Papers
1
Total Citations
17
H-Index
1
About
Qitong Xu is a researcher specializing in intelligent fault diagnosis and mechanical system health monitoring, with a particular focus on complex rotating machinery. His most cited work, "An Improved Convolutional Capsule Network for Compound Fault Diagnosis of RV Reducers" (2022), addresses a critical challenge in industrial maintenance: diagnosing compound faults when only single-fault training data is available. By enhancing convolutional capsule networks, Xu developed a method that recognizes the inherent associations between compound and single faults, enabling accurate diagnosis even without compound fault samples—a significant advancement over traditional approaches that treat compound faults as isolated modes. This work has garnered 17 citations, reflecting its practical relevance for industries relying on RV reducers, such as robotics and precision manufacturing. Xu’s contributions lie at the intersection of deep learning and mechanical engineering, offering robust solutions for real-world fault diagnosis under data-scarce conditions. His research continues to push the boundaries of intelligent maintenance, making him a promising voice in the field of industrial AI and condition monitoring.
Research Focus
Key Achievements
Top Papers
- 1