A Neuro-Fuzzy Knowledge-Based Model for the Risk Assessment of Microbiologically Influenced Corrosion in Crude Oil Pipelines

The oil and gas industry heavily relies on the integrity of their pipeline systems and underground storage containers for economical and environmental reasons. The integrity of the pipeline systems and storage containers is largely threatened by localized corrosion. One of the primary forms of internal corrosion found in oil and gas pipelines, in addition to corrosion enhanced with carbon dioxide (CO₂) and hydrogen sulfide (H₂S), is microbiologically influenced corrosion (MIC). Biofilms are produced by microbes from the excretion of exopolymeric substances (EPS). These biofilms adhere to the surface of materials and provide an environment for the anaerobic processes underneath its surface, as nitrate reduction or sulfate reduction, etc., which ultimately may cause localized corrosion. Localized corrosion starts underneath such biofilms by establishing small corrosion cells where oxygen levels are negligible and pH is low. Such conditions favor the growth of sulfate-reducing bacteria (SRB). MIC is mainly prevalent underneath biofilms; the probability of biofouling should be directly proportional to the risk of MIC. Our objectives were to assess the chances of biofouling in crude oil pipelines under specified operational conditions and the corrosion damage that may occur at the places where the biofilms develop.