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.

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.

A novel biodegradable high nitrogen iron alloy with simultaneous enhancement of corrosion rate and local corrosion resistance

To improve the corrosion rate and suppress the local corrosion,a novel biodegradable high nitrogen(N)FeMnN alloy was developed,and the effects of N content on the corrosion behaviors were systematically investigated.It was found that,as the N content increased,the corrosion rate was significantly enhanced in both Hank’s solution and simulated gastric fluid.Meanwhile,as the N content increased,the size and depth of pits decreased obviously,and the number of pits increased,which presented a more uniform corrosion morphology.X-ray photoelectron spectroscopy(XPS)results indicated that N existed in the form of NH_(4)^(+) in the corrosion products and[FeN]clusters in the matrix.The[FeN]clusters would simultane-ously improve the corrosion rate and suppress the local corrosion,which provides a new perspective for the development of biodegradable Fe alloy.

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.

Calculation of corrosion rate for reinforced concrete beams based on corrosive crack width

This paper deals with a correction method for corrosive crack width caused by non-uniform corrosion. Considering the corrosion cracking characteristics of a reinforced concrete structure, a correction model of corrosive crack width involving the mutual impacts between adjacent measuring points is established. The calculation model for steel bar corrosion rate for single point is obtained through quantitative analysis and accelerated corrosion tests on more than 70 reinforced cubic members. Two methods are suggested by combining two models, the correction and the corrosion calculation ones. Electrolyte accelerated cor- rosion tests on seven beams are carried out to verify these methods. The experimental results show that the ratio between the maximum corrosion rate by the indirect method and the measured average value ranges from 1.4 to 2.4, and the indirect method is shown to be an effective method for calculating the maximum corrosion rate.

Static Corrosion Rates of Fused-cast AZS Refractory Materials by Molten Glass

In order to investigate corrosive phenomena of fused-cast Al_2O_3-ZrO_2-SiO_2(AZS) refractory materials by molten glass,two types of fused-cast AZS refractory bricks were taken as the interests of the research to study static corrosion rates(mm/d) of the two type materials by molten soda-lime-silica glass at different temperatures(1400,1450 and 1500 *C) and for different isothermal periods(0.5,1.0 and 1.5 d).It was shown that static corrosion rate of each AZS material by molten glass at the triple point developed with raising temperature but slightly decreased with enhancing isothermal period.Based on chemical compositions,microstructures,and corrosive morphologies of AZS refractory materials,the relation between them and static corrosion rates of AZS refractory materials by molten glass was analyzed.

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.

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.

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.

Effect of purification treatment on corrosion resistance of Mg-Gd-Y-Zr alloy

Mg-Gd-Y-Zr alloys were purified by filtering purification with and without vacuum. The type, morphology, size distribution and volume fraction of inclusion were analyzed with OM and SEM. The effect of inclusion in Mg-Gd-Y-Zr alloys on anticorrosion ability was investigated with salt spray test and electrochemical test. The results show that the inclusions in the alloy can be removed effectively by filtering purification. The average size of inclusions in the alloys is decreased from 12.7 μm to 2.0 μm and the volume fraction of inclusions is reduced from 0.30% to 0.04%. With the decrease of the size of inclusions in the alloys, the corrosion rate of the alloys decreases dramatically from 38.8 g/（m 2 ·d） to 2.4 g/（m 2 ·d） in the salt spray test. The corrosion potential increases while the corrosion current decreases and the polarization resistance increases in the electrochemical tests, which indicates that the anticorrosion ability is improved.

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.

Effects of chromium on the corrosion and electrochemical behaviors of ultra high strength steels

The effects of chromium on the corrosion and the electrochemical behaviors of ultra high strength steels were studied by the salt spray test and electrochemical methods. The results show that ultra high strength steels remain martensite structures and have anodic dissolution characteristic with an increase of chromium content. There is no typical passive region on the polarization curves of an ultra high strength stainless steel, AerMet 100 steel, and 300M steel. However, chromium improves the corrosion resistance of the stainless steel remarkably. It has the slowest corrosion rate in the salt spray test, one order of magnitude less than that of AerMet 100 and 300M steels. With the increase of chromium content, the polarization resistance becomes larger, the corrosion potential shifts towards the positive direction with a value of 545 mV, and the corrosion current density decreases in electrochemical measures in 3.5wt% NaCl solutions. Because of the higher content of chromium, the ultra high strength stainless steel has a better corrosion resistance than AerMet 100 and 300M steels.

Corrosion behavior of Mg-Mn-Ca alloy:Influences of Al,Sn and Zn

The effects of different elements including Al,Sn and Zn with ability of solution hardening on corrosion behavior of a Mg alloy have been studied.The microstructure was analyzed and the electrochemical and immersion techniques were used for corrosion studies.Scanning kelvin probe force microscopy(SKPFM)was utilized to analyze the volta-potential distribution on the surface.It was found that all additives reduced the corrosion resistance;however,Zn decreased the corrosion resistance less than Al and Sn.The corrosion rate was quantitatively explained through volta-potential difference and the second phase fraction.

Microstructure and mechanical and corrosion properties of hot-extruded Mg–Zn–Ca–(Mn)biodegradable alloys

Biodegradable Mg-based implants are widely used in clinical applications because they exhibit mechanical properties comparable to those of human bone and require no revision surgery for their removal.Among Mg-based alloys,Mg–Zn–Ca–(Mn)alloys have been extensively investigated for medical applications because the constituent elements of these alloys,Mg,Zn,Ca,and Mn,are present in human tissues as nutrient elements.In this study,we investigated the effect of the hot extrusion temperature on the microstructure,mechanical properties,and biodegradation rate of Mg–Zn–Ca–(Mn)alloys.The results showed that the addition of Mn and a decrease in the extrusion temperature resulted in grain refinement followed by an increase in the strength and a decrease in the elongation at fracture of the alloys.The alloys showed different mechanical properties along the directions parallel and perpendicular to the extrusion direction.The corrosion test of the alloys in the Hanks’solution revealed that the addition of Mn significantly reduced the corrosion rate of the alloys.The Mg–2 wt%Zn–0.7 wt%Ca–1 wt%Mn alloy hot-extruded at 300℃ with an ultimate tensile strength of 278MPa,an yield strength of 229MPa,an elongation at fracture of 10%,and a corrosion rate of 0.3 mm/year was found to be suitable for orthopedic implants.

Comparison of the corrosion behaviour of AZ31B magnesium alloy under immersion test and potentiodynamic polarization test in NaCl solution

This paper reports the comparative evaluation of the corrosion behaviour of AZ31B magnesium alloy under immersion and potentiodynamic polarization test in NaCl solution at different chloride ion concentrations,pH value and exposure time.The specimens were exposed to immersion and polarization environments in order to evaluate their corrosion rates.Empirical relationship was established to predict the corrosion rate of AZ31B magnesium alloy.Three factors,five level,central composite rotatable design matrix was used to minimize the number of experimental conditions.Response surface methodology was used to develop the relationship.The developed relationship can be effectively used to predict the corrosion rate of AZ31B magnesium alloy at 95%confidence level for both the testing.This research work proves a better corrosion resistance of AZ31B magnesium alloy at the alkaline solution than the acidic and the neutral solutions,moreover,low corrosion rate was found at low concentrated solution and higher exposure time respectively.