Design of strong anti-corrosion and high electrical conductivity protective bilayer coatings on bipolar plates in PEMWE cells by machine learning

Proton exchange membrane water electrolyzers (PEMWE) are a key way to make high‑purity hydrogen, but the strong acid and anodic conditions inside them quickly corrode metallic bipolar plates. To keep corrosion low while still allowing good electrical flow, engineers need protective bilayer coatings. This work looks at using machine learning (ML) to find the best coating composition, thickness, and structure. Historical experimental data on many coating materials are fed into predictive models that link design choices to two performance numbers: interfacial contact resistance (ICR) and corrosion current density. The study tests several regression methods—random forests, support‑vector machines, and deep neural networks—to see which predicts best. The ML‑chosen bilayer designs aim

to cut degradation and raise electrical efficiency. By using this approach, material screening becomes systematic and requires far fewer trial‑and‑error experiments. The framework helps create durable, highly conductive parts for electrochemical energy‑conversion systems and offers a clear path for advanced material design in clean‑energy applications.

Message: Hi FE, I need help with “Design of strong anti-corrosion and high electrical conductivity protective bilayer coatings on bipolar plates in PEMWE cells by machine learning” in “Electrical Engineering”