Longda Zhang
Papers
4
Total Citations
52
H-Index
4
About
Longda Zhang is a leading researcher in intelligent fault diagnosis for mobile robots, specializing in graph neural networks and generative artificial intelligence. Their work addresses critical challenges in robotic health monitoring by developing advanced deep learning models that capture both spatial and temporal correlations from multi-sensor data. Zhang's most impactful contributions include the introduction of dual-graph convolutional networks and spatial-temporal graph attention networks, which have garnered 17 citations each for their ability to handle imbalanced data and model complex fault patterns. Their innovative adaptive temporal-topological graph convolution network (ATGCN) further advances the field by incorporating nodal attention mechanisms for more precise diagnosis. Zhang has also pioneered generative approaches, such as multimodal knowledge-based GANs, to synthesize realistic fault signals and overcome data scarcity. With over 50 total citations across their top papers, Zhang's work is widely recognized for pushing the boundaries of reliable, data-efficient fault diagnosis in wheeled robots, offering practical solutions for ensuring operational safety in autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4