Xiaojia Han
Papers
1
Total Citations
6
H-Index
1
About
Xiaojia Han is a leading researcher in intelligent fault diagnosis and industrial robotics, with a focus on tackling data imbalance challenges in real-world manufacturing systems. Her most cited work, "Intelligent Fault Diagnosis of Industrial Robot Based on Multiclass Mahalanobis-Taguchi System for Imbalanced Data" (2022, 6 citations), addresses a critical bottleneck: the scarcity of fault data compared to abundant normal operating data. By developing a multiclass Mahalanobis-Taguchi System, Han’s approach overcomes the bias of traditional methods toward majority categories, enabling more accurate and reliable detection of rare faults in industrial robots. This contribution is pivotal for predictive maintenance, reducing downtime, and enhancing safety in automated production lines. Han’s research bridges statistical learning and practical engineering, offering scalable solutions for imbalanced datasets—a common yet underexplored problem in industry. Her work has been recognized for its potential to transform fault diagnosis from reactive to proactive, with implications for smart manufacturing and Industry 4.0. Through her innovative methodologies, Han continues to advance the reliability and intelligence of robotic systems, making her a key figure in the field of industrial diagnostics.
Research Focus
Key Achievements
Top Papers
- 1