Machine learning for real-time parameters estimation and control of robotic laser cleaning

Surface cleaning is a technology used in a wide variety of industries, from heavy manufacturing and the energy sector through to conservation and restoration. Historically, technologies such as sandblasting and pressure washing have been used which have significant environmental and waste challenges. More recently, laser ablation has been used for surface cleaning. This last technology has a much lower waste disposal requirement due to the lack of blast media along with other benefits. Currently, lasers are used in paint stripping, rust removal, radioactive surface removal as well as component resurfacing for further processing. The current market’s needs hold a lot of potential. Market adoption of laser cleaning is limited as the systems available today must be operated by highly skilled technicians with constant monitoring/control of the cleaning process. The main objective of this project is to integrate AI and machine learning capabilities with the laser cleaning technology to allow for faster, more accurate and autonomous cleaning of increasingly complex components. This is achieved through constant monitoring of the substrate surface using sensors. The data from these sensors will be used to compare against required surface conditions and the AI will be used to control the laser settings accordingly.

Faculty Supervisor:

Moulay Akhloufi

Student:

Partner:

ASP Laser Inc

Discipline:

Computer science

Sector:

Clean Technology; Advanced Manufacturing; Artificial Intelligence

University:

Université de Moncton

Program: