Research under this area is focussed on the digitalisation of manufacturing, which aims to improve productivity and reduce costs through the effective use of digital tools such as machine learning and advanced process simulation. The overarching goal is to develop an advanced manufacturing decision support system that will interact with, and support, the machine operator in making decisions during the manufacturing process.

The research in this area is focussed on bringing together a wide range of decision information and data streams (including those from temperature and speed sensors, as well as image data) into an interactive support tool so that different manufacturing options can be offered to the operator, based on what is happening in real time during the manufacturing process. The challenge is to sort, simplify, visualise and interpret this data to produce actionable insights, enabling operators and engineers to make better informed decisions.

Projects include

  1. Design of experiments and database management for metal PBF-LB process optimisation.
  2. Accelerated process development and optimisation tools via code surrogates and inclusion of CAx information.
  3. Machine learning techniques for process feedback and control in AM.
  4. Develop software tools and recommender systems to aid in acceleration of metal LB PBF process optimisation.

Click here to view related publications