• Industry 4.0
Amount granted


Printed circuit boards (PCBs) are among the most significant types of e-waste, presenting recycling challenges due to their complexity. However, they contain valuable metals like gold, silver, and copper. While machine learning (ML) and AI have improved e-waste recycling, their focus on metal recovery is limited.

This proposed project aims to explore the potential of ML algorithms in optimizing electrowinning by monitoring parameters. The objectives include ML model development to predict optimal parameters for metal recovery. Developing an ML model for electrowinning advances circular economy practices by increasing metal recovery, reducing primary extraction, and conserving resources. This aligns with circular economy principles, promoting responsible material use and waste reduction.

Affiliated research axes

Axis 2: Planning Optimization

2.1 – Support the development and use of tools to analyze and monitor the circular economy
2.4 – Plan and optimize the production of products and delivery of services in the context of the circular economy

Axis 3: Resource and Product Maximization

3.1 – Map the knowledge and potential of product circularization
3.3 – Identify models for product circularization strategies


  • Lucas Hof

  • Philippe Bocher

    ing., Ph.D. Professor
  • Sabrina Gravel

    Ph.D. Associate Professor
  • Mohsen Mokhtabad-Amrei

    Ph.D. Researcher
  • Soroosh Hakimian

    M.Sc. Student member


Shamim Pourrahimi Seyghalani

ETS Student
The RRECQ is supported by the Fonds de recherche du Québec.
Fonds de recherche - Québec