Résumé:
Corrosion is a major challenge in the oil and gas industry, compromising the safety, reliability,
and sustainability of transportation infrastructure. This project proposes the design of an
embedded system dedicated to analyzing and predicting corrosion in metal pipelines. It is based
on the exploitation of data from inspections carried out over several years, combined with a
BiLSTM (Bidirectional Long Short-Term Memory) deep learning model to predict the maximum
corrosion depth at a given horizon. The dataset undergoes various preparation steps: missing
value processing, correlation analysis and feature matching between inspection years. The
developed model demonstrated high predictive accuracy with a low mean absolute error. This
approach enables effective predictive maintenance and contributes to failure prevention, thus
providing an innovative and suitable solution for real-time corrosion monitoring in embedded
industrial systems.
