Bingyin Hu
Papers
2
Total Citations
15
H-Index
2
About
Bingyin Hu is a researcher advancing intelligent manufacturing through deep learning-driven tool condition monitoring. His work focuses on robotic milling, particularly the real-time detection of tool wear—a critical challenge for precision machining of aerospace alloys like Al7050-T7451. Hu’s major contributions lie in fusing multi-domain signal features (e.g., vibration, force, and acoustic emission) with novel neural network architectures. His most cited paper (2023, 10 citations) introduces a parallel bidirectional LSTM (BiLSTM) model that simultaneously processes time- and frequency-domain features, achieving robust wear prediction under complex robotic dynamics. Expanding this work, his 2025 study (5 citations) integrates stacked sparse autoencoders with BiLSTM networks, leveraging singularity features to enhance sensitivity to incipient wear. Together, these papers demonstrate a systematic progression from feature engineering to end-to-end deep learning, offering practical solutions for reducing downtime and improving surface quality in automated machining. Hu’s research bridges the gap between theoretical AI and industrial application, providing a foundation for adaptive, self-optimizing manufacturing systems. His work is particularly relevant for researchers exploring sensor fusion, transfer learning, or edge computing in cyber-physical production environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2