Modeling the corrosion behavior of Ni-Cr-Mo-V high strength steel in the simulated deep sea environments using design of experiment and artificial neural network

The development of a mechanistic-chemometrics model with multi-degree of freedom for pitting corrosion of HP-13Cr stainless steel under extremely oilfield environments

“…This method is based on the decomposition of total variability in the selected response (y) and assesses the relationship between the factors and the variability of responses. The significant factors or interactions can be identified as the ratio of the mean square of a factor or as an interaction and the residual mean square (F-value) [49][50]. If the F-value was less than 11.27, the factors were considered as negligible [55].…”

“…In addition, chemometrics method belongs to a discipline that provides an efficient approach through statistical or mathematical methods to investigate the effect of each variable and the interaction between variables [48][49][50]. A combination of chemometric method and the model proposed by Zhang's group results in a novel mechanistic-chemometric prediction model, which is developed herein in order to incorporate the influence of temperature, CO2 pressure, flow rate and stress on the growth kinetics of pits.…”

Analysis of Environmental Factors Affecting the Atmospheric Corrosion Rate of Low-Alloy Steel Using Random Forest-Based Models

“…With substantial analysis and simulation capacities to multi-feature fitting problems and small datasets, machine learning has been widely used in material research [ 22 , 23 ]. In the field of corrosion research, machine learning has also been used for corrosion rate prediction, electrochemical test simulation, corrosion inhibitor design [ 24 , 25 ], etc. Wen et al proposed a support vector regression model for prediction of the corrosion rate of 3C steel under five different seawater environmental factors, including temperature, dissolved oxygen, salinity, pH value, and oxidation-reduction potential [ 26 ].…”

Principal Component Analysis Based Dynamic Fuzzy Neural Network for Internal Corrosion Rate Prediction of Gas Pipelines

“…Abbas et al developed neural networks (NN) to predict CO 2 corrosion on pipelines at high partial pressures and assessed the degree of suitability for CO 2 corrosion rate prediction [10]. Hu et al combined the design of experiment (DOE) approach with ANN to discuss the effects of environmental factors in the deep sea on the Ni-Cr-Mo-V high strength steel corrosion behavior [11]. Although these works have showed great advantages and potential in solving highly nonlinear problems, these models have shortcomings, such as poor fuzzy logic inference ability when completing the "black box" nonlinear mapping from the input to output.…”