Abstract

The formation of pitting is a major problem in most metals, which is caused by extremely localized corrosion that creates small holes in metal and subsequently, it changes into cracks under mechanical load, thermo-mechanical stress, and corrosion process factors. This research aims to study pit to crack transition phenomenon of steel boiler heat tubes under cyclic thermal load, and mathematical modeling as well as Artificial Neural Networks (ANN) used to estimate the cycles takes to initiate a crack. In this study, the pit-to-crack transition model is developed mathematically, and the effects of stress intensity factor on the number of cycles to initiate crack and pit size are studied for steam tubes under thermal stress at 500℃. The ANN model is designed to predict the number of cycles required for the transition from pit to crack. The novelty of the approach lies in the use of ANN model for the complex behavior of materials under cyclic thermal loading. The stress intensity factor is a parameter that amplifies the magnitude of applied stress that includes the geometric parameter. In-pit-to-crack transition stage stress intensity factor-based approach and volumetric pit growth rate used. The fit regression of all R-values of the output pit size and number of cycles is 0.99195 and 0.9954 respectively showing good agreement for the obtained results using ANN. In addition, the comparison of mathematical model predicted results using equations and ANN predicted outputs using MATLAB® for pit size, and number of cycles shows good agreement in results. In addition, the comparison of mathematical model predicted results using equations and ANN predicted outputs using MATLAB® for pit size, and number of cycles shows good agreement in results. Hence, the formation of pitting problems in most of the metals can be effectively analyzed and reduced by using this research study.

Citations

Author (1)