Combined Experimental and Field Data Sources in a Prediction Model for Corrosion Rate under Insulation

Abstract

Corrosion under insulation (CUI) is one of the increasing industrial problems, especially in chemical plants that have been running for an extended time. Prediction modeling, which is one of the solutions for this issue, has attracted increasing attention and has been considered for several industrial applications. The main objective of this work was to investigate the effect of combined data input in prediction modeling, which could be applied to improve the existing CUI rate prediction model. Experimental data and field historical data were gathered and simulated using an artificial neural network separately. To analyze the effect of data sources on the final corrosion rate under the insulation prediction model, both sources of data from experiment and field data were then combined and simulated again using an artificial neural network. Results exhibited the advantages of combined input data type from the experiment and field in the final prediction model. The model developed clearly shows the occurrence of corrosion by phases, which are uniform corrosion at the early phases and pitting corrosion at the later phases. The prediction model will enable better mitigation actions in preventing loss of containment due to CUI, which in turn will improve overall sustainability of the plant.