Cheng-Han Dai

Papers

Total Citations

H-Index

About

Cheng-Han Dai is a researcher at the forefront of intelligent manufacturing and condition monitoring, with a focus on integrating deep learning with signal processing for industrial applications. His work centers on applying advanced computational techniques—particularly recurrence plot analysis and convolutional neural networks—to enhance the reliability and efficiency of automated systems. In his most-cited study, "Application of Recurrence Plots and VGG Deep Learning Model to the Study of Condition Monitoring of Robotic Grinding" (2023), Dai pioneered a novel approach that transforms time-series vibration data into visual recurrence plots, which are then classified using a VGG deep learning architecture. This method achieved high accuracy in detecting tool wear and process anomalies in robotic grinding, offering a cost-effective, non-invasive solution for real-time industrial monitoring. With 8 citations to date, this work has already influenced subsequent research in predictive maintenance and smart manufacturing. Dai’s contributions bridge the gap between traditional signal processing and modern AI, providing a scalable framework for condition monitoring that is both robust and interpretable. His research continues to push the boundaries of how deep learning can be harnessed for real-world engineering challenges.