Prediction model for corrosion rate of low-alloy steels under atmospheric conditions using machine learning algorithms

This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.

Prediction of corrosion rate for friction stir processed WE43 alloy by combining PSO-based virtual sample generation and machine learning

The corrosion rate is a crucial factor that impacts the longevity of materials in different applications.After undergoing friction stir processing(FSP),the refined grain structure leads to a notable decrease in corrosion rate.However,a better understanding of the correlation between the FSP process parameters and the corrosion rate is still lacking.The current study used machine learning to establish the relationship between the corrosion rate and FSP process parameters(rotational speed,traverse speed,and shoulder diameter)for WE43 alloy.The Taguchi L27 design of experiments was used for the experimental analysis.In addition,synthetic data was generated using particle swarm optimization for virtual sample generation(VSG).The application of VSG has led to an increase in the prediction accuracy of machine learning models.A sensitivity analysis was performed using Shapley Additive Explanations to determine the key factors affecting the corrosion rate.The shoulder diameter had a significant impact in comparison to the traverse speed.A graphical user interface(GUI)has been created to predict the corrosion rate using the identified factors.This study focuses on the WE43 alloy,but its findings can also be used to predict the corrosion rate of other magnesium alloys.

The corrosion characteristic and mechanism of Mg-5Y-1.5Nd-xZn-0.5Zr(x=0,2,4,6 wt.%)alloys in marine atmospheric environment

The microstructure and precipitated phases of as-cast Mg-5Y-1.5Nd-x Zn-0.5Zr(x=0,2,4,6 wt.%)alloys were investigated by optical microscopy,scanning electron microscopy,energy-dispersive spectrometry and X-ray Diffraction.The exposure corrosion experiment of these magnesium alloys was tested in South China Sea and KEXUE vessel atmospheric environment.The corrosion characteristic and mechanism of magnesium alloys of Mg-5Y-1.5Nd-x Zn-0.5Zr(x=0,2,4,6 wt.%)alloys were analyzed by weight loss rate,corrosion depth,corrosion products and corrosion morphologies.The electrochemical corrosion tests were also measured in the natural seawater.The comprehensive results showed that Mg-5Y-1.5Nd-4Zn-0.5Zr magnesium alloy existed the best corrosion resistance whether in the marine atmospheric environment and natural seawater environment.That depended on the microstructure,type and distribution of precipitated phases in Mg-5Y-1.5Nd-4Zn-0.5Zr magnesium alloy.Sufficient quantity anodic precipitated phases in the microstructure of Mg-5Y-1.5Nd-4Zn-0.5Zr alloy played the key role in the corrosion resistance.

Experimental Study on Corrosion of Stainless Steel in Low Temperature Multi effect Seawater Desalination

Starting from the corrosion mechanism,this paper analyzes the characteristics of various types of stainless steel and selects the best performance composite plate composite plate stainless steel.Analyze and select the most suitable corrosion detection method based on specific practical multi working conditions,discuss the interference factors that affect metal corrosion during experimental simulation,and the advantages of newly developed sheet metal.The new development of composite board panels,with the substrate and composite materials applying their respective capabilities for MED,will bring breakthrough progress to the scientific research and engineering applica-tion of composite boards.

Effect of the microstructure parameters on the corrosion characteristics of Mg-Zn-Ca alloy with columnar structure

Magnesium alloys with homogeneous degradation and controlled degradation rate are desirable for biodegradable materials.In the present work,Mg-3 wt.%Zn-0.2 wt.%Ca alloys with different columnar structures were fabricated and the degradation in 0.9 wt.%NaCl were investigated.With the increase of the growth rate for the directional solidification,the microstructure of the directionally solidified(DSed)alloy evolved from cellular to dendritic coupled with the change of the spacing of the primary trunks(λ_(1))and the volume fraction(fv)of Ca_(2)Mg_(6)Zn_(3) phase.The results of the corrosion test suggested that the alloy with cellular structure experienced homogeneous corrosion and exhibited the lowest corrosion rate.The good corrosion resistance of the alloy with cellular structure was attributed to the protective corrosion products film(CPF),which was closely related to the fv of Ca_(2)Mg_(6)Zn_(3) phase andλ_(1).To evaluate the corrosion rates(CR)of the DSed Mg-Zn-Ca alloys with different microstructures,a parameterαwas proposed in this work,which was calculated byλ_(1) and the fv of Ca_(2)Mg_(6)Zn_(3) phase.The fitting result showed that there was a linear relationship between CR andα,which was CR=4.1899+0.00432α.This means that the CR of the DSed Mg-Zn-Ca alloy can be evaluated if the microstructure had been characterized.

In-situ observation on filiform corrosion propagation and its dependence on Zr distribution in Mg alloy WE43

The direct industrial importance of the corrosion resistance in WE43 is best emphasized by its extensive use in the automotive, aerospace and electronic industries where weight reduction is a necessary requirement. In this work, the corrosion especially the filiform corrosion in a 3.5 wt.% Na Cl solution and their dependence on the Zr distribution for WE43 were studied by weight loss tests, hydrogen evolution tests, electrochemical measurements and microscopic analyses. The Zr distribution significantly influenced the initiation and propagation of the filiform corrosion, and accordingly significantly influenced the corrosion rate. WE43 with a cluster Zr distribution displayed filiform corrosion throughout the entire surface with an irregular network distribution of filaments. WE43 with a uniform line Zr distribution exhibited only a few examples of linear filiform corrosion. WE43 with a dispersive Zr distribution exhibited no filiform corrosion. The stability of the corrosion film was responsible for the filiform corrosion. Anodic polarisation promoted the initiation and progression of the filiform corrosion,while cathodic polarisation had an inhibiting effect on the filiform corrosion. The serrated interface of the filiform corrosion increased the contact area between the substrate and the corrosive medium, and hence increased the corrosion rate.

The Influence of the Corrosion Product Layer Generated on the High Strength Low-Alloy Steels Welded by Underwater Wet Welding with Stainless Steel Electrodes in Seawater

The high strength low-alloy steels are welded by underwater wet welding with stainless steel electrodes. The microstructural and electrochemical corrosion study of base metal(BM), weld zone(WZ) and heat affected zone(HAZ) are carried out to understand the influence of the corrosion product layer generated on the high strength low-alloy steels welded by underwater wet welding with stainless steel electrodes, methods used including, potentiodynamic polarization, electrochemical impedance spectroscopy(EIS) and scanning electron microscope(SEM). The results indicate that the WZ acts as a cathode and there is no corrosion product on it throughout the immersion period in seawater. The HAZ and BM acts as anodes. The corrosion rates of the HAZ and BM change with the immersion time increasing. In the initial immersion period, the HAZ has the highest corrosion rate because it has a coarse tempered martensite structure and the BM exhibites a microstructure with very fine grains of ferrite and pearlite. After a period of immersion, the BM has the highest corrosion rate. The reason is that the corrosion product layer on the HAZ is dense and has a better protective property while that on the BM is loose and can not inhibit the diffusion of oxygen.

Formulation of corrosion rate of magnesium alloys using microstructural parameters

Up to the date of writing this article,a quantitative analysis between corrosion rate and combined microstructural parameters including composition,grain size,and precipitations has not been reported.Hence,a literature review was carried out on these parameters to understand the quantitative effect of each one on the corrosion rate of Mg and Mg alloys.Moreover,using the available data in the literature and several experimental results,a new model was developed to predict the corrosion rate,through microstructural parameters.This model suggests that by using ultra-fined grains,alloying compounds with low Volta-potential difference relative to the matrix and a low fraction of secondary phase,a very low corrosion rates of materials are achievable.

Establishing empirical relationships to predict porosity level and corrosion rate of atmospheric plasma-sprayed alumina coatings on AZ31B magnesium alloy

Plasma sprayed ceramic coatings are successfully used in many industrial applications,where high wear and corrosion resistance with thermal insulation are required.In this work,empirical relationships were developed to predict the porosity and corrosion rate of alumina coatings by incorporating independently controllable atmospheric plasma spray operational parameters(input power,stand-off distance and powder feed rate)using response surface methodology(RSM).A central composite rotatable design with three factors and five levels was chosen to minimize the number of experimental conditions.Within the scope of the design space,the input power and the stand-off distance appeared to be the most significant two parameters affecting the responses among the three investigated process parameters.A linear regression relationship was also established between porosity and corrosion rate of the alumina coatings.Further,sensitivity analysis was carried out and compared with the relative impact of three process parameters on porosity level and corrosion rate to verify the measurement errors on the values of the uncertainty in estimated parameters.

Predictive Model for Corrosion Rate of Oil Tubes in CO_2/H_2S Coexistent Environment Part Ⅰ: Building of Model

Based on an analysis of the existing models of CO 2 corrosion in literatures and the autoclave simulative experiments, a predictive model of corrosion rate (r corr) in CO 2/H 2S corrosion for oil tubes has been established, in which r corr is expressed as a function of pH, temperature (T), pressure of CO 2 (P CO 2) and pressure of H 2S (P H 2S). The model has been verified by experimental data obtained on N80 steel. The improved features of the predictive model include the following aspects: (1) The influence of temperature on the protectiveness of corrosion film is taken into consideration for establishment of predictive model of the r corr in CO 2/H 2S corrosion. The Equations of scale temperature and scale factor are put forward, and they fit the experimental result very well. (2) The linear relationship still exists between ln r corr and ln P CO 2 in CO 2/H 2S corrosion (as same as that in CO 2 corrosion). Therefore, a correction factor as a function of P H 2S has been introduced into the predictive model in CO 2/H 2S corrosion. (3) The model is compatible with the main existing models.

Release rate kinetics of corrosion inhibitor loaded halloysite nanotube-based anticorrosion coatings on magnesium alloy AZ91D

Halloysite nanotubes were used as nanocontainers to hold corrosion inhibitors such as Ce^(3+)-Zr^(4+),2-mercaptobenzothiazole and 8-hydroxyquinoline in their lumen.An acid assisted etching of the nanotubes was carried out with a view to increase the lumen diameter and thereby,increase the amount of loading of the corrosion inhibitor.The morphology of as-received and etched halloysite nanotubes was ob-served using TEM analysis.The loading of corrosion inhibitors was confirmed using SEM-EDS and BET analysis.Polymeric microcapsules were used as capping agents for the ends of the loaded HNTs following which,they were dispersed into a hybrid sol-gel silica matrix.Dip coating method was used to generate coatings on AZ91D substrates followed by heat treatment at 130℃ for 1 h.The release rate kinetics of corrosion inhibitors from as-received and etched nanotubes was investigated in buffer solutions of 3.5 wt%NaCl at different pH.The release mechanism of corrosion inhibitors from the HNT lumen was validated using various semi-empirical models.Coatings were also evaluated for their corrosion protection ability using electrochemical techniques after exposure to 3.5 wt%NaCl solution for 120 h.Coatings generated using Ce^(3+)-Zr^(4+)loaded into as-received halloysite nanotubes have shown more effective corrosion protection when compared to other corrosion inhibitors after 120 h exposure to the corrosive medium.

On investigating the soda-lime shot blasting of AZ31 alloy:Effects on surface roughness,material removal rate,corrosion resistance,and bioactivity

In the present study,a novel method of surface finish improvement is proposed using shot blasting of soda lime(SBSL)beads on the Mg-AZ31 alloy.The effect of the soda blasting process parameters,such as blast pressure,stand-off distance,and blast duration,have been studied in-response of material removal rate(MRR)and surface roughness(SR)and corresponding statistical models have been obtained.The multi-objective optimization has also been performed to obtain parameters for maximum MRR and minimum SR.The corrosion behavior of the treated specimens has been performed to study their in-vitro biodegradability in simulated body fluid(SBF)for 1,3,7,10,15,and 21 days.The wettability study of the SBSL treated samples has been investigated using sessile drop methodology.Further,cell adhesion test has also been performed to study the biocompatibility characteristics of the SBSL treated samples using Huh7 liver cell lines.Based on obtained quantitative data as well as scanning electron microscopy analysis of treated samples,the SBSL treatment of the AZ31 alloy has been found highly useful in producing biocompatibility surfaces along with desirable morphological features.

EFFECTS OF HEAT TREATMENT AND ENVIRONMENT ON CRACK PROPAGATION RATE IN STEEL GC-4 UNDER CORROSION FATIGUE AND STRESS CORROSION

Comparative investigations were carried out of the effect of heat treatment regimes Jor steel GC-4(40CrMnSiMoVA)on its crack propagating rates,from corrosion fatigue, (da/dN)_(CF),or stress corrosion cracking,(da/dt)_(SCC),in media with various constituents and pH values.Both(da/dN)_(CF) and(da/dt)_(SCC) accelerate with the increase of yield stress of the steel,yet the former is far less than the later.In comparison with media,the (da/dt)_(SCC) in distilled water is slightly greater than that in 3.5% NaCl solution,and the (da/dN)_(CF) in distilled water is far less than that in 3.5% NaCl solution.With the pH value increasing in 3.5% NaCl solution,the(da/dN)_(CF) lowers down and the(da/dt)_(SCC) speeds up.An explanation was also proposed with concept of the cyclic hardening and softening at crack tip,as well as the crack closure and occluded cell effect.

Evaluation of Corrosion Product Activity in a Typical PWR with Extended Cycles and Flow Rate Perturbations

Effect of flow rate perturbations has been studied using the modified computer program CPAIR-P for time dependent corrosion rates in Pressurized Water Reactors (PWRs) having extended cycles. In these simulations, a decrease in the corresponding saturation values of corrosion product activity (CPA) is observed for higher pH values. Comparison of CPA’s behavior has been done for constant flow-rate case as well as for transients with elevated 10B levels (~40%) in dissolved boric acid in coolant in two operating cycles. When the flow rate is decreased in the first cycle, the saturation value of CPA attains new higher values. Also, in the second operating cycle, the saturation values are about 12% higher when compared with the values in the first cycle.

Predictability of Al-Mn Alloy Exposure Time Based on Its As-Cast Weight and Corrosion Rate in Sea Water Environment

This paper presents the predictability of aluminium-manganese alloy exposure time based on its as-cast weight and corrosion rate in sea water environment. The validity of the derived model: α = 26.67γ + 0.55β?- 0.29 is rooted on the core expression: 0.0375α = γ + 0.0206β?- 0.0109 where both sides of the expression are correspondingly approximately equal. Statistical analysis of model-predicted and experimentally evaluated exposure time for each value of as-cast weight and alloy corrosion rate considered shows a standard error of 0.0017% & 0.0044% and 0.0140% & 0.0150% respectively. The depths of corrosion penetration (at increasing corrosion rate: 0.0104 - 0.0157 mm/yr) as predicted by derived model and obtained from experiment are 0.7208 × 10-4 & 1.0123 × 10-4 mm and 2.5460 × 10-4 & 1.8240 × 10-4 mm (at decreasing corrosion rate: 0.0157 - 0.0062 mm/yr) respectively. Deviational analysis indicates that the maxi- mum deviation of the model-predicted alloy exposure time from the corresponding experimental value is less than 10%.

Effects of Strain Rate on Stress Corrosion of S355 Steel in 3.5% NaCl Solutions

The stress corrosion of S355 steel in 3.5% NaCl solution under the different strain rates was analyzed with the slow strain rate test（SSRT）, the stress corrosion cracking（SCC） behaviors of S355 steel under the different strain rates in the solution were investigated, and the fracture morphologies and compositions of corrosion products under the different strain rates were analyzed with scanning electron microscopy（SEM） and energy dispersive spectrometerry（EDS）, respectively. The experimental results show that the SCC sensitivity index is the highest when the strain rate is 2×10-6, and the medium corrosion is the main reason resulting in the highest SCC sensitivity index. The SCC sensitivity index is the least when the strain rate is 5×10-6, and the stress is the main reason resulting in the stress corrosion. The SCC sensitivity index is the middle when the strain rate is 9×10-6, the interaction of stress and medium is the stress corrosion fracture mechanism.

Studies on the Construction Parameter of an Artificial Occluded Cell for In-situ Inspection of the Propagation Rate of Localized Corrosion

An artificial localized corrosion system is assembled and some parameters related to the localized corrosion in active dissolution state (i.e., non-passive state) have been studied. The results showed that the developed electrochemical system can satisfactorily imitate a naturally formed localized corrosion and the coupling current can indicate the maximum localized propagating rate. In this artificial system, the anodic dissolution reaction followed the auto-catalytic mechanism. The localized corrosion current density was dependent on the area ratio R of the cathode to the occluded anode. While R was equal to or more than 6, the coupling current reached at a maximum value and did not alter with the increase in R-value. Therefore, R=7 is chosen as one of these optimum parameters used in constructing the system, with which the biggest galvanic current might be obtained. In contrast, the thickness of the polymer filler separating the occluded anode area from the bulk electrolyte solution and the volume of the occluded anode area did not affect the corrosion current obviously. They might affect the response time to approach a steady state.

Flow-Accelerated Corrosion in Pipe Wall Downstream of Orifice for Water and Air-Water Bubble Flows

An orifice is used widely as a flow meter or a contraction device in pipeline systems in hydro-power plants, thermal power plants, and chemical plants because of its simple construction, high reliability, and low cost. However, it is well known that flow-accelerated corrosion (FAC) occurs on the pipe wall downstream of the orifice. Some of the authors have examined FAC through experimental and numerical analyses and have reported that one of the major governing parameters of FAC for single-phase water flow is the pressure fluctuation p’ on the pipe wall, and also that pipe wall thinning rate TR can be estimated by p’. In addition, they have presented the effects of the ori-fice geometry on p’ or TR, and have described a method for suppressing p’ or TR. In the present study, FAC for a two-phase air-water bubble flow is examined and compared with the single-phase water flow experimentally. Further, it is shown that because p’ is also considered a governing parameter of FAC for a two-phase air-water bubble flow, TR can be estimated using p’. It is also indicated that, by using a downstream pipe with a smaller diameter than that of the upstream pipe, p’ or TR can be suppressed.

Corrosion resistance of 2195 aluminum alloy treated by multi-step-heating-rate controlled process

2195 aluminum-lithium alloy was widely applied in the aviation and aerospace industry, but it is highly susceptible to pitting and intergranular corrosion undergoing sever corrosive circumstance and moisture atmosphere. To solve this problem and consequently to prolong its service life, a multi-step-heating-rate(MSRC) process was carried out. Investigations were carried out to find the effect of the MSRC process on the alloys corrosion resistance. It is found that the MSRC process is more favorable for the uniform phase precipitation by comparing the corrosion resistance of samples treated by traditional heat treatments. The potential difference between phases can be reduced and intergranular corrosion is able to be prohibited efficiently. Besides, the rare earth infiltration is beneficial to improving the corrosion resistance. As heating time increases, the corrosion resistance declines gradually, samples treated by artificial aging and solid solution also exhibit a better corrosion resistance.

Effect of H_2S concentration on the corrosion behavior of pipeline steel under the coexistence of H_2S and CO_2

The effect of H2S concentration on H2S/CO2 corrosion of API-X60 steel was studied by scanning electron microscopy, a weight-loss method, potentiodynamic polarization tests, and the electrochemical impedance spectroscopy technique. It is found that the cor-rosion process of the steel in an environment where H2S and CO2 coexist at different H2S concentrations is related to the morphological structure and stability of the corrosion product film. With the addition of a small amount of H2S, the size of the anode reaction region is de-creased due to constant adsorption and separation of more FeS sediment or more FeHS＋ions on the surface of the steel. Meanwhile, the dou-ble-layer capacitance is diminished with increasing anion adsorption capacity. Therefore, the corrosion process is inhibited. The general cor-rosion rate of the steel rapidly decreases after the addition of a small amount of H2S under the coexistence of H2S and CO2. With a further increase in H2S concentration, certain parts of the corrosion product film become loose and even fall off. Thus, the protection provided by the corrosion product film worsens, and the corrosion rate tends to increase.