Machine Learning for Corrosion Management

Symposium Chair(s)

• FA

  Francois Ayello

  DNV AS

Symposium Vice Chair(s)

• TS

  Theresa Stewart

This symposium highlights the growing role of machine learning in managing pipeline corrosion, from predicting degradation rates to enhancing inspection and monitoring strategies. By combining historical data, sensor inputs, and environmental factors, machine learning enables more accurate risk assessments and proactive maintenance. The session aims to connect corrosion experts and data scientists to drive smarter, data-informed integrity solutions.

Presentations:

• 1:00 PM - 1:30 PM Central

  Bayesian network modeling of industrial systems
  

  Presenting Author: Narasi Sridhar – State of Ohio
• 1:30 PM - 2:00 PM Central

  Effect of Sampling Dataset Size and Distribution on Machine Learning-Based Surrogate Modelling of CO2 Corrosion
  

  Presenting Author: James Willson – University of Leeds
• 2:00 PM - 2:30 PM Central

  Application of Machine Learning Tools to Enhance Corrosion Inhibitor Mixture Optimization Experimentation
  

  Presenting Author: Richard Woollam – University of Leeds
• 2:30 PM - 3:00 PM Central

  Enhancing Pipeline Integrity with Probabilistic Digital Twins and Bayesian Machine Learning
  

  Presenting Author: Guanlan Liu – DNV
• 3:00 PM - 3:30 PM Central

  Balancing Pipeline Profitability and Failure in Hydrogen Pipelines Using Machine Learning-Derived Operational Rules
  

  Presenting Author: Francois Ayello – DNV AS