PhD academic projects in The University of Manchester
Under the supervision of Dr Robert Heinemann and Otto Jan Bakker.
Remove size limit of preceiving signals to achieve real-time process incidence identification.
TPP in process incidence identification
Deep learning, Tool wear, Process monitoring
Achieve multi-objectives prediction in one unified model.
Multi-objective prediction in drilling hybrid stacks
Deep learning, Tool wear, Process monitoring
MEng academic projects in Northwestern Polytechnical University
Under the supervision of Prof. Rong Mo and Huibin Sun.
Predict the future tendency of tool wear evolution in an online way.
LSTM based tool wear forecast
Deep learning, Tool wear forecast, Long-short term memory
A fast and accurate CNN model to monitor tool wear during machining process.
Tool wear monitoring in multiple condition
Deep Learning, Machine Tool, Tool wear monitoring, Convolutional Neural Network
One model to predict tool wear in multiple machining condition and its easy transferring to new condition.
The transfer learning in tool wear monitoring
Deep Learning, Machine Tool, Tool wear monitoring, Transfer Learning
Easy, intuitive and accurate way to demonstrate Mechanism of convolutional kernel in processing 1D signal.
DBSCAN based TDA Visualization
Deep Learning, Keras, Topology Data Analysis, Visualization
Simulate real and random signal accordance to tool wear by deep conditional convolutional generative adversarial network
Deep CGAN based tool wear digital twin
Deep Learning, Keras, Machine Tool, Digital Twin, Deep Convolutional Generative Adversarial Neural Network