 2
   Model-based on-line sensor fault detection in Wireless Sensor Actuator Networks

   12 citations · 2015
3. 3
   Output observer for fault detection in linear systems

   3 citations · 2016
4. 4
   A generalized proportional‐integral observer for fault detection: An approximate input disturbance decoupling approach

   2 citations · 2023
5. 5
   OD-TGCN: An Observer-Driven Temporal Graph Convolutional Network for Early Fault Detection of Control Systems

   1 citations · 2025

Key Collaborators

Contact & Links