Abstract
Pitting corrosion seriously harms the service life of oil field gathering and transportation pipelines, which is an important subject of corrosion prevention. In this study, we collected the corrosion data of pipeline steel immersion experiment and established a pitting judgment model based on machine learning algorithm. Feature reduction methods, including feature importance calculation and pearson correlation analysis, were first adopted to find the important factors affecting pitting. Then, the best input feature set for pitting judgment was constructed by combining feature combination and feature creation. Through receiver operating characteristic (ROC) curve and area under curve (AUC) calculation, random forest algorithm was selected as the modeling algorithm. As a result, the pitting judgment model based on machine learning and high dimensional feature parameters (i.e., material factors, solution factors, environment factors) showed good prediction accuracy. This study provided an effective means for processing high-dimensional and complex corrosion data, and proved the feasibility of machine learning in solving material corrosion problems.
Highlights
Corrosion damage seriously reduces the strength and service life of pipelines in oil and gas fields, which makes the problem of pipeline corrosion increasingly serious (Soares et al, 2009; JiménezCome et al, 2012)
Salinity refers to the total ion content in the solution, and the increase of its content can change the solubility of CO2 and H2S, affecting the development of pitting corrosion (Han et al, 2011)
We proposed a machine learning model based on experimental data to judge the occurrence of pitting for pipeline steel
Summary
Corrosion damage seriously reduces the strength and service life of pipelines in oil and gas fields, which makes the problem of pipeline corrosion increasingly serious (Soares et al, 2009; JiménezCome et al, 2012). Among all corrosion types, pitting corrosion is one of the most destructive and dangerous corrosion forms (Bhandari et al, 2015; Kolawole et al, 2016). It is of great practical significance to better judge the pitting corrosion of pipeline steel for the research and development of anti-corrosion technology and the prediction of structural integrity (Balekelayi and Tesfamariam, 2020). Pitting is a complex process that includes many complicated phenomena, such as mass transfer, metal dissolution and passivation, etc.), the influencing factors of pitting corrosion are many, such as metal components, medium temperature, pressure, pH, the type and concentration of ions (Choi et al, 2005; Li et al, 2012), which makes the modeling of pitting on more difficult
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
