Postgraduate research project

Deep learning for process control and predictive capability for laser machining

Funding
Competition funded View fees and funding
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

Advances in lasers now allow the laser-based processing of almost any material. Innovation in this field is now therefore becoming heavily focussed on making existing processing techniques more precise and efficient.

Neural networks are a computing paradigm inspired by the biological neurons in the human brain. They offer the capability for learning directly from experimental data, and hence can be used to find solutions even when the problem is not understood by a human. Neural networks therefore offer a remarkable solution to the optimisation and control of laser machining, which itself is far from understood.

The team is combining state-of-the-art neural networks with high-precision femtosecond laser machining, with the objective of achieving repeatable and high-speed fabrication at resolutions well-below the diffraction limit.

Your PhD will be focussed on the following applications:

  1. convolutional neural networks and reinforcement learning for real-time control of laser machining
  2. generative adversarial networks for simulating and predicting laser machining.

Neural networks require large amounts of experimental data for training, and hence this PhD will therefore involve a mixture of experimental photonics and femtosecond laser machining, experimental automation, and programming and designing neural networks.