A Machine Learning-Based Model for Predicting Atmospheric Corrosion Rate of Carbon Steel

The purpose of this study is to develop a practical artificial neural network (ANN) model for predicting the atmospheric corrosion rate of carbon steel. A set of 240 data samples, which are collected from the experimental results of atmospheric corrosion in tropical climate conditions, are utilized to develop the ANN model. Accordingly, seven meteorological and chemical factors of corrosion, namely, the average temperature, the average relative humidity, the total rainfall, the time of wetness, the hours of sunshine, the average chloride ion concentration, and the average sulfur dioxide deposition rate, are used as input variables for the ANN model. Meanwhile, the atmospheric corrosion rate of carbon steel is considered as the output variable. An optimal ANN model with a high coefficient of determination of 0.999 and a small root mean square error of 0.281 mg/m2.month is retained to predict the corrosion rate. Moreover, the sensitivity analysis shows that the rainfall and hours of sunshine are the most influential parameters on predicting the atmospheric corrosion rate, whereas the average chloride ion concentration, the average temperature, and the time of wetness are less sensitive to the atmospheric corrosion rate. An ANN-based formula, which accommodates all input parameters, is thereafter proposed to estimate the atmospheric corrosion rate of carbon steel. Finally, a graphical user interface is developed for calculating the atmospheric corrosion rate of carbon steel in tropical climate conditions.

Moisture Dry-Out Capability of Steel-Faced Mineral Wool Insulated Sandwich Panels

Moisture dry-out from steel-faced insulated sandwich panels has previously received little attention from researchers. This paper reports the results from laboratory tests and dynamic heat, air, and moisture transport simulations of the moisture dry-out capabilities of a steel-faced sandwich panel with a mineral wool core. Three test walls (TWs) with dimensions of 1.2 m × 0.4 m × 0.23 m were put above water containers to examine the moisture transport through the TWs. A calibrated simulation model was used to investigate the hygrothermal regime of a sandwich panel wall enclosure with different initial moisture contents and panel joint tightening tapes. The moisture dry-out capacity of the studied sandwich panels is limited (up to 2 g/day through a 30-mm-wide and 3-m-long vertical joint without tapes). When the vertical joint was covered with a vapour-permeable tape, the moisture dry-out was reduced to 1 g/day and when the joint was covered with a vapour-retarding tape, the dry-out was negligible. A very small amount of rain would be enough to raise the moisture content to water vapour saturation levels inside the sandwich wall, had the rain ingressed the enclosure. The calculated time of wetness (TOW) on the internal surface of the outer steel sheet stayed indefinitely at about 5500 h/year when vapour-retarding tapes were used and the initial relative humidity (RH) was over 80%. TOW stabilised to about 2000 h/year when a vapour-permeable tape was used regardless of the initial humidity inside the panel. A vapour-permeable tape allowed moisture dry-out but also vapour diffusion from the outside environment. To minimise the risk of moisture damage, avoiding moisture ingress during construction time or due to accidents is necessary. Additionally, a knowledge-based method is recommended to manage moisture safety during the construction process.

Corrosive Environment Factors and their Influence on the Development of Weathering Steel Corrosion Products

This article deals with the topic of atmospheric corrosion. Atmospheric corrosion causes damage to nearly 80% of all existing steel structures. The main parameters of atmospheric corrosion are the time of wetness (TOW), air temperature and aggressive corrosive agents such as chlorides, sulfur dioxide and others. Currently, low alloy steels with improved atmospheric corrosion resistance called weathering steels are used for the steel structures located in outdoor environment. A protective layer of corrosion products is created on the steel surface and this layer can reduce continuation of corrosion of steel. The time of wetness together with the effect of aggressive corrosive agents are various for surfaces oriented vertically or horizontally. Experimental tests of atmospheric weathering steel were carried out to monitor the impact of location and position of surface on the different constructions. These tests allow monitoring the development of corrosion products in real exposures. The article presents a part of the research, which includes monitoring the development of the thickness of corrosion products with regard to the position on the structure. Research is developed to refine of prediction models with the aim of improving determination of corrosion losses during the service life of the structure. Second part of these experiments is dedicated to measuring the deposition rate of chlorides. Chlorides have a corrosive impact on the steel surface. Under normal conditions the chlorides does not create suitable environment for the development of a protective layer of corrosion products.

The Influence of Test-Panel Orientation and Exposure Angle on the Corrosion Rate of Carbon Steel. Mathematical Modelling

The effects of both test-panel orientation and exposure angle on the atmospheric corrosion rates of carbon steel probes exposed to a marine atmosphere were investigated. Test samples were exposed in a tree-shape metallic frame with either three exposure angles of 30°, 45° and 60° and orientation north-northeast (N-NE), or eight different orientation angles around a circumference. It was found that the experimental corrosion rates of carbon steel decreased for the specimens exposed with greater exposure angles, whereas the highest corrosion rates were found for those oriented to N-NE due to the influence of the prevailing winds. The obtained data obtained were fitted using the bi-logarithmic law and its variations as to take in account the amounts of pollutants and the time of wetness (TOW) for each particular case with somewhat good agreement, although these models failed when all the effects were considered simultaneously. In this work, we propose a new mathematical model including qualitative variables to account for the effects of both exposure and orientation angles while producing the highest quality fits. The goodness of the fit was used to determine the performance of the mathematical models.