Search results

This paper aims to predict the localized corrosion resistance by the application of artificial neural networks. It emphasizes the importance to take into account the relationships between the physical parameters before presenting them to the network.

The work was conducted in two phases. At the beginning, the authors executed an experimental program to measure pitting corrosion resistance of carbon steel in an aqueous environment. More than 900 electrochemical experiments were conducted in chemical solutions containing different concentrations of pitting agents, corrosion inhibitors and oxidant reagents. The obtained results were collected in a table where for a combination of the experimental parameters corresponds a pitting potential Epit obtained from the corresponding electrochemical experiment. In the second step, the authors used the experimental data to train different artificial neuron networks for predicting pitting potentials.

In this step, the authors considered the relationships that the chemical parameters are likely to have between them. Two types of relationships were taken into account: chemical equilibria which are controlled by the pH and the synergistic relationships that some corrosion inhibitors may have when they are in the presence of a chemical oxidant.

This comparative study shows that adjusting the input data by considering the physical relationships between them allows a better prediction of the pitting potential. The quality of the prediction, quantified by a regression factor, is qualitatively confirmed by a statistical distribution of the gap between experimental and calculated pitting potentials.

The purpose of this study is to confirm the idea that observing the electrochemical data of a steel polarized around its open circuit potential can provide insight into its performance against pitting corrosion. To confirm this idea a two-step work was carried out. The authors collected electrochemical data through experiments and exploited them through machine learning by building neural networks capable of predicting the behaviour of the steel against the pitting corrosion.

The electrochemical experiments consist in plotting voltammograms of the steel in chemical solutions of various degrees of corrosiveness. For each experiment, the authors observe how the open-circuit potential evolves over a period of 1 min, and following this, the authors observe the current evolution when they impose a potential scan that starts from the open-circuit potential. For each of these situations, the pitting potential Epit is noted. The authors then build different artificial neural networks, which after learning, can, by receiving electrochemical data, calculate a pitting potential Epit′. The performance of the neural networks is evaluated by the correlation of Epit and Epit′.

Through this work, different types of networks were compared. The results show that recurrent or convolutional networks can better capture the temporal nature of the input data.

The results of this work support the idea that the measurable electrochemical data around the free potential of a material can be correlated with its behaviour at more anodic potentials, particularly the initiation of pits.

To constitute input data, the authors carried out electrochemical experiments. The authors performed voltammetric scans in a very cathodic potential region. The authors constituted an experimental table where for each experiment we note the current values recorded at a low polarization range and the pitting potential observed in the anodic region. This study aims to concern carbon steel used in a nuclear installation. The properties of the chemical solutions are close to that of the cooling fluid used in the circuit.

In a previous study, this paper demonstrated the effectiveness of machine learning in predicting the localized corrosion resistance of a material by considering as input data the physicochemical properties of its environment (Boucherit et al., 2019). With the present study, the authors improve the results by considering as input data, cathodic currents. The reason of such an approach is to have input data that integrate both the surface state of the material and the physicochemical properties of its environment.

The experimental table was submitted to two neural networks, namely, a recurrent network and a convolution network. The convolution network gives better pitting potential predictions. Results also prove that the prediction by observing cathodic currents is better than that obtained by considering the physicochemical properties of the solution.

The originality of the study lies in the use of cathodic currents as input data. These data contain implicit information on both the chemical environment of the material and its surface condition. This approach appears to be more efficient than considering the chemical composition of the solution as input data. The objective of this study remains, at the same time, to seek the optimal neuronal architectures and the best input data.

The evolution of a semi‐open cooling circuit of a nuclear reactor was monitored over a two year period. The work aims to provide orientation elements for preventive procedures against localised corrosion.

The water of the circuit was analysed in stagnation and in circulation, at various sampling points. The rust was analysed by neutron diffraction and the surface quality of the steel was checked by microscopic observations.

The obtained results did not confirm the presence of rust in iron compounds supported by chlorine, such as the Akaganeite, β‐FeOOH. In addition, chemical analysis of water showed that, after two years, the increase of chlorine concentration and water conductivity remained weak. Moreover, the pH was maintained within values favourable rather to the passivation of the steel.

It was deduced through this work that the dosing of the circuit with chlorine was not sufficient that it should require an annual replacement of the water.

The originality of this work resides in the evaluation of a semi‐open coolant circuit in service for ten years and located in an area subjected to seasonal sand winds.

The purpose of this paper is to illustrate the usefulness of inhibitors for the prevention of localised corrosion of carbon steel in a low‐aggressive medium. The efficiencies of two inorganic non‐toxic inhibitors are compared, associated with an oxidant.

Many experiments were conducted. For each experiment, a solution was prepared with different concentrations of pitting agent, inhibitor and oxidant. The performance was then estimated by the pitting potential taken from the voltammograms of carbon steel obtained with each solution.

The results show that the efficiency of molybdate and tungstate were comparable. The presence of iodate, which plays an oxidizing role, can be synergistic to the inhibitor but harmful if the concentration ratio is not adequate.

The interest in the use of an oxidant is that it makes it possible to reduce the inhibitor concentration, which limits the pH increase and prevents scale deposition.

This work provides useful guidance in the localised corrosion prevention of a semi‐open cooling circuit subject to seasonal sand‐storms. The obtained results from the many experiments carried out were compiled using neural networks for performance prediction.

As a common form of failure in industry, corrosion causes huge economic losses. At present, with the development of computational techniques, artificial intelligence (AI) is playing a more and more important role in the field of scientific research. This paper aims to review the application of AI in corrosion protection research.

In this paper, the role of AI in corrosion protection is systematically described in terms of anticorrosion materials and methods, corrosion image recognition and corrosion life prediction.

With efficient and in-depth data processing methods, AI can rapidly advance the research process in terms of anticorrosion materials and methods, corrosion image recognition and corrosion life prediction and save on costs.

This paper summarizes the application of AI in corrosion protection research and provides the basis for corrosion engineers to quickly and comprehensively understand the role of AI and improve production processes.

This paper aims to propose a simulation model integrated with an empirical regression analysis to provide a new mathematical formulation for automated storage and retrieval system (AS/RS) travel time estimation under class-based storage and different input/output (I/O) point vertical levels.

A simulation approach is adopted to compute the travel time under different warehouse scenarios. Simulation runs with several I/O point levels and multiple shape factor values.

The proposed model is extremely precise for both single command (SC) and dual command (DC) cycles and very well fitted for a reliable computation of travel times.

The proposed mathematical formulation for estimating the AS/RS travel time advances widely applied methodologies existing in literature. As well as, it provides a practical implication by supporting faster and more accurate travel time computations for both SC and DC cycles. However, the regression analysis is conducted based on simulated data and can be refined by numerical values coming from real warehouses.

This work provides a new simulation model and a refined mathematical equation to estimate AS/RS travel time.

The purpose of this paper is to extract electrochemical reaction kinetics parameters, such as Tafel slope, exchange current density and equilibrium potential, which cannot be directly measured, this study aims to propose an improved particle swarm optimization (PSO) algorithm.

In traditional PSO algorithms, each particle’s historical optimal solution is compared with the global optimal solution in each iteration step, and the optimal solution is replaced with a certain probability to achieve the goal of jumping out of the local optimum. However, this will to some extent undermine the (true) optimal solution. In view of this, this study has improved the traditional algorithm: at each iteration of each particle, the historical optimal solution is not compared with the global optimal solution. Instead, after all particles have iterated, the optimal solution is selected and compared with the global optimal solution and then the optimal solution is replaced with a certain probability. This to some extent protects the global optimal solution.

The polarization curve plotted by this equation is in good agreement with the experimental values, which demonstrates the reliability of this algorithm and provides a new method for measuring electrochemical parameters.

This study has improved the traditional method, which has high accuracy and can provide great support for corrosion research.

The aim of this paper is to study the effect of the parametric sensitivity of all critical parameters of feed water and other operating variables on the corrosion rate and oxide scale deposition on economizer tubes of a typical coal-fired 250-MW boiler.

In this paper, a multilayer perceptron-based artificial neural network (ANN) model has been developed to envisage the corrosion rate and oxide scale deposition rate in economizer tubes of a coal-fired boiler. The neural network architecture has been optimized using an efficient gradient-based network optimization algorithm to minimize the training and testing errors rapidly during simulation runs.

The parametric sensitivity of all critical parameters of feed water and other operating variables on the corrosion rate and oxide scale deposition activities has been investigated. It has been observed that dissolved oxygen, dissolved copper content, residual hydrazine content and pH of the feed water have a relatively predominant influence on the corrosion rate, whereas dissolved iron content, silica content, pH and temperature of the feed water have a moderately major influence on oxide scale deposition phenomenon. There has been very good agreement between ANN model predictions and the measured values of corrosion rate and oxide scale deposition rate substantiated by the regression fit between these values.

This paper details the development of an alternative model to accurately predict corrosion rate and deposition rate on the inner surface of economizer tubes of a boiler over first principle-based kinetic model.

Pitting inhibition efficiency of SO₄⁻ and NO₃⁻ on AISI 316L stainless steel in contact with Cl⁻-containing fiber dyeing solutions together with the influence of the anions on absorption behavior of the solutions were investigated. The purpose of the study is to experimentally determine an optimized dyeing solution efficient on both – inhibition of the steel’s pitting and exhaustion of the dyes dissolved.

Methods such as electrochemical cyclic polarization, UV-visible range spectrophotometry and scanning electron microscopy have been used to assess the performance of two inhibitors on both pitting inhibition of the steel and dissolving ability over the reactive dyes. To find out a promising dyeing solution mixture in both aspects, Cl content of the original dyeing solution was replaced gradually with the inhibiting anions, where the total anionic content was kept constant to unchange the dye exhaustion potential of the solution. Then, those solutions came out with diverse pitting inhibition, and dye absorption levels were compared together for reducing/avoiding the pitting issues of the reactive dyeing vessels of the industry.

Rather high absorption levels detected by visible range spectrophotometry on the solutions showing sound inhibition levels indicated possibility of unaltered reactive dyeing qualities with an enhanced vessel lifetime as the inhibitive anions replace Cl⁻. Nitrate performed better than sulfate both on inhibition and absorption in the dyeing solutions. Also, 316L vessels became open to an extra anodic protection in inhibitor added solutions.

The findings are valid for a certain group of reactive dyes and dyeing solutions held at 70°C. However, the testing methods are available to almost any dyeing solution and dyeing temperature.

The work presents a combined testing of pitting inhibition and absorption behavior of dyeing solutions involving Cl⁻ that has not been reported so far. It shows that solution recipes least harmful to the steel vessels can be outlined for various reactive or other types of dye groups.