Potential Distribution in Pipeline Network using a Numerical Impedance-Based Model and Artificial Intelligence (C2026-00325)

Hui Wang, Sreelakshmi Sreeharan, Reece Goldsberry, Homero Castaneda

Infrastructure monitoring and maintenance are critical to ensuring the safety, reliability, and longevity of underground pipelines. Indirect inspection technologies are commonly employed in external corrosion direct assessment (ECDA) to provide qualitative information on coating condition and cathodic protection (CP) levels. An impedance-based model has been validated for several quasi-one-dimensional cases, demonstrating its ability to account for spatial heterogeneities in the soil and coating phases of the system. It has been shown that this model can be used for either extracting information about the state of the coating, helping to identify possible regions of low impedance which could be attributed to holidays/defects present in the coating from survey data, or, if given real-world factors, it can be used for the design and integration of CP systems. In this work, we have extended the model's capabilities to accurately simulate the potential distribution for electrically connected pipeline networks, along with possible forms of CP interferences. The enhanced model was used for simplified bonding scenarios to ensure that the output made physical sense before simulating more complex and realistic scenarios. This estimations aims to utilize Artificial Intelligence to quantify anomalies in coating or the effectiveness of cathodic protection in the selected pipeline.