A two-phase system is experimentally simulated to produce bubble and slug flows, similar to those found in pipelines. Different hydrocarbon/electrolyte test fluid mixtures in the range from 99.9/0.02 to
85/15 ratio by volume were prepared from diesel and 3% NaCl solution. Electrochemical current noise (ECN) is recorded by using a rotating system with 3 mild steel electrodes embedded in "activated" resin
under various flow conditions and test fluid mixtures. Depending on flow intensity and electrolyte content, ECN presents different types of signals, which are related to the wetting of the metal surface and corrosion intensity. Three types of neural networks have been tested to identify 3 signal patterns obtained from the experimental system as part of a corrosion monitoring system for water in oil systems where early and systematic corrosion detection is desirable. Keywords: oil-water mixtures, neural networks, activated electrodes