Corrosion rate prediction and influencing factors evaluation of low-alloy steels in marine atmosphere using machine learning approach

Abstract

The empirical modeling methods are widely used in corrosion behavior analysis. But due to the limited regression ability of conventional algorithms, modeling objects are often limited to individual factors and specific environments. This study proposed a modeling method based on machine learning to simulate the marine atmospheric corrosion behavior of low-alloy steels. The correlations between material, environmental factors and corrosion rate were evaluated, and their influences on the corrosion behavior of steels were analyzed intuitively. By using the selected dominating factors as input variables, an optimized random forest model was established with a high prediction accuracy of corrosion rate (R 2 values, 0.94 and 0.73 to the training set and testing set) to different low-alloy steel samples in several typical marine atmospheric environments. The results demonstrated that machine learning was efficient in corrosion behavior analysis, which usually involves a regression analysis of multiple factors.

Plasticity of Bead-on-Plate Welds Made with the Use of Stored Flux-Cored Wires for Offshore Applications

“…The degradation of the surface of wires is one of the first signs of environmental impact on the material. General and atmospheric corrosion develops on the surface of the wires [ 5 , 6 , 26 ]. Depending on the storage location, it had a different intensity—A and B wires in MAB were exposed to increased relative humidity, which was the reason for accelerating surface degradation.…”

“…Predicting environmental loading is one of the key challenges in the design and construction of offshore structures [ 1 , 2 , 3 ]. These harmful loads include the influence of wind and water: waves, ocean currents, and even atmospheric precipitation [ 4 , 5 , 6 ]. In difficult marine conditions, in addition to mechanical static loads, material fatigue and environmental destruction mechanisms play a decisive role in assessing structural durability [ 7 , 8 ].…”

Predicting the corrosion properties of cast and hot isostatic pressed CoCrMo/W alloys in seawater by machine learning

“…Machine learning (ML) approaches have been transforming materials research by changing the paradigm from "trial-and-error" to a data-driven methodology, especially in high-entropy alloys (Wen et al, 2019;Zhang et al, 2020aZhang et al, , 2020b, perovskite catalysts (Weng et al, 2020), shape memory alloys (Xue et al, 2016) and copper alloys (Zhang et al, 2020a(Zhang et al, , 2020b(Zhang et al, , 2021Wang et al, 2019). Corrosion behavior research has also begun to focus on the ML prediction for corrosion rate of low-alloy steel (Yan et al, 2020;Diao et al, 2021) and carbon steel (Zhi et al, 2021;Pei et al, 2020). Diao et al (2021) used both the chemical composition of low-alloy steel and environmental factors to predict the corrosion rate using the random forest algorithm.…”

“…Cobalt-based alloys, because of their high strength over a wide temperature range and resistance to many environments, can be used in a wide range of industrial sectors, including the nuclear, aerospace and gas-turbine industries; bone surgery; and steel production and so on (Wu et al , 2021; Thawari et al , 2021; Garcia-Cabezon et al , 2020; Ding et al , 2020; Karimi et al , 2019; Ding et al , 2017; Malayoglu et al , 2005). Seawater systems have been used by many authors in laboratory studies to assess the corrosion behavior of a range of materials because its chloride-containing environment is similar to real situations and is suitable for analyzing localized corrosion (Yang et al , 2021; Song et al , 2020). Seawater is roughly equivalent in strength to a 3.5 Wt.% solution of sodium chloride, but the composition is much more complex, containing several major constituents and almost all naturally occurring elements.…”

Environmental and Microbial Influences on Corrosion of Selected Types of Petroleum Industry Steel

“…Environmental stimuli around the metal are the most common triggers of physicochemical corrosion. Properties like characteristics of the metal, chloride and SO2 deposition rates, temperature, humidity, pH, salinity and length of exposure are key initiators of physical and chemical corrosion in steel installations (Yan et al, 2020). Biological corrosion, more commonly tagged microbially influenced corrosion (MIC), is the irreversible deterioration of metal by the activities of microorganisms.…”